Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- google_t5/t5_base_amazon/README.md +87 -0
- google_t5/t5_base_amazon/all_results.json +23 -0
- google_t5/t5_base_amazon/checkpoint-700/config.json +113 -0
- google_t5/t5_base_amazon/checkpoint-700/model.safetensors +3 -0
- google_t5/t5_base_amazon/checkpoint-700/optimizer.pt +3 -0
- google_t5/t5_base_amazon/checkpoint-700/rng_state_0.pth +3 -0
- google_t5/t5_base_amazon/checkpoint-700/rng_state_1.pth +3 -0
- google_t5/t5_base_amazon/checkpoint-700/scheduler.pt +3 -0
- google_t5/t5_base_amazon/checkpoint-700/special_tokens_map.json +107 -0
- google_t5/t5_base_amazon/checkpoint-700/spiece.model +3 -0
- google_t5/t5_base_amazon/checkpoint-700/tokenizer.json +0 -0
- google_t5/t5_base_amazon/checkpoint-700/tokenizer_config.json +937 -0
- google_t5/t5_base_amazon/checkpoint-700/trainer_state.json +665 -0
- google_t5/t5_base_amazon/checkpoint-700/training_args.bin +3 -0
- google_t5/t5_base_amazon/config.json +113 -0
- google_t5/t5_base_amazon/eval_results.json +11 -0
- google_t5/t5_base_amazon/model.safetensors +3 -0
- google_t5/t5_base_amazon/run.log +4 -0
- google_t5/t5_base_amazon/special_tokens_map.json +107 -0
- google_t5/t5_base_amazon/spiece.model +3 -0
- google_t5/t5_base_amazon/test_results.json +10 -0
- google_t5/t5_base_amazon/tokenizer.json +0 -0
- google_t5/t5_base_amazon/tokenizer_config.json +937 -0
- google_t5/t5_base_amazon/train_results.json +8 -0
- google_t5/t5_base_amazon/trainer_state.json +1070 -0
- google_t5/t5_base_amazon/training_args.bin +3 -0
- google_t5/t5_base_ledgar/README.md +93 -0
- google_t5/t5_base_ledgar/all_results.json +23 -0
- google_t5/t5_base_ledgar/checkpoint-2800/config.json +267 -0
- google_t5/t5_base_ledgar/checkpoint-2800/model.safetensors +3 -0
- google_t5/t5_base_ledgar/checkpoint-2800/optimizer.pt +3 -0
- google_t5/t5_base_ledgar/checkpoint-2800/rng_state_0.pth +3 -0
- google_t5/t5_base_ledgar/checkpoint-2800/rng_state_1.pth +3 -0
- google_t5/t5_base_ledgar/checkpoint-2800/scheduler.pt +3 -0
- google_t5/t5_base_ledgar/checkpoint-2800/special_tokens_map.json +107 -0
- google_t5/t5_base_ledgar/checkpoint-2800/spiece.model +3 -0
- google_t5/t5_base_ledgar/checkpoint-2800/tokenizer.json +0 -0
- google_t5/t5_base_ledgar/checkpoint-2800/tokenizer_config.json +937 -0
- google_t5/t5_base_ledgar/checkpoint-2800/trainer_state.json +1113 -0
- google_t5/t5_base_ledgar/checkpoint-2800/training_args.bin +3 -0
- google_t5/t5_base_ledgar/config.json +267 -0
- google_t5/t5_base_ledgar/eval_results.json +11 -0
- google_t5/t5_base_ledgar/model.safetensors +3 -0
- google_t5/t5_base_ledgar/run.log +4 -0
- google_t5/t5_base_ledgar/special_tokens_map.json +107 -0
- google_t5/t5_base_ledgar/spiece.model +3 -0
- google_t5/t5_base_ledgar/test_results.json +10 -0
- google_t5/t5_base_ledgar/tokenizer.json +0 -0
- google_t5/t5_base_ledgar/tokenizer_config.json +937 -0
- google_t5/t5_base_ledgar/train_results.json +8 -0
google_t5/t5_base_amazon/README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google-t5/t5-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: t5_base_amazon
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# t5_base_amazon
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5565
|
| 21 |
+
- Accuracy: 0.8399
|
| 22 |
+
- F1 Macro: 0.8113
|
| 23 |
+
- F1 Micro: 0.8399
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0005
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 16
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 2
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- total_eval_batch_size: 32
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 3.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
|
| 58 |
+
| 1.2275 | 0.13 | 50 | 1.0353 | 0.6950 | 0.6073 | 0.6950 |
|
| 59 |
+
| 0.8341 | 0.26 | 100 | 0.8838 | 0.7385 | 0.6814 | 0.7385 |
|
| 60 |
+
| 0.7773 | 0.39 | 150 | 0.7473 | 0.7833 | 0.7340 | 0.7833 |
|
| 61 |
+
| 0.7188 | 0.53 | 200 | 0.7024 | 0.7925 | 0.7433 | 0.7925 |
|
| 62 |
+
| 0.7483 | 0.66 | 250 | 0.7056 | 0.7872 | 0.7396 | 0.7872 |
|
| 63 |
+
| 0.6228 | 0.79 | 300 | 0.6338 | 0.8129 | 0.7636 | 0.8129 |
|
| 64 |
+
| 0.7089 | 0.92 | 350 | 0.6130 | 0.8208 | 0.7963 | 0.8208 |
|
| 65 |
+
| 0.5055 | 1.05 | 400 | 0.5939 | 0.8300 | 0.8075 | 0.8300 |
|
| 66 |
+
| 0.3942 | 1.18 | 450 | 0.6021 | 0.8241 | 0.7916 | 0.8241 |
|
| 67 |
+
| 0.4248 | 1.32 | 500 | 0.5956 | 0.8300 | 0.8060 | 0.8300 |
|
| 68 |
+
| 0.3595 | 1.45 | 550 | 0.6173 | 0.8175 | 0.7897 | 0.8175 |
|
| 69 |
+
| 0.5263 | 1.58 | 600 | 0.6170 | 0.8162 | 0.7908 | 0.8162 |
|
| 70 |
+
| 0.5153 | 1.71 | 650 | 0.6007 | 0.8327 | 0.8043 | 0.8327 |
|
| 71 |
+
| 0.4237 | 1.84 | 700 | 0.5565 | 0.8399 | 0.8113 | 0.8399 |
|
| 72 |
+
| 0.3852 | 1.97 | 750 | 0.5631 | 0.8439 | 0.8146 | 0.8439 |
|
| 73 |
+
| 0.1916 | 2.11 | 800 | 0.5848 | 0.8439 | 0.8132 | 0.8439 |
|
| 74 |
+
| 0.2108 | 2.24 | 850 | 0.6054 | 0.8432 | 0.8094 | 0.8432 |
|
| 75 |
+
| 0.1752 | 2.37 | 900 | 0.6142 | 0.8439 | 0.8131 | 0.8439 |
|
| 76 |
+
| 0.1502 | 2.5 | 950 | 0.6100 | 0.8452 | 0.8119 | 0.8452 |
|
| 77 |
+
| 0.2253 | 2.63 | 1000 | 0.6084 | 0.8439 | 0.8228 | 0.8439 |
|
| 78 |
+
| 0.2193 | 2.76 | 1050 | 0.6062 | 0.8485 | 0.8171 | 0.8485 |
|
| 79 |
+
| 0.2182 | 2.89 | 1100 | 0.5966 | 0.8498 | 0.8182 | 0.8498 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.39.0.dev0
|
| 85 |
+
- Pytorch 2.2.1+cu121
|
| 86 |
+
- Datasets 2.18.0
|
| 87 |
+
- Tokenizers 0.15.2
|
google_t5/t5_base_amazon/all_results.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8399209486166008,
|
| 4 |
+
"eval_f1_macro": 0.8112898753723374,
|
| 5 |
+
"eval_f1_micro": 0.8399209486166008,
|
| 6 |
+
"eval_loss": 0.5565423369407654,
|
| 7 |
+
"eval_runtime": 3.8107,
|
| 8 |
+
"eval_samples": 1518,
|
| 9 |
+
"eval_samples_per_second": 398.35,
|
| 10 |
+
"eval_steps_per_second": 12.596,
|
| 11 |
+
"test_accuracy": 0.857707509881423,
|
| 12 |
+
"test_f1_macro": 0.8293055942786999,
|
| 13 |
+
"test_f1_micro": 0.857707509881423,
|
| 14 |
+
"test_loss": 0.5306673645973206,
|
| 15 |
+
"test_runtime": 3.7633,
|
| 16 |
+
"test_samples_per_second": 403.37,
|
| 17 |
+
"test_steps_per_second": 12.755,
|
| 18 |
+
"train_loss": 0.5285837122222834,
|
| 19 |
+
"train_runtime": 447.0645,
|
| 20 |
+
"train_samples": 12144,
|
| 21 |
+
"train_samples_per_second": 81.492,
|
| 22 |
+
"train_steps_per_second": 2.55
|
| 23 |
+
}
|
google_t5/t5_base_amazon/checkpoint-700/config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-t5/t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"finetuning_task": "text-classification",
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "0",
|
| 18 |
+
"1": "1",
|
| 19 |
+
"2": "10",
|
| 20 |
+
"3": "11",
|
| 21 |
+
"4": "12",
|
| 22 |
+
"5": "13",
|
| 23 |
+
"6": "14",
|
| 24 |
+
"7": "15",
|
| 25 |
+
"8": "16",
|
| 26 |
+
"9": "17",
|
| 27 |
+
"10": "18",
|
| 28 |
+
"11": "19",
|
| 29 |
+
"12": "2",
|
| 30 |
+
"13": "20",
|
| 31 |
+
"14": "21",
|
| 32 |
+
"15": "22",
|
| 33 |
+
"16": "3",
|
| 34 |
+
"17": "4",
|
| 35 |
+
"18": "5",
|
| 36 |
+
"19": "6",
|
| 37 |
+
"20": "7",
|
| 38 |
+
"21": "8",
|
| 39 |
+
"22": "9"
|
| 40 |
+
},
|
| 41 |
+
"initializer_factor": 1.0,
|
| 42 |
+
"is_encoder_decoder": true,
|
| 43 |
+
"is_gated_act": false,
|
| 44 |
+
"label2id": {
|
| 45 |
+
"0": 0,
|
| 46 |
+
"1": 1,
|
| 47 |
+
"10": 2,
|
| 48 |
+
"11": 3,
|
| 49 |
+
"12": 4,
|
| 50 |
+
"13": 5,
|
| 51 |
+
"14": 6,
|
| 52 |
+
"15": 7,
|
| 53 |
+
"16": 8,
|
| 54 |
+
"17": 9,
|
| 55 |
+
"18": 10,
|
| 56 |
+
"19": 11,
|
| 57 |
+
"2": 12,
|
| 58 |
+
"20": 13,
|
| 59 |
+
"21": 14,
|
| 60 |
+
"22": 15,
|
| 61 |
+
"3": 16,
|
| 62 |
+
"4": 17,
|
| 63 |
+
"5": 18,
|
| 64 |
+
"6": 19,
|
| 65 |
+
"7": 20,
|
| 66 |
+
"8": 21,
|
| 67 |
+
"9": 22
|
| 68 |
+
},
|
| 69 |
+
"layer_norm_epsilon": 1e-06,
|
| 70 |
+
"model_type": "t5",
|
| 71 |
+
"n_positions": 512,
|
| 72 |
+
"num_decoder_layers": 12,
|
| 73 |
+
"num_heads": 12,
|
| 74 |
+
"num_layers": 12,
|
| 75 |
+
"output_past": true,
|
| 76 |
+
"pad_token_id": 0,
|
| 77 |
+
"problem_type": "single_label_classification",
|
| 78 |
+
"relative_attention_max_distance": 128,
|
| 79 |
+
"relative_attention_num_buckets": 32,
|
| 80 |
+
"task_specific_params": {
|
| 81 |
+
"summarization": {
|
| 82 |
+
"early_stopping": true,
|
| 83 |
+
"length_penalty": 2.0,
|
| 84 |
+
"max_length": 200,
|
| 85 |
+
"min_length": 30,
|
| 86 |
+
"no_repeat_ngram_size": 3,
|
| 87 |
+
"num_beams": 4,
|
| 88 |
+
"prefix": "summarize: "
|
| 89 |
+
},
|
| 90 |
+
"translation_en_to_de": {
|
| 91 |
+
"early_stopping": true,
|
| 92 |
+
"max_length": 300,
|
| 93 |
+
"num_beams": 4,
|
| 94 |
+
"prefix": "translate English to German: "
|
| 95 |
+
},
|
| 96 |
+
"translation_en_to_fr": {
|
| 97 |
+
"early_stopping": true,
|
| 98 |
+
"max_length": 300,
|
| 99 |
+
"num_beams": 4,
|
| 100 |
+
"prefix": "translate English to French: "
|
| 101 |
+
},
|
| 102 |
+
"translation_en_to_ro": {
|
| 103 |
+
"early_stopping": true,
|
| 104 |
+
"max_length": 300,
|
| 105 |
+
"num_beams": 4,
|
| 106 |
+
"prefix": "translate English to Romanian: "
|
| 107 |
+
}
|
| 108 |
+
},
|
| 109 |
+
"torch_dtype": "float32",
|
| 110 |
+
"transformers_version": "4.39.0.dev0",
|
| 111 |
+
"use_cache": true,
|
| 112 |
+
"vocab_size": 32128
|
| 113 |
+
}
|
google_t5/t5_base_amazon/checkpoint-700/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:793ee165edf28806fd5d823c7f8559e2764d24d6a360fd01fcaab3c3b51a43b7
|
| 3 |
+
size 894081308
|
google_t5/t5_base_amazon/checkpoint-700/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6826461ddc187854774503393d07d2bab54a9545971ea1a146982ab3d4c6e8d
|
| 3 |
+
size 1788314362
|
google_t5/t5_base_amazon/checkpoint-700/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c07361a99a91c0c9b6371248704b1b3dca05b07d15619b60759b3d2ff74fd1f
|
| 3 |
+
size 14512
|
google_t5/t5_base_amazon/checkpoint-700/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cc509d254e83e747331fff71c722f69fec583ca0a30405bbfed8debff379aef
|
| 3 |
+
size 14512
|
google_t5/t5_base_amazon/checkpoint-700/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf00ee845c47f044a643cdd9c93d8563aaf47d1f4581854acf7abb83f7302f20
|
| 3 |
+
size 1064
|
google_t5/t5_base_amazon/checkpoint-700/special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
google_t5/t5_base_amazon/checkpoint-700/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
google_t5/t5_base_amazon/checkpoint-700/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
google_t5/t5_base_amazon/checkpoint-700/tokenizer_config.json
ADDED
|
@@ -0,0 +1,937 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 512,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"tokenizer_class": "T5Tokenizer",
|
| 936 |
+
"unk_token": "<unk>"
|
| 937 |
+
}
|
google_t5/t5_base_amazon/checkpoint-700/trainer_state.json
ADDED
|
@@ -0,0 +1,665 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5565423369407654,
|
| 3 |
+
"best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/google_t5/t5_base_amazon/checkpoint-700",
|
| 4 |
+
"epoch": 1.8421052631578947,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 700,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 2.8495495319366455,
|
| 14 |
+
"learning_rate": 0.0004956140350877193,
|
| 15 |
+
"loss": 3.117,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 2.5190072059631348,
|
| 21 |
+
"learning_rate": 0.0004912280701754386,
|
| 22 |
+
"loss": 2.7209,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 2.294928789138794,
|
| 28 |
+
"learning_rate": 0.0004868421052631579,
|
| 29 |
+
"loss": 2.0205,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 3.267091751098633,
|
| 35 |
+
"learning_rate": 0.0004824561403508772,
|
| 36 |
+
"loss": 1.2866,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.13,
|
| 41 |
+
"grad_norm": 4.188276767730713,
|
| 42 |
+
"learning_rate": 0.00047807017543859647,
|
| 43 |
+
"loss": 1.2275,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13,
|
| 48 |
+
"eval_accuracy": 0.6949934123847167,
|
| 49 |
+
"eval_f1_macro": 0.6073038050199799,
|
| 50 |
+
"eval_f1_micro": 0.6949934123847167,
|
| 51 |
+
"eval_loss": 1.035279631614685,
|
| 52 |
+
"eval_runtime": 3.7814,
|
| 53 |
+
"eval_samples_per_second": 401.442,
|
| 54 |
+
"eval_steps_per_second": 12.694,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.16,
|
| 59 |
+
"grad_norm": 6.240413665771484,
|
| 60 |
+
"learning_rate": 0.00047368421052631577,
|
| 61 |
+
"loss": 1.0172,
|
| 62 |
+
"step": 60
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.18,
|
| 66 |
+
"grad_norm": 3.5446884632110596,
|
| 67 |
+
"learning_rate": 0.0004692982456140351,
|
| 68 |
+
"loss": 1.0344,
|
| 69 |
+
"step": 70
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.21,
|
| 73 |
+
"grad_norm": 4.263936519622803,
|
| 74 |
+
"learning_rate": 0.00046491228070175437,
|
| 75 |
+
"loss": 0.8594,
|
| 76 |
+
"step": 80
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.24,
|
| 80 |
+
"grad_norm": 3.0901923179626465,
|
| 81 |
+
"learning_rate": 0.0004605263157894737,
|
| 82 |
+
"loss": 0.8781,
|
| 83 |
+
"step": 90
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.26,
|
| 87 |
+
"grad_norm": 2.737272262573242,
|
| 88 |
+
"learning_rate": 0.000456140350877193,
|
| 89 |
+
"loss": 0.8341,
|
| 90 |
+
"step": 100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.26,
|
| 94 |
+
"eval_accuracy": 0.738471673254282,
|
| 95 |
+
"eval_f1_macro": 0.6814380216401201,
|
| 96 |
+
"eval_f1_micro": 0.738471673254282,
|
| 97 |
+
"eval_loss": 0.8838083744049072,
|
| 98 |
+
"eval_runtime": 3.8044,
|
| 99 |
+
"eval_samples_per_second": 399.016,
|
| 100 |
+
"eval_steps_per_second": 12.617,
|
| 101 |
+
"step": 100
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.29,
|
| 105 |
+
"grad_norm": 2.692996025085449,
|
| 106 |
+
"learning_rate": 0.00045175438596491233,
|
| 107 |
+
"loss": 0.9941,
|
| 108 |
+
"step": 110
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.32,
|
| 112 |
+
"grad_norm": 2.3376717567443848,
|
| 113 |
+
"learning_rate": 0.0004473684210526316,
|
| 114 |
+
"loss": 0.8984,
|
| 115 |
+
"step": 120
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.34,
|
| 119 |
+
"grad_norm": 2.112525224685669,
|
| 120 |
+
"learning_rate": 0.0004429824561403509,
|
| 121 |
+
"loss": 0.909,
|
| 122 |
+
"step": 130
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.37,
|
| 126 |
+
"grad_norm": 2.8785059452056885,
|
| 127 |
+
"learning_rate": 0.0004385964912280702,
|
| 128 |
+
"loss": 0.7654,
|
| 129 |
+
"step": 140
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.39,
|
| 133 |
+
"grad_norm": 2.3538177013397217,
|
| 134 |
+
"learning_rate": 0.0004342105263157895,
|
| 135 |
+
"loss": 0.7773,
|
| 136 |
+
"step": 150
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.39,
|
| 140 |
+
"eval_accuracy": 0.7832674571805006,
|
| 141 |
+
"eval_f1_macro": 0.7339618917892343,
|
| 142 |
+
"eval_f1_micro": 0.7832674571805006,
|
| 143 |
+
"eval_loss": 0.7473268508911133,
|
| 144 |
+
"eval_runtime": 3.8195,
|
| 145 |
+
"eval_samples_per_second": 397.435,
|
| 146 |
+
"eval_steps_per_second": 12.567,
|
| 147 |
+
"step": 150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.42,
|
| 151 |
+
"grad_norm": 2.850787401199341,
|
| 152 |
+
"learning_rate": 0.0004298245614035088,
|
| 153 |
+
"loss": 0.7734,
|
| 154 |
+
"step": 160
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.45,
|
| 158 |
+
"grad_norm": 3.4294583797454834,
|
| 159 |
+
"learning_rate": 0.0004254385964912281,
|
| 160 |
+
"loss": 0.7876,
|
| 161 |
+
"step": 170
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.47,
|
| 165 |
+
"grad_norm": 2.0919501781463623,
|
| 166 |
+
"learning_rate": 0.00042105263157894734,
|
| 167 |
+
"loss": 0.7329,
|
| 168 |
+
"step": 180
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.5,
|
| 172 |
+
"grad_norm": 5.026761531829834,
|
| 173 |
+
"learning_rate": 0.0004166666666666667,
|
| 174 |
+
"loss": 0.8396,
|
| 175 |
+
"step": 190
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.53,
|
| 179 |
+
"grad_norm": 2.3940157890319824,
|
| 180 |
+
"learning_rate": 0.000412280701754386,
|
| 181 |
+
"loss": 0.7188,
|
| 182 |
+
"step": 200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.53,
|
| 186 |
+
"eval_accuracy": 0.7924901185770751,
|
| 187 |
+
"eval_f1_macro": 0.7432732481576452,
|
| 188 |
+
"eval_f1_micro": 0.7924901185770751,
|
| 189 |
+
"eval_loss": 0.7023962140083313,
|
| 190 |
+
"eval_runtime": 3.8263,
|
| 191 |
+
"eval_samples_per_second": 396.73,
|
| 192 |
+
"eval_steps_per_second": 12.545,
|
| 193 |
+
"step": 200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.55,
|
| 197 |
+
"grad_norm": 2.965258836746216,
|
| 198 |
+
"learning_rate": 0.00040789473684210524,
|
| 199 |
+
"loss": 0.66,
|
| 200 |
+
"step": 210
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.58,
|
| 204 |
+
"grad_norm": 3.2059409618377686,
|
| 205 |
+
"learning_rate": 0.00040350877192982455,
|
| 206 |
+
"loss": 0.7795,
|
| 207 |
+
"step": 220
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.61,
|
| 211 |
+
"grad_norm": 4.9381537437438965,
|
| 212 |
+
"learning_rate": 0.0003991228070175439,
|
| 213 |
+
"loss": 0.7163,
|
| 214 |
+
"step": 230
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.63,
|
| 218 |
+
"grad_norm": 4.937159061431885,
|
| 219 |
+
"learning_rate": 0.00039473684210526315,
|
| 220 |
+
"loss": 0.7546,
|
| 221 |
+
"step": 240
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.66,
|
| 225 |
+
"grad_norm": 2.786454439163208,
|
| 226 |
+
"learning_rate": 0.00039035087719298245,
|
| 227 |
+
"loss": 0.7483,
|
| 228 |
+
"step": 250
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.66,
|
| 232 |
+
"eval_accuracy": 0.7872200263504612,
|
| 233 |
+
"eval_f1_macro": 0.7396308270254102,
|
| 234 |
+
"eval_f1_micro": 0.7872200263504612,
|
| 235 |
+
"eval_loss": 0.7055577039718628,
|
| 236 |
+
"eval_runtime": 3.8209,
|
| 237 |
+
"eval_samples_per_second": 397.29,
|
| 238 |
+
"eval_steps_per_second": 12.563,
|
| 239 |
+
"step": 250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.68,
|
| 243 |
+
"grad_norm": 2.2485697269439697,
|
| 244 |
+
"learning_rate": 0.00038596491228070175,
|
| 245 |
+
"loss": 0.7216,
|
| 246 |
+
"step": 260
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.71,
|
| 250 |
+
"grad_norm": 3.388631582260132,
|
| 251 |
+
"learning_rate": 0.00038157894736842105,
|
| 252 |
+
"loss": 0.7437,
|
| 253 |
+
"step": 270
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.74,
|
| 257 |
+
"grad_norm": 2.945599317550659,
|
| 258 |
+
"learning_rate": 0.00037719298245614036,
|
| 259 |
+
"loss": 0.6433,
|
| 260 |
+
"step": 280
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.76,
|
| 264 |
+
"grad_norm": 2.894361972808838,
|
| 265 |
+
"learning_rate": 0.00037280701754385966,
|
| 266 |
+
"loss": 0.6333,
|
| 267 |
+
"step": 290
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.79,
|
| 271 |
+
"grad_norm": 1.8753783702850342,
|
| 272 |
+
"learning_rate": 0.00036842105263157896,
|
| 273 |
+
"loss": 0.6228,
|
| 274 |
+
"step": 300
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.79,
|
| 278 |
+
"eval_accuracy": 0.8129117259552042,
|
| 279 |
+
"eval_f1_macro": 0.7636250391666534,
|
| 280 |
+
"eval_f1_micro": 0.8129117259552042,
|
| 281 |
+
"eval_loss": 0.6337724924087524,
|
| 282 |
+
"eval_runtime": 3.8242,
|
| 283 |
+
"eval_samples_per_second": 396.945,
|
| 284 |
+
"eval_steps_per_second": 12.552,
|
| 285 |
+
"step": 300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.82,
|
| 289 |
+
"grad_norm": 3.340951442718506,
|
| 290 |
+
"learning_rate": 0.00036403508771929826,
|
| 291 |
+
"loss": 0.5978,
|
| 292 |
+
"step": 310
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.84,
|
| 296 |
+
"grad_norm": 3.2675557136535645,
|
| 297 |
+
"learning_rate": 0.00035964912280701756,
|
| 298 |
+
"loss": 0.7124,
|
| 299 |
+
"step": 320
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.87,
|
| 303 |
+
"grad_norm": 2.308924674987793,
|
| 304 |
+
"learning_rate": 0.00035526315789473687,
|
| 305 |
+
"loss": 0.7423,
|
| 306 |
+
"step": 330
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.89,
|
| 310 |
+
"grad_norm": 3.407076835632324,
|
| 311 |
+
"learning_rate": 0.0003508771929824561,
|
| 312 |
+
"loss": 0.6787,
|
| 313 |
+
"step": 340
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.92,
|
| 317 |
+
"grad_norm": 2.5976576805114746,
|
| 318 |
+
"learning_rate": 0.00034649122807017547,
|
| 319 |
+
"loss": 0.7089,
|
| 320 |
+
"step": 350
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.92,
|
| 324 |
+
"eval_accuracy": 0.8208168642951251,
|
| 325 |
+
"eval_f1_macro": 0.7962943499701793,
|
| 326 |
+
"eval_f1_micro": 0.8208168642951251,
|
| 327 |
+
"eval_loss": 0.6130083799362183,
|
| 328 |
+
"eval_runtime": 3.8233,
|
| 329 |
+
"eval_samples_per_second": 397.037,
|
| 330 |
+
"eval_steps_per_second": 12.555,
|
| 331 |
+
"step": 350
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.95,
|
| 335 |
+
"grad_norm": 2.053323745727539,
|
| 336 |
+
"learning_rate": 0.00034210526315789477,
|
| 337 |
+
"loss": 0.5299,
|
| 338 |
+
"step": 360
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.97,
|
| 342 |
+
"grad_norm": 3.201794147491455,
|
| 343 |
+
"learning_rate": 0.000337719298245614,
|
| 344 |
+
"loss": 0.7405,
|
| 345 |
+
"step": 370
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.0,
|
| 349 |
+
"grad_norm": 2.8295910358428955,
|
| 350 |
+
"learning_rate": 0.0003333333333333333,
|
| 351 |
+
"loss": 0.7584,
|
| 352 |
+
"step": 380
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.03,
|
| 356 |
+
"grad_norm": 1.9317399263381958,
|
| 357 |
+
"learning_rate": 0.0003289473684210527,
|
| 358 |
+
"loss": 0.4822,
|
| 359 |
+
"step": 390
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.05,
|
| 363 |
+
"grad_norm": 2.5840656757354736,
|
| 364 |
+
"learning_rate": 0.0003245614035087719,
|
| 365 |
+
"loss": 0.5055,
|
| 366 |
+
"step": 400
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.05,
|
| 370 |
+
"eval_accuracy": 0.8300395256916996,
|
| 371 |
+
"eval_f1_macro": 0.8075388232802375,
|
| 372 |
+
"eval_f1_micro": 0.8300395256916996,
|
| 373 |
+
"eval_loss": 0.5938563346862793,
|
| 374 |
+
"eval_runtime": 3.8245,
|
| 375 |
+
"eval_samples_per_second": 396.912,
|
| 376 |
+
"eval_steps_per_second": 12.551,
|
| 377 |
+
"step": 400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.08,
|
| 381 |
+
"grad_norm": 2.4889354705810547,
|
| 382 |
+
"learning_rate": 0.00032017543859649123,
|
| 383 |
+
"loss": 0.425,
|
| 384 |
+
"step": 410
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.11,
|
| 388 |
+
"grad_norm": 2.618088722229004,
|
| 389 |
+
"learning_rate": 0.00031578947368421053,
|
| 390 |
+
"loss": 0.3865,
|
| 391 |
+
"step": 420
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.13,
|
| 395 |
+
"grad_norm": 2.8282623291015625,
|
| 396 |
+
"learning_rate": 0.00031140350877192983,
|
| 397 |
+
"loss": 0.4543,
|
| 398 |
+
"step": 430
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.16,
|
| 402 |
+
"grad_norm": 3.4801692962646484,
|
| 403 |
+
"learning_rate": 0.00030701754385964913,
|
| 404 |
+
"loss": 0.4152,
|
| 405 |
+
"step": 440
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.18,
|
| 409 |
+
"grad_norm": 1.7531658411026,
|
| 410 |
+
"learning_rate": 0.00030263157894736844,
|
| 411 |
+
"loss": 0.3942,
|
| 412 |
+
"step": 450
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.18,
|
| 416 |
+
"eval_accuracy": 0.8241106719367589,
|
| 417 |
+
"eval_f1_macro": 0.7915647113122625,
|
| 418 |
+
"eval_f1_micro": 0.8241106719367589,
|
| 419 |
+
"eval_loss": 0.6020949482917786,
|
| 420 |
+
"eval_runtime": 3.8282,
|
| 421 |
+
"eval_samples_per_second": 396.536,
|
| 422 |
+
"eval_steps_per_second": 12.539,
|
| 423 |
+
"step": 450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.21,
|
| 427 |
+
"grad_norm": 2.6115176677703857,
|
| 428 |
+
"learning_rate": 0.0002982456140350877,
|
| 429 |
+
"loss": 0.4801,
|
| 430 |
+
"step": 460
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.24,
|
| 434 |
+
"grad_norm": 2.1855995655059814,
|
| 435 |
+
"learning_rate": 0.00029385964912280704,
|
| 436 |
+
"loss": 0.3942,
|
| 437 |
+
"step": 470
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.26,
|
| 441 |
+
"grad_norm": 2.3812382221221924,
|
| 442 |
+
"learning_rate": 0.00028947368421052634,
|
| 443 |
+
"loss": 0.485,
|
| 444 |
+
"step": 480
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.29,
|
| 448 |
+
"grad_norm": 2.102308750152588,
|
| 449 |
+
"learning_rate": 0.00028508771929824564,
|
| 450 |
+
"loss": 0.417,
|
| 451 |
+
"step": 490
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.32,
|
| 455 |
+
"grad_norm": 4.095526218414307,
|
| 456 |
+
"learning_rate": 0.0002807017543859649,
|
| 457 |
+
"loss": 0.4248,
|
| 458 |
+
"step": 500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.32,
|
| 462 |
+
"eval_accuracy": 0.8300395256916996,
|
| 463 |
+
"eval_f1_macro": 0.8060251760691185,
|
| 464 |
+
"eval_f1_micro": 0.8300395256916996,
|
| 465 |
+
"eval_loss": 0.5956056714057922,
|
| 466 |
+
"eval_runtime": 3.8218,
|
| 467 |
+
"eval_samples_per_second": 397.192,
|
| 468 |
+
"eval_steps_per_second": 12.559,
|
| 469 |
+
"step": 500
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.34,
|
| 473 |
+
"grad_norm": 3.2039239406585693,
|
| 474 |
+
"learning_rate": 0.00027631578947368425,
|
| 475 |
+
"loss": 0.4209,
|
| 476 |
+
"step": 510
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.37,
|
| 480 |
+
"grad_norm": 1.9944714307785034,
|
| 481 |
+
"learning_rate": 0.00027192982456140355,
|
| 482 |
+
"loss": 0.5373,
|
| 483 |
+
"step": 520
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.39,
|
| 487 |
+
"grad_norm": 3.2802696228027344,
|
| 488 |
+
"learning_rate": 0.0002675438596491228,
|
| 489 |
+
"loss": 0.5216,
|
| 490 |
+
"step": 530
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.42,
|
| 494 |
+
"grad_norm": 1.4747893810272217,
|
| 495 |
+
"learning_rate": 0.0002631578947368421,
|
| 496 |
+
"loss": 0.3785,
|
| 497 |
+
"step": 540
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.45,
|
| 501 |
+
"grad_norm": 1.2378747463226318,
|
| 502 |
+
"learning_rate": 0.00025877192982456146,
|
| 503 |
+
"loss": 0.3595,
|
| 504 |
+
"step": 550
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.45,
|
| 508 |
+
"eval_accuracy": 0.8175230566534915,
|
| 509 |
+
"eval_f1_macro": 0.7897278945523275,
|
| 510 |
+
"eval_f1_micro": 0.8175230566534915,
|
| 511 |
+
"eval_loss": 0.6172593832015991,
|
| 512 |
+
"eval_runtime": 3.8184,
|
| 513 |
+
"eval_samples_per_second": 397.551,
|
| 514 |
+
"eval_steps_per_second": 12.571,
|
| 515 |
+
"step": 550
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.47,
|
| 519 |
+
"grad_norm": 2.6604156494140625,
|
| 520 |
+
"learning_rate": 0.0002543859649122807,
|
| 521 |
+
"loss": 0.4231,
|
| 522 |
+
"step": 560
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.5,
|
| 526 |
+
"grad_norm": 1.879952311515808,
|
| 527 |
+
"learning_rate": 0.00025,
|
| 528 |
+
"loss": 0.4555,
|
| 529 |
+
"step": 570
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.53,
|
| 533 |
+
"grad_norm": 3.9825170040130615,
|
| 534 |
+
"learning_rate": 0.0002456140350877193,
|
| 535 |
+
"loss": 0.3988,
|
| 536 |
+
"step": 580
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.55,
|
| 540 |
+
"grad_norm": 2.999025583267212,
|
| 541 |
+
"learning_rate": 0.0002412280701754386,
|
| 542 |
+
"loss": 0.3854,
|
| 543 |
+
"step": 590
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.58,
|
| 547 |
+
"grad_norm": 2.778930425643921,
|
| 548 |
+
"learning_rate": 0.00023684210526315788,
|
| 549 |
+
"loss": 0.5263,
|
| 550 |
+
"step": 600
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.58,
|
| 554 |
+
"eval_accuracy": 0.8162055335968379,
|
| 555 |
+
"eval_f1_macro": 0.7908253969964322,
|
| 556 |
+
"eval_f1_micro": 0.8162055335968379,
|
| 557 |
+
"eval_loss": 0.6170048117637634,
|
| 558 |
+
"eval_runtime": 3.838,
|
| 559 |
+
"eval_samples_per_second": 395.517,
|
| 560 |
+
"eval_steps_per_second": 12.506,
|
| 561 |
+
"step": 600
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.61,
|
| 565 |
+
"grad_norm": 2.2400004863739014,
|
| 566 |
+
"learning_rate": 0.00023245614035087719,
|
| 567 |
+
"loss": 0.443,
|
| 568 |
+
"step": 610
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.63,
|
| 572 |
+
"grad_norm": 2.5458765029907227,
|
| 573 |
+
"learning_rate": 0.0002280701754385965,
|
| 574 |
+
"loss": 0.4106,
|
| 575 |
+
"step": 620
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.66,
|
| 579 |
+
"grad_norm": 2.955345392227173,
|
| 580 |
+
"learning_rate": 0.0002236842105263158,
|
| 581 |
+
"loss": 0.4078,
|
| 582 |
+
"step": 630
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.68,
|
| 586 |
+
"grad_norm": 3.5653369426727295,
|
| 587 |
+
"learning_rate": 0.0002192982456140351,
|
| 588 |
+
"loss": 0.4746,
|
| 589 |
+
"step": 640
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.71,
|
| 593 |
+
"grad_norm": 1.5618356466293335,
|
| 594 |
+
"learning_rate": 0.0002149122807017544,
|
| 595 |
+
"loss": 0.5153,
|
| 596 |
+
"step": 650
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.71,
|
| 600 |
+
"eval_accuracy": 0.8326745718050066,
|
| 601 |
+
"eval_f1_macro": 0.8042732309505177,
|
| 602 |
+
"eval_f1_micro": 0.8326745718050066,
|
| 603 |
+
"eval_loss": 0.6007006168365479,
|
| 604 |
+
"eval_runtime": 3.8189,
|
| 605 |
+
"eval_samples_per_second": 397.495,
|
| 606 |
+
"eval_steps_per_second": 12.569,
|
| 607 |
+
"step": 650
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 1.74,
|
| 611 |
+
"grad_norm": 3.3417813777923584,
|
| 612 |
+
"learning_rate": 0.00021052631578947367,
|
| 613 |
+
"loss": 0.3366,
|
| 614 |
+
"step": 660
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.76,
|
| 618 |
+
"grad_norm": 3.232940912246704,
|
| 619 |
+
"learning_rate": 0.000206140350877193,
|
| 620 |
+
"loss": 0.4284,
|
| 621 |
+
"step": 670
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.79,
|
| 625 |
+
"grad_norm": 2.414170265197754,
|
| 626 |
+
"learning_rate": 0.00020175438596491227,
|
| 627 |
+
"loss": 0.4816,
|
| 628 |
+
"step": 680
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.82,
|
| 632 |
+
"grad_norm": 2.161409378051758,
|
| 633 |
+
"learning_rate": 0.00019736842105263157,
|
| 634 |
+
"loss": 0.398,
|
| 635 |
+
"step": 690
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.84,
|
| 639 |
+
"grad_norm": 2.6579811573028564,
|
| 640 |
+
"learning_rate": 0.00019298245614035088,
|
| 641 |
+
"loss": 0.4237,
|
| 642 |
+
"step": 700
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.84,
|
| 646 |
+
"eval_accuracy": 0.8399209486166008,
|
| 647 |
+
"eval_f1_macro": 0.8112898753723374,
|
| 648 |
+
"eval_f1_micro": 0.8399209486166008,
|
| 649 |
+
"eval_loss": 0.5565423369407654,
|
| 650 |
+
"eval_runtime": 3.8246,
|
| 651 |
+
"eval_samples_per_second": 396.904,
|
| 652 |
+
"eval_steps_per_second": 12.55,
|
| 653 |
+
"step": 700
|
| 654 |
+
}
|
| 655 |
+
],
|
| 656 |
+
"logging_steps": 10,
|
| 657 |
+
"max_steps": 1140,
|
| 658 |
+
"num_input_tokens_seen": 0,
|
| 659 |
+
"num_train_epochs": 3,
|
| 660 |
+
"save_steps": 50,
|
| 661 |
+
"total_flos": 3420628430356480.0,
|
| 662 |
+
"train_batch_size": 16,
|
| 663 |
+
"trial_name": null,
|
| 664 |
+
"trial_params": null
|
| 665 |
+
}
|
google_t5/t5_base_amazon/checkpoint-700/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9058d2c55809c08dfe5d631fdecbc63ece4067a6cea137e1478fddc6e29958ed
|
| 3 |
+
size 5048
|
google_t5/t5_base_amazon/config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-t5/t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"finetuning_task": "text-classification",
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "0",
|
| 18 |
+
"1": "1",
|
| 19 |
+
"2": "10",
|
| 20 |
+
"3": "11",
|
| 21 |
+
"4": "12",
|
| 22 |
+
"5": "13",
|
| 23 |
+
"6": "14",
|
| 24 |
+
"7": "15",
|
| 25 |
+
"8": "16",
|
| 26 |
+
"9": "17",
|
| 27 |
+
"10": "18",
|
| 28 |
+
"11": "19",
|
| 29 |
+
"12": "2",
|
| 30 |
+
"13": "20",
|
| 31 |
+
"14": "21",
|
| 32 |
+
"15": "22",
|
| 33 |
+
"16": "3",
|
| 34 |
+
"17": "4",
|
| 35 |
+
"18": "5",
|
| 36 |
+
"19": "6",
|
| 37 |
+
"20": "7",
|
| 38 |
+
"21": "8",
|
| 39 |
+
"22": "9"
|
| 40 |
+
},
|
| 41 |
+
"initializer_factor": 1.0,
|
| 42 |
+
"is_encoder_decoder": true,
|
| 43 |
+
"is_gated_act": false,
|
| 44 |
+
"label2id": {
|
| 45 |
+
"0": 0,
|
| 46 |
+
"1": 1,
|
| 47 |
+
"10": 2,
|
| 48 |
+
"11": 3,
|
| 49 |
+
"12": 4,
|
| 50 |
+
"13": 5,
|
| 51 |
+
"14": 6,
|
| 52 |
+
"15": 7,
|
| 53 |
+
"16": 8,
|
| 54 |
+
"17": 9,
|
| 55 |
+
"18": 10,
|
| 56 |
+
"19": 11,
|
| 57 |
+
"2": 12,
|
| 58 |
+
"20": 13,
|
| 59 |
+
"21": 14,
|
| 60 |
+
"22": 15,
|
| 61 |
+
"3": 16,
|
| 62 |
+
"4": 17,
|
| 63 |
+
"5": 18,
|
| 64 |
+
"6": 19,
|
| 65 |
+
"7": 20,
|
| 66 |
+
"8": 21,
|
| 67 |
+
"9": 22
|
| 68 |
+
},
|
| 69 |
+
"layer_norm_epsilon": 1e-06,
|
| 70 |
+
"model_type": "t5",
|
| 71 |
+
"n_positions": 512,
|
| 72 |
+
"num_decoder_layers": 12,
|
| 73 |
+
"num_heads": 12,
|
| 74 |
+
"num_layers": 12,
|
| 75 |
+
"output_past": true,
|
| 76 |
+
"pad_token_id": 0,
|
| 77 |
+
"problem_type": "single_label_classification",
|
| 78 |
+
"relative_attention_max_distance": 128,
|
| 79 |
+
"relative_attention_num_buckets": 32,
|
| 80 |
+
"task_specific_params": {
|
| 81 |
+
"summarization": {
|
| 82 |
+
"early_stopping": true,
|
| 83 |
+
"length_penalty": 2.0,
|
| 84 |
+
"max_length": 200,
|
| 85 |
+
"min_length": 30,
|
| 86 |
+
"no_repeat_ngram_size": 3,
|
| 87 |
+
"num_beams": 4,
|
| 88 |
+
"prefix": "summarize: "
|
| 89 |
+
},
|
| 90 |
+
"translation_en_to_de": {
|
| 91 |
+
"early_stopping": true,
|
| 92 |
+
"max_length": 300,
|
| 93 |
+
"num_beams": 4,
|
| 94 |
+
"prefix": "translate English to German: "
|
| 95 |
+
},
|
| 96 |
+
"translation_en_to_fr": {
|
| 97 |
+
"early_stopping": true,
|
| 98 |
+
"max_length": 300,
|
| 99 |
+
"num_beams": 4,
|
| 100 |
+
"prefix": "translate English to French: "
|
| 101 |
+
},
|
| 102 |
+
"translation_en_to_ro": {
|
| 103 |
+
"early_stopping": true,
|
| 104 |
+
"max_length": 300,
|
| 105 |
+
"num_beams": 4,
|
| 106 |
+
"prefix": "translate English to Romanian: "
|
| 107 |
+
}
|
| 108 |
+
},
|
| 109 |
+
"torch_dtype": "float32",
|
| 110 |
+
"transformers_version": "4.39.0.dev0",
|
| 111 |
+
"use_cache": true,
|
| 112 |
+
"vocab_size": 32128
|
| 113 |
+
}
|
google_t5/t5_base_amazon/eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8399209486166008,
|
| 4 |
+
"eval_f1_macro": 0.8112898753723374,
|
| 5 |
+
"eval_f1_micro": 0.8399209486166008,
|
| 6 |
+
"eval_loss": 0.5565423369407654,
|
| 7 |
+
"eval_runtime": 3.8107,
|
| 8 |
+
"eval_samples": 1518,
|
| 9 |
+
"eval_samples_per_second": 398.35,
|
| 10 |
+
"eval_steps_per_second": 12.596
|
| 11 |
+
}
|
google_t5/t5_base_amazon/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:793ee165edf28806fd5d823c7f8559e2764d24d6a360fd01fcaab3c3b51a43b7
|
| 3 |
+
size 894081308
|
google_t5/t5_base_amazon/run.log
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
03/15/2024 11:09:53 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False
|
| 2 |
+
03/15/2024 11:09:53 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, 16-bits training: False
|
| 3 |
+
03/15/2024 11:09:56 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
|
| 4 |
+
03/15/2024 11:09:56 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
|
google_t5/t5_base_amazon/special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
google_t5/t5_base_amazon/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
google_t5/t5_base_amazon/test_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"test_accuracy": 0.857707509881423,
|
| 4 |
+
"test_f1_macro": 0.8293055942786999,
|
| 5 |
+
"test_f1_micro": 0.857707509881423,
|
| 6 |
+
"test_loss": 0.5306673645973206,
|
| 7 |
+
"test_runtime": 3.7633,
|
| 8 |
+
"test_samples_per_second": 403.37,
|
| 9 |
+
"test_steps_per_second": 12.755
|
| 10 |
+
}
|
google_t5/t5_base_amazon/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
google_t5/t5_base_amazon/tokenizer_config.json
ADDED
|
@@ -0,0 +1,937 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 512,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"tokenizer_class": "T5Tokenizer",
|
| 936 |
+
"unk_token": "<unk>"
|
| 937 |
+
}
|
google_t5/t5_base_amazon/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.5285837122222834,
|
| 4 |
+
"train_runtime": 447.0645,
|
| 5 |
+
"train_samples": 12144,
|
| 6 |
+
"train_samples_per_second": 81.492,
|
| 7 |
+
"train_steps_per_second": 2.55
|
| 8 |
+
}
|
google_t5/t5_base_amazon/trainer_state.json
ADDED
|
@@ -0,0 +1,1070 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5565423369407654,
|
| 3 |
+
"best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/google_t5/t5_base_amazon/checkpoint-700",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 1140,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 2.8495495319366455,
|
| 14 |
+
"learning_rate": 0.0004956140350877193,
|
| 15 |
+
"loss": 3.117,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 2.5190072059631348,
|
| 21 |
+
"learning_rate": 0.0004912280701754386,
|
| 22 |
+
"loss": 2.7209,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 2.294928789138794,
|
| 28 |
+
"learning_rate": 0.0004868421052631579,
|
| 29 |
+
"loss": 2.0205,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 3.267091751098633,
|
| 35 |
+
"learning_rate": 0.0004824561403508772,
|
| 36 |
+
"loss": 1.2866,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.13,
|
| 41 |
+
"grad_norm": 4.188276767730713,
|
| 42 |
+
"learning_rate": 0.00047807017543859647,
|
| 43 |
+
"loss": 1.2275,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13,
|
| 48 |
+
"eval_accuracy": 0.6949934123847167,
|
| 49 |
+
"eval_f1_macro": 0.6073038050199799,
|
| 50 |
+
"eval_f1_micro": 0.6949934123847167,
|
| 51 |
+
"eval_loss": 1.035279631614685,
|
| 52 |
+
"eval_runtime": 3.7814,
|
| 53 |
+
"eval_samples_per_second": 401.442,
|
| 54 |
+
"eval_steps_per_second": 12.694,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.16,
|
| 59 |
+
"grad_norm": 6.240413665771484,
|
| 60 |
+
"learning_rate": 0.00047368421052631577,
|
| 61 |
+
"loss": 1.0172,
|
| 62 |
+
"step": 60
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.18,
|
| 66 |
+
"grad_norm": 3.5446884632110596,
|
| 67 |
+
"learning_rate": 0.0004692982456140351,
|
| 68 |
+
"loss": 1.0344,
|
| 69 |
+
"step": 70
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.21,
|
| 73 |
+
"grad_norm": 4.263936519622803,
|
| 74 |
+
"learning_rate": 0.00046491228070175437,
|
| 75 |
+
"loss": 0.8594,
|
| 76 |
+
"step": 80
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.24,
|
| 80 |
+
"grad_norm": 3.0901923179626465,
|
| 81 |
+
"learning_rate": 0.0004605263157894737,
|
| 82 |
+
"loss": 0.8781,
|
| 83 |
+
"step": 90
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.26,
|
| 87 |
+
"grad_norm": 2.737272262573242,
|
| 88 |
+
"learning_rate": 0.000456140350877193,
|
| 89 |
+
"loss": 0.8341,
|
| 90 |
+
"step": 100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.26,
|
| 94 |
+
"eval_accuracy": 0.738471673254282,
|
| 95 |
+
"eval_f1_macro": 0.6814380216401201,
|
| 96 |
+
"eval_f1_micro": 0.738471673254282,
|
| 97 |
+
"eval_loss": 0.8838083744049072,
|
| 98 |
+
"eval_runtime": 3.8044,
|
| 99 |
+
"eval_samples_per_second": 399.016,
|
| 100 |
+
"eval_steps_per_second": 12.617,
|
| 101 |
+
"step": 100
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.29,
|
| 105 |
+
"grad_norm": 2.692996025085449,
|
| 106 |
+
"learning_rate": 0.00045175438596491233,
|
| 107 |
+
"loss": 0.9941,
|
| 108 |
+
"step": 110
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.32,
|
| 112 |
+
"grad_norm": 2.3376717567443848,
|
| 113 |
+
"learning_rate": 0.0004473684210526316,
|
| 114 |
+
"loss": 0.8984,
|
| 115 |
+
"step": 120
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.34,
|
| 119 |
+
"grad_norm": 2.112525224685669,
|
| 120 |
+
"learning_rate": 0.0004429824561403509,
|
| 121 |
+
"loss": 0.909,
|
| 122 |
+
"step": 130
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.37,
|
| 126 |
+
"grad_norm": 2.8785059452056885,
|
| 127 |
+
"learning_rate": 0.0004385964912280702,
|
| 128 |
+
"loss": 0.7654,
|
| 129 |
+
"step": 140
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.39,
|
| 133 |
+
"grad_norm": 2.3538177013397217,
|
| 134 |
+
"learning_rate": 0.0004342105263157895,
|
| 135 |
+
"loss": 0.7773,
|
| 136 |
+
"step": 150
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.39,
|
| 140 |
+
"eval_accuracy": 0.7832674571805006,
|
| 141 |
+
"eval_f1_macro": 0.7339618917892343,
|
| 142 |
+
"eval_f1_micro": 0.7832674571805006,
|
| 143 |
+
"eval_loss": 0.7473268508911133,
|
| 144 |
+
"eval_runtime": 3.8195,
|
| 145 |
+
"eval_samples_per_second": 397.435,
|
| 146 |
+
"eval_steps_per_second": 12.567,
|
| 147 |
+
"step": 150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.42,
|
| 151 |
+
"grad_norm": 2.850787401199341,
|
| 152 |
+
"learning_rate": 0.0004298245614035088,
|
| 153 |
+
"loss": 0.7734,
|
| 154 |
+
"step": 160
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.45,
|
| 158 |
+
"grad_norm": 3.4294583797454834,
|
| 159 |
+
"learning_rate": 0.0004254385964912281,
|
| 160 |
+
"loss": 0.7876,
|
| 161 |
+
"step": 170
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.47,
|
| 165 |
+
"grad_norm": 2.0919501781463623,
|
| 166 |
+
"learning_rate": 0.00042105263157894734,
|
| 167 |
+
"loss": 0.7329,
|
| 168 |
+
"step": 180
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.5,
|
| 172 |
+
"grad_norm": 5.026761531829834,
|
| 173 |
+
"learning_rate": 0.0004166666666666667,
|
| 174 |
+
"loss": 0.8396,
|
| 175 |
+
"step": 190
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.53,
|
| 179 |
+
"grad_norm": 2.3940157890319824,
|
| 180 |
+
"learning_rate": 0.000412280701754386,
|
| 181 |
+
"loss": 0.7188,
|
| 182 |
+
"step": 200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.53,
|
| 186 |
+
"eval_accuracy": 0.7924901185770751,
|
| 187 |
+
"eval_f1_macro": 0.7432732481576452,
|
| 188 |
+
"eval_f1_micro": 0.7924901185770751,
|
| 189 |
+
"eval_loss": 0.7023962140083313,
|
| 190 |
+
"eval_runtime": 3.8263,
|
| 191 |
+
"eval_samples_per_second": 396.73,
|
| 192 |
+
"eval_steps_per_second": 12.545,
|
| 193 |
+
"step": 200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.55,
|
| 197 |
+
"grad_norm": 2.965258836746216,
|
| 198 |
+
"learning_rate": 0.00040789473684210524,
|
| 199 |
+
"loss": 0.66,
|
| 200 |
+
"step": 210
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.58,
|
| 204 |
+
"grad_norm": 3.2059409618377686,
|
| 205 |
+
"learning_rate": 0.00040350877192982455,
|
| 206 |
+
"loss": 0.7795,
|
| 207 |
+
"step": 220
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.61,
|
| 211 |
+
"grad_norm": 4.9381537437438965,
|
| 212 |
+
"learning_rate": 0.0003991228070175439,
|
| 213 |
+
"loss": 0.7163,
|
| 214 |
+
"step": 230
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.63,
|
| 218 |
+
"grad_norm": 4.937159061431885,
|
| 219 |
+
"learning_rate": 0.00039473684210526315,
|
| 220 |
+
"loss": 0.7546,
|
| 221 |
+
"step": 240
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.66,
|
| 225 |
+
"grad_norm": 2.786454439163208,
|
| 226 |
+
"learning_rate": 0.00039035087719298245,
|
| 227 |
+
"loss": 0.7483,
|
| 228 |
+
"step": 250
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.66,
|
| 232 |
+
"eval_accuracy": 0.7872200263504612,
|
| 233 |
+
"eval_f1_macro": 0.7396308270254102,
|
| 234 |
+
"eval_f1_micro": 0.7872200263504612,
|
| 235 |
+
"eval_loss": 0.7055577039718628,
|
| 236 |
+
"eval_runtime": 3.8209,
|
| 237 |
+
"eval_samples_per_second": 397.29,
|
| 238 |
+
"eval_steps_per_second": 12.563,
|
| 239 |
+
"step": 250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.68,
|
| 243 |
+
"grad_norm": 2.2485697269439697,
|
| 244 |
+
"learning_rate": 0.00038596491228070175,
|
| 245 |
+
"loss": 0.7216,
|
| 246 |
+
"step": 260
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.71,
|
| 250 |
+
"grad_norm": 3.388631582260132,
|
| 251 |
+
"learning_rate": 0.00038157894736842105,
|
| 252 |
+
"loss": 0.7437,
|
| 253 |
+
"step": 270
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.74,
|
| 257 |
+
"grad_norm": 2.945599317550659,
|
| 258 |
+
"learning_rate": 0.00037719298245614036,
|
| 259 |
+
"loss": 0.6433,
|
| 260 |
+
"step": 280
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.76,
|
| 264 |
+
"grad_norm": 2.894361972808838,
|
| 265 |
+
"learning_rate": 0.00037280701754385966,
|
| 266 |
+
"loss": 0.6333,
|
| 267 |
+
"step": 290
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.79,
|
| 271 |
+
"grad_norm": 1.8753783702850342,
|
| 272 |
+
"learning_rate": 0.00036842105263157896,
|
| 273 |
+
"loss": 0.6228,
|
| 274 |
+
"step": 300
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.79,
|
| 278 |
+
"eval_accuracy": 0.8129117259552042,
|
| 279 |
+
"eval_f1_macro": 0.7636250391666534,
|
| 280 |
+
"eval_f1_micro": 0.8129117259552042,
|
| 281 |
+
"eval_loss": 0.6337724924087524,
|
| 282 |
+
"eval_runtime": 3.8242,
|
| 283 |
+
"eval_samples_per_second": 396.945,
|
| 284 |
+
"eval_steps_per_second": 12.552,
|
| 285 |
+
"step": 300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.82,
|
| 289 |
+
"grad_norm": 3.340951442718506,
|
| 290 |
+
"learning_rate": 0.00036403508771929826,
|
| 291 |
+
"loss": 0.5978,
|
| 292 |
+
"step": 310
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.84,
|
| 296 |
+
"grad_norm": 3.2675557136535645,
|
| 297 |
+
"learning_rate": 0.00035964912280701756,
|
| 298 |
+
"loss": 0.7124,
|
| 299 |
+
"step": 320
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.87,
|
| 303 |
+
"grad_norm": 2.308924674987793,
|
| 304 |
+
"learning_rate": 0.00035526315789473687,
|
| 305 |
+
"loss": 0.7423,
|
| 306 |
+
"step": 330
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.89,
|
| 310 |
+
"grad_norm": 3.407076835632324,
|
| 311 |
+
"learning_rate": 0.0003508771929824561,
|
| 312 |
+
"loss": 0.6787,
|
| 313 |
+
"step": 340
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.92,
|
| 317 |
+
"grad_norm": 2.5976576805114746,
|
| 318 |
+
"learning_rate": 0.00034649122807017547,
|
| 319 |
+
"loss": 0.7089,
|
| 320 |
+
"step": 350
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.92,
|
| 324 |
+
"eval_accuracy": 0.8208168642951251,
|
| 325 |
+
"eval_f1_macro": 0.7962943499701793,
|
| 326 |
+
"eval_f1_micro": 0.8208168642951251,
|
| 327 |
+
"eval_loss": 0.6130083799362183,
|
| 328 |
+
"eval_runtime": 3.8233,
|
| 329 |
+
"eval_samples_per_second": 397.037,
|
| 330 |
+
"eval_steps_per_second": 12.555,
|
| 331 |
+
"step": 350
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.95,
|
| 335 |
+
"grad_norm": 2.053323745727539,
|
| 336 |
+
"learning_rate": 0.00034210526315789477,
|
| 337 |
+
"loss": 0.5299,
|
| 338 |
+
"step": 360
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.97,
|
| 342 |
+
"grad_norm": 3.201794147491455,
|
| 343 |
+
"learning_rate": 0.000337719298245614,
|
| 344 |
+
"loss": 0.7405,
|
| 345 |
+
"step": 370
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.0,
|
| 349 |
+
"grad_norm": 2.8295910358428955,
|
| 350 |
+
"learning_rate": 0.0003333333333333333,
|
| 351 |
+
"loss": 0.7584,
|
| 352 |
+
"step": 380
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.03,
|
| 356 |
+
"grad_norm": 1.9317399263381958,
|
| 357 |
+
"learning_rate": 0.0003289473684210527,
|
| 358 |
+
"loss": 0.4822,
|
| 359 |
+
"step": 390
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.05,
|
| 363 |
+
"grad_norm": 2.5840656757354736,
|
| 364 |
+
"learning_rate": 0.0003245614035087719,
|
| 365 |
+
"loss": 0.5055,
|
| 366 |
+
"step": 400
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.05,
|
| 370 |
+
"eval_accuracy": 0.8300395256916996,
|
| 371 |
+
"eval_f1_macro": 0.8075388232802375,
|
| 372 |
+
"eval_f1_micro": 0.8300395256916996,
|
| 373 |
+
"eval_loss": 0.5938563346862793,
|
| 374 |
+
"eval_runtime": 3.8245,
|
| 375 |
+
"eval_samples_per_second": 396.912,
|
| 376 |
+
"eval_steps_per_second": 12.551,
|
| 377 |
+
"step": 400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.08,
|
| 381 |
+
"grad_norm": 2.4889354705810547,
|
| 382 |
+
"learning_rate": 0.00032017543859649123,
|
| 383 |
+
"loss": 0.425,
|
| 384 |
+
"step": 410
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.11,
|
| 388 |
+
"grad_norm": 2.618088722229004,
|
| 389 |
+
"learning_rate": 0.00031578947368421053,
|
| 390 |
+
"loss": 0.3865,
|
| 391 |
+
"step": 420
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.13,
|
| 395 |
+
"grad_norm": 2.8282623291015625,
|
| 396 |
+
"learning_rate": 0.00031140350877192983,
|
| 397 |
+
"loss": 0.4543,
|
| 398 |
+
"step": 430
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.16,
|
| 402 |
+
"grad_norm": 3.4801692962646484,
|
| 403 |
+
"learning_rate": 0.00030701754385964913,
|
| 404 |
+
"loss": 0.4152,
|
| 405 |
+
"step": 440
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.18,
|
| 409 |
+
"grad_norm": 1.7531658411026,
|
| 410 |
+
"learning_rate": 0.00030263157894736844,
|
| 411 |
+
"loss": 0.3942,
|
| 412 |
+
"step": 450
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.18,
|
| 416 |
+
"eval_accuracy": 0.8241106719367589,
|
| 417 |
+
"eval_f1_macro": 0.7915647113122625,
|
| 418 |
+
"eval_f1_micro": 0.8241106719367589,
|
| 419 |
+
"eval_loss": 0.6020949482917786,
|
| 420 |
+
"eval_runtime": 3.8282,
|
| 421 |
+
"eval_samples_per_second": 396.536,
|
| 422 |
+
"eval_steps_per_second": 12.539,
|
| 423 |
+
"step": 450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.21,
|
| 427 |
+
"grad_norm": 2.6115176677703857,
|
| 428 |
+
"learning_rate": 0.0002982456140350877,
|
| 429 |
+
"loss": 0.4801,
|
| 430 |
+
"step": 460
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.24,
|
| 434 |
+
"grad_norm": 2.1855995655059814,
|
| 435 |
+
"learning_rate": 0.00029385964912280704,
|
| 436 |
+
"loss": 0.3942,
|
| 437 |
+
"step": 470
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.26,
|
| 441 |
+
"grad_norm": 2.3812382221221924,
|
| 442 |
+
"learning_rate": 0.00028947368421052634,
|
| 443 |
+
"loss": 0.485,
|
| 444 |
+
"step": 480
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.29,
|
| 448 |
+
"grad_norm": 2.102308750152588,
|
| 449 |
+
"learning_rate": 0.00028508771929824564,
|
| 450 |
+
"loss": 0.417,
|
| 451 |
+
"step": 490
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.32,
|
| 455 |
+
"grad_norm": 4.095526218414307,
|
| 456 |
+
"learning_rate": 0.0002807017543859649,
|
| 457 |
+
"loss": 0.4248,
|
| 458 |
+
"step": 500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.32,
|
| 462 |
+
"eval_accuracy": 0.8300395256916996,
|
| 463 |
+
"eval_f1_macro": 0.8060251760691185,
|
| 464 |
+
"eval_f1_micro": 0.8300395256916996,
|
| 465 |
+
"eval_loss": 0.5956056714057922,
|
| 466 |
+
"eval_runtime": 3.8218,
|
| 467 |
+
"eval_samples_per_second": 397.192,
|
| 468 |
+
"eval_steps_per_second": 12.559,
|
| 469 |
+
"step": 500
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.34,
|
| 473 |
+
"grad_norm": 3.2039239406585693,
|
| 474 |
+
"learning_rate": 0.00027631578947368425,
|
| 475 |
+
"loss": 0.4209,
|
| 476 |
+
"step": 510
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.37,
|
| 480 |
+
"grad_norm": 1.9944714307785034,
|
| 481 |
+
"learning_rate": 0.00027192982456140355,
|
| 482 |
+
"loss": 0.5373,
|
| 483 |
+
"step": 520
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.39,
|
| 487 |
+
"grad_norm": 3.2802696228027344,
|
| 488 |
+
"learning_rate": 0.0002675438596491228,
|
| 489 |
+
"loss": 0.5216,
|
| 490 |
+
"step": 530
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.42,
|
| 494 |
+
"grad_norm": 1.4747893810272217,
|
| 495 |
+
"learning_rate": 0.0002631578947368421,
|
| 496 |
+
"loss": 0.3785,
|
| 497 |
+
"step": 540
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.45,
|
| 501 |
+
"grad_norm": 1.2378747463226318,
|
| 502 |
+
"learning_rate": 0.00025877192982456146,
|
| 503 |
+
"loss": 0.3595,
|
| 504 |
+
"step": 550
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.45,
|
| 508 |
+
"eval_accuracy": 0.8175230566534915,
|
| 509 |
+
"eval_f1_macro": 0.7897278945523275,
|
| 510 |
+
"eval_f1_micro": 0.8175230566534915,
|
| 511 |
+
"eval_loss": 0.6172593832015991,
|
| 512 |
+
"eval_runtime": 3.8184,
|
| 513 |
+
"eval_samples_per_second": 397.551,
|
| 514 |
+
"eval_steps_per_second": 12.571,
|
| 515 |
+
"step": 550
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.47,
|
| 519 |
+
"grad_norm": 2.6604156494140625,
|
| 520 |
+
"learning_rate": 0.0002543859649122807,
|
| 521 |
+
"loss": 0.4231,
|
| 522 |
+
"step": 560
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.5,
|
| 526 |
+
"grad_norm": 1.879952311515808,
|
| 527 |
+
"learning_rate": 0.00025,
|
| 528 |
+
"loss": 0.4555,
|
| 529 |
+
"step": 570
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.53,
|
| 533 |
+
"grad_norm": 3.9825170040130615,
|
| 534 |
+
"learning_rate": 0.0002456140350877193,
|
| 535 |
+
"loss": 0.3988,
|
| 536 |
+
"step": 580
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.55,
|
| 540 |
+
"grad_norm": 2.999025583267212,
|
| 541 |
+
"learning_rate": 0.0002412280701754386,
|
| 542 |
+
"loss": 0.3854,
|
| 543 |
+
"step": 590
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.58,
|
| 547 |
+
"grad_norm": 2.778930425643921,
|
| 548 |
+
"learning_rate": 0.00023684210526315788,
|
| 549 |
+
"loss": 0.5263,
|
| 550 |
+
"step": 600
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.58,
|
| 554 |
+
"eval_accuracy": 0.8162055335968379,
|
| 555 |
+
"eval_f1_macro": 0.7908253969964322,
|
| 556 |
+
"eval_f1_micro": 0.8162055335968379,
|
| 557 |
+
"eval_loss": 0.6170048117637634,
|
| 558 |
+
"eval_runtime": 3.838,
|
| 559 |
+
"eval_samples_per_second": 395.517,
|
| 560 |
+
"eval_steps_per_second": 12.506,
|
| 561 |
+
"step": 600
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.61,
|
| 565 |
+
"grad_norm": 2.2400004863739014,
|
| 566 |
+
"learning_rate": 0.00023245614035087719,
|
| 567 |
+
"loss": 0.443,
|
| 568 |
+
"step": 610
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.63,
|
| 572 |
+
"grad_norm": 2.5458765029907227,
|
| 573 |
+
"learning_rate": 0.0002280701754385965,
|
| 574 |
+
"loss": 0.4106,
|
| 575 |
+
"step": 620
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.66,
|
| 579 |
+
"grad_norm": 2.955345392227173,
|
| 580 |
+
"learning_rate": 0.0002236842105263158,
|
| 581 |
+
"loss": 0.4078,
|
| 582 |
+
"step": 630
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.68,
|
| 586 |
+
"grad_norm": 3.5653369426727295,
|
| 587 |
+
"learning_rate": 0.0002192982456140351,
|
| 588 |
+
"loss": 0.4746,
|
| 589 |
+
"step": 640
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.71,
|
| 593 |
+
"grad_norm": 1.5618356466293335,
|
| 594 |
+
"learning_rate": 0.0002149122807017544,
|
| 595 |
+
"loss": 0.5153,
|
| 596 |
+
"step": 650
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.71,
|
| 600 |
+
"eval_accuracy": 0.8326745718050066,
|
| 601 |
+
"eval_f1_macro": 0.8042732309505177,
|
| 602 |
+
"eval_f1_micro": 0.8326745718050066,
|
| 603 |
+
"eval_loss": 0.6007006168365479,
|
| 604 |
+
"eval_runtime": 3.8189,
|
| 605 |
+
"eval_samples_per_second": 397.495,
|
| 606 |
+
"eval_steps_per_second": 12.569,
|
| 607 |
+
"step": 650
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 1.74,
|
| 611 |
+
"grad_norm": 3.3417813777923584,
|
| 612 |
+
"learning_rate": 0.00021052631578947367,
|
| 613 |
+
"loss": 0.3366,
|
| 614 |
+
"step": 660
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.76,
|
| 618 |
+
"grad_norm": 3.232940912246704,
|
| 619 |
+
"learning_rate": 0.000206140350877193,
|
| 620 |
+
"loss": 0.4284,
|
| 621 |
+
"step": 670
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.79,
|
| 625 |
+
"grad_norm": 2.414170265197754,
|
| 626 |
+
"learning_rate": 0.00020175438596491227,
|
| 627 |
+
"loss": 0.4816,
|
| 628 |
+
"step": 680
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.82,
|
| 632 |
+
"grad_norm": 2.161409378051758,
|
| 633 |
+
"learning_rate": 0.00019736842105263157,
|
| 634 |
+
"loss": 0.398,
|
| 635 |
+
"step": 690
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.84,
|
| 639 |
+
"grad_norm": 2.6579811573028564,
|
| 640 |
+
"learning_rate": 0.00019298245614035088,
|
| 641 |
+
"loss": 0.4237,
|
| 642 |
+
"step": 700
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.84,
|
| 646 |
+
"eval_accuracy": 0.8399209486166008,
|
| 647 |
+
"eval_f1_macro": 0.8112898753723374,
|
| 648 |
+
"eval_f1_micro": 0.8399209486166008,
|
| 649 |
+
"eval_loss": 0.5565423369407654,
|
| 650 |
+
"eval_runtime": 3.8246,
|
| 651 |
+
"eval_samples_per_second": 396.904,
|
| 652 |
+
"eval_steps_per_second": 12.55,
|
| 653 |
+
"step": 700
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.87,
|
| 657 |
+
"grad_norm": 3.548602342605591,
|
| 658 |
+
"learning_rate": 0.00018859649122807018,
|
| 659 |
+
"loss": 0.4094,
|
| 660 |
+
"step": 710
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.89,
|
| 664 |
+
"grad_norm": 2.4683637619018555,
|
| 665 |
+
"learning_rate": 0.00018421052631578948,
|
| 666 |
+
"loss": 0.4157,
|
| 667 |
+
"step": 720
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.92,
|
| 671 |
+
"grad_norm": 3.2135560512542725,
|
| 672 |
+
"learning_rate": 0.00017982456140350878,
|
| 673 |
+
"loss": 0.4306,
|
| 674 |
+
"step": 730
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.95,
|
| 678 |
+
"grad_norm": 2.9333302974700928,
|
| 679 |
+
"learning_rate": 0.00017543859649122806,
|
| 680 |
+
"loss": 0.4584,
|
| 681 |
+
"step": 740
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.97,
|
| 685 |
+
"grad_norm": 3.854954957962036,
|
| 686 |
+
"learning_rate": 0.00017105263157894739,
|
| 687 |
+
"loss": 0.3852,
|
| 688 |
+
"step": 750
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.97,
|
| 692 |
+
"eval_accuracy": 0.8438735177865613,
|
| 693 |
+
"eval_f1_macro": 0.8146328190948308,
|
| 694 |
+
"eval_f1_micro": 0.8438735177865613,
|
| 695 |
+
"eval_loss": 0.563149094581604,
|
| 696 |
+
"eval_runtime": 3.8078,
|
| 697 |
+
"eval_samples_per_second": 398.657,
|
| 698 |
+
"eval_steps_per_second": 12.606,
|
| 699 |
+
"step": 750
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.0,
|
| 703 |
+
"grad_norm": 2.8746769428253174,
|
| 704 |
+
"learning_rate": 0.00016666666666666666,
|
| 705 |
+
"loss": 0.3997,
|
| 706 |
+
"step": 760
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.03,
|
| 710 |
+
"grad_norm": 1.5188621282577515,
|
| 711 |
+
"learning_rate": 0.00016228070175438596,
|
| 712 |
+
"loss": 0.2052,
|
| 713 |
+
"step": 770
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.05,
|
| 717 |
+
"grad_norm": 2.1245510578155518,
|
| 718 |
+
"learning_rate": 0.00015789473684210527,
|
| 719 |
+
"loss": 0.2673,
|
| 720 |
+
"step": 780
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.08,
|
| 724 |
+
"grad_norm": 1.595406174659729,
|
| 725 |
+
"learning_rate": 0.00015350877192982457,
|
| 726 |
+
"loss": 0.1844,
|
| 727 |
+
"step": 790
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 2.11,
|
| 731 |
+
"grad_norm": 1.294638991355896,
|
| 732 |
+
"learning_rate": 0.00014912280701754384,
|
| 733 |
+
"loss": 0.1916,
|
| 734 |
+
"step": 800
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.11,
|
| 738 |
+
"eval_accuracy": 0.8438735177865613,
|
| 739 |
+
"eval_f1_macro": 0.8132477856483462,
|
| 740 |
+
"eval_f1_micro": 0.8438735177865613,
|
| 741 |
+
"eval_loss": 0.5847834944725037,
|
| 742 |
+
"eval_runtime": 3.8164,
|
| 743 |
+
"eval_samples_per_second": 397.762,
|
| 744 |
+
"eval_steps_per_second": 12.577,
|
| 745 |
+
"step": 800
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.13,
|
| 749 |
+
"grad_norm": 1.5228568315505981,
|
| 750 |
+
"learning_rate": 0.00014473684210526317,
|
| 751 |
+
"loss": 0.203,
|
| 752 |
+
"step": 810
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.16,
|
| 756 |
+
"grad_norm": 2.10640025138855,
|
| 757 |
+
"learning_rate": 0.00014035087719298245,
|
| 758 |
+
"loss": 0.1871,
|
| 759 |
+
"step": 820
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.18,
|
| 763 |
+
"grad_norm": 2.23407244682312,
|
| 764 |
+
"learning_rate": 0.00013596491228070177,
|
| 765 |
+
"loss": 0.2381,
|
| 766 |
+
"step": 830
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.21,
|
| 770 |
+
"grad_norm": 4.305612564086914,
|
| 771 |
+
"learning_rate": 0.00013157894736842105,
|
| 772 |
+
"loss": 0.1792,
|
| 773 |
+
"step": 840
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.24,
|
| 777 |
+
"grad_norm": 2.1483376026153564,
|
| 778 |
+
"learning_rate": 0.00012719298245614035,
|
| 779 |
+
"loss": 0.2108,
|
| 780 |
+
"step": 850
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.24,
|
| 784 |
+
"eval_accuracy": 0.8432147562582345,
|
| 785 |
+
"eval_f1_macro": 0.8094003161642315,
|
| 786 |
+
"eval_f1_micro": 0.8432147562582345,
|
| 787 |
+
"eval_loss": 0.6054214239120483,
|
| 788 |
+
"eval_runtime": 3.8173,
|
| 789 |
+
"eval_samples_per_second": 397.661,
|
| 790 |
+
"eval_steps_per_second": 12.574,
|
| 791 |
+
"step": 850
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.26,
|
| 795 |
+
"grad_norm": 2.0426666736602783,
|
| 796 |
+
"learning_rate": 0.00012280701754385965,
|
| 797 |
+
"loss": 0.1777,
|
| 798 |
+
"step": 860
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.29,
|
| 802 |
+
"grad_norm": 1.9927353858947754,
|
| 803 |
+
"learning_rate": 0.00011842105263157894,
|
| 804 |
+
"loss": 0.1886,
|
| 805 |
+
"step": 870
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 2.32,
|
| 809 |
+
"grad_norm": 2.371792793273926,
|
| 810 |
+
"learning_rate": 0.00011403508771929824,
|
| 811 |
+
"loss": 0.1927,
|
| 812 |
+
"step": 880
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.34,
|
| 816 |
+
"grad_norm": 1.061587929725647,
|
| 817 |
+
"learning_rate": 0.00010964912280701755,
|
| 818 |
+
"loss": 0.1,
|
| 819 |
+
"step": 890
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.37,
|
| 823 |
+
"grad_norm": 3.100485324859619,
|
| 824 |
+
"learning_rate": 0.00010526315789473683,
|
| 825 |
+
"loss": 0.1752,
|
| 826 |
+
"step": 900
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.37,
|
| 830 |
+
"eval_accuracy": 0.8438735177865613,
|
| 831 |
+
"eval_f1_macro": 0.8131496787168201,
|
| 832 |
+
"eval_f1_micro": 0.8438735177865613,
|
| 833 |
+
"eval_loss": 0.6142441630363464,
|
| 834 |
+
"eval_runtime": 3.8158,
|
| 835 |
+
"eval_samples_per_second": 397.817,
|
| 836 |
+
"eval_steps_per_second": 12.579,
|
| 837 |
+
"step": 900
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.39,
|
| 841 |
+
"grad_norm": 4.032674789428711,
|
| 842 |
+
"learning_rate": 0.00010087719298245614,
|
| 843 |
+
"loss": 0.2409,
|
| 844 |
+
"step": 910
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.42,
|
| 848 |
+
"grad_norm": 1.537070393562317,
|
| 849 |
+
"learning_rate": 9.649122807017544e-05,
|
| 850 |
+
"loss": 0.2244,
|
| 851 |
+
"step": 920
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.45,
|
| 855 |
+
"grad_norm": 2.81392765045166,
|
| 856 |
+
"learning_rate": 9.210526315789474e-05,
|
| 857 |
+
"loss": 0.2367,
|
| 858 |
+
"step": 930
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.47,
|
| 862 |
+
"grad_norm": 4.410009860992432,
|
| 863 |
+
"learning_rate": 8.771929824561403e-05,
|
| 864 |
+
"loss": 0.2912,
|
| 865 |
+
"step": 940
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.5,
|
| 869 |
+
"grad_norm": 2.0353574752807617,
|
| 870 |
+
"learning_rate": 8.333333333333333e-05,
|
| 871 |
+
"loss": 0.1502,
|
| 872 |
+
"step": 950
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.5,
|
| 876 |
+
"eval_accuracy": 0.8451910408432147,
|
| 877 |
+
"eval_f1_macro": 0.8119149292307762,
|
| 878 |
+
"eval_f1_micro": 0.8451910408432147,
|
| 879 |
+
"eval_loss": 0.6100274324417114,
|
| 880 |
+
"eval_runtime": 3.8177,
|
| 881 |
+
"eval_samples_per_second": 397.617,
|
| 882 |
+
"eval_steps_per_second": 12.573,
|
| 883 |
+
"step": 950
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 2.53,
|
| 887 |
+
"grad_norm": 0.4018252193927765,
|
| 888 |
+
"learning_rate": 7.894736842105263e-05,
|
| 889 |
+
"loss": 0.2425,
|
| 890 |
+
"step": 960
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.55,
|
| 894 |
+
"grad_norm": 1.633636236190796,
|
| 895 |
+
"learning_rate": 7.456140350877192e-05,
|
| 896 |
+
"loss": 0.3121,
|
| 897 |
+
"step": 970
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.58,
|
| 901 |
+
"grad_norm": 1.6794798374176025,
|
| 902 |
+
"learning_rate": 7.017543859649122e-05,
|
| 903 |
+
"loss": 0.1456,
|
| 904 |
+
"step": 980
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 2.61,
|
| 908 |
+
"grad_norm": 1.684718132019043,
|
| 909 |
+
"learning_rate": 6.578947368421052e-05,
|
| 910 |
+
"loss": 0.1977,
|
| 911 |
+
"step": 990
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 2.63,
|
| 915 |
+
"grad_norm": 1.3666688203811646,
|
| 916 |
+
"learning_rate": 6.140350877192983e-05,
|
| 917 |
+
"loss": 0.2253,
|
| 918 |
+
"step": 1000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.63,
|
| 922 |
+
"eval_accuracy": 0.8438735177865613,
|
| 923 |
+
"eval_f1_macro": 0.8227552343954732,
|
| 924 |
+
"eval_f1_micro": 0.8438735177865613,
|
| 925 |
+
"eval_loss": 0.6083930730819702,
|
| 926 |
+
"eval_runtime": 3.8094,
|
| 927 |
+
"eval_samples_per_second": 398.489,
|
| 928 |
+
"eval_steps_per_second": 12.6,
|
| 929 |
+
"step": 1000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.66,
|
| 933 |
+
"grad_norm": 1.7882211208343506,
|
| 934 |
+
"learning_rate": 5.701754385964912e-05,
|
| 935 |
+
"loss": 0.1514,
|
| 936 |
+
"step": 1010
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.68,
|
| 940 |
+
"grad_norm": 1.7349433898925781,
|
| 941 |
+
"learning_rate": 5.263157894736842e-05,
|
| 942 |
+
"loss": 0.2528,
|
| 943 |
+
"step": 1020
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.71,
|
| 947 |
+
"grad_norm": 1.9312665462493896,
|
| 948 |
+
"learning_rate": 4.824561403508772e-05,
|
| 949 |
+
"loss": 0.238,
|
| 950 |
+
"step": 1030
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.74,
|
| 954 |
+
"grad_norm": 2.227630376815796,
|
| 955 |
+
"learning_rate": 4.3859649122807014e-05,
|
| 956 |
+
"loss": 0.2113,
|
| 957 |
+
"step": 1040
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.76,
|
| 961 |
+
"grad_norm": 1.098223328590393,
|
| 962 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 963 |
+
"loss": 0.2193,
|
| 964 |
+
"step": 1050
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.76,
|
| 968 |
+
"eval_accuracy": 0.8484848484848485,
|
| 969 |
+
"eval_f1_macro": 0.817141995514716,
|
| 970 |
+
"eval_f1_micro": 0.8484848484848485,
|
| 971 |
+
"eval_loss": 0.6062248945236206,
|
| 972 |
+
"eval_runtime": 3.8206,
|
| 973 |
+
"eval_samples_per_second": 397.322,
|
| 974 |
+
"eval_steps_per_second": 12.564,
|
| 975 |
+
"step": 1050
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.79,
|
| 979 |
+
"grad_norm": 0.6382438540458679,
|
| 980 |
+
"learning_rate": 3.508771929824561e-05,
|
| 981 |
+
"loss": 0.2207,
|
| 982 |
+
"step": 1060
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.82,
|
| 986 |
+
"grad_norm": 2.2816574573516846,
|
| 987 |
+
"learning_rate": 3.0701754385964913e-05,
|
| 988 |
+
"loss": 0.2896,
|
| 989 |
+
"step": 1070
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.84,
|
| 993 |
+
"grad_norm": 1.8550561666488647,
|
| 994 |
+
"learning_rate": 2.631578947368421e-05,
|
| 995 |
+
"loss": 0.2776,
|
| 996 |
+
"step": 1080
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.87,
|
| 1000 |
+
"grad_norm": 1.517103672027588,
|
| 1001 |
+
"learning_rate": 2.1929824561403507e-05,
|
| 1002 |
+
"loss": 0.1744,
|
| 1003 |
+
"step": 1090
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.89,
|
| 1007 |
+
"grad_norm": 1.9958040714263916,
|
| 1008 |
+
"learning_rate": 1.7543859649122806e-05,
|
| 1009 |
+
"loss": 0.2182,
|
| 1010 |
+
"step": 1100
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.89,
|
| 1014 |
+
"eval_accuracy": 0.849802371541502,
|
| 1015 |
+
"eval_f1_macro": 0.8181612702287439,
|
| 1016 |
+
"eval_f1_micro": 0.849802371541502,
|
| 1017 |
+
"eval_loss": 0.5966492891311646,
|
| 1018 |
+
"eval_runtime": 3.822,
|
| 1019 |
+
"eval_samples_per_second": 397.173,
|
| 1020 |
+
"eval_steps_per_second": 12.559,
|
| 1021 |
+
"step": 1100
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.92,
|
| 1025 |
+
"grad_norm": 1.0382195711135864,
|
| 1026 |
+
"learning_rate": 1.3157894736842104e-05,
|
| 1027 |
+
"loss": 0.2314,
|
| 1028 |
+
"step": 1110
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.95,
|
| 1032 |
+
"grad_norm": 0.6311368346214294,
|
| 1033 |
+
"learning_rate": 8.771929824561403e-06,
|
| 1034 |
+
"loss": 0.2827,
|
| 1035 |
+
"step": 1120
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.97,
|
| 1039 |
+
"grad_norm": 2.1355645656585693,
|
| 1040 |
+
"learning_rate": 4.3859649122807014e-06,
|
| 1041 |
+
"loss": 0.1823,
|
| 1042 |
+
"step": 1130
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 3.0,
|
| 1046 |
+
"grad_norm": 0.8415520191192627,
|
| 1047 |
+
"learning_rate": 0.0,
|
| 1048 |
+
"loss": 0.168,
|
| 1049 |
+
"step": 1140
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.0,
|
| 1053 |
+
"step": 1140,
|
| 1054 |
+
"total_flos": 5570737729437696.0,
|
| 1055 |
+
"train_loss": 0.5285837122222834,
|
| 1056 |
+
"train_runtime": 447.0645,
|
| 1057 |
+
"train_samples_per_second": 81.492,
|
| 1058 |
+
"train_steps_per_second": 2.55
|
| 1059 |
+
}
|
| 1060 |
+
],
|
| 1061 |
+
"logging_steps": 10,
|
| 1062 |
+
"max_steps": 1140,
|
| 1063 |
+
"num_input_tokens_seen": 0,
|
| 1064 |
+
"num_train_epochs": 3,
|
| 1065 |
+
"save_steps": 50,
|
| 1066 |
+
"total_flos": 5570737729437696.0,
|
| 1067 |
+
"train_batch_size": 16,
|
| 1068 |
+
"trial_name": null,
|
| 1069 |
+
"trial_params": null
|
| 1070 |
+
}
|
google_t5/t5_base_amazon/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9058d2c55809c08dfe5d631fdecbc63ece4067a6cea137e1478fddc6e29958ed
|
| 3 |
+
size 5048
|
google_t5/t5_base_ledgar/README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google-t5/t5-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: t5_base_ledgar
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# t5_base_ledgar
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5004
|
| 21 |
+
- Accuracy: 0.8664
|
| 22 |
+
- F1 Macro: 0.7948
|
| 23 |
+
- F1 Micro: 0.8664
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0005
|
| 43 |
+
- train_batch_size: 32
|
| 44 |
+
- eval_batch_size: 32
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 2
|
| 48 |
+
- total_train_batch_size: 64
|
| 49 |
+
- total_eval_batch_size: 64
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 3.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
|
| 58 |
+
| 1.443 | 0.11 | 100 | 1.1133 | 0.7291 | 0.5312 | 0.7291 |
|
| 59 |
+
| 0.8813 | 0.21 | 200 | 0.8404 | 0.7712 | 0.6296 | 0.7712 |
|
| 60 |
+
| 0.761 | 0.32 | 300 | 0.7386 | 0.8021 | 0.6789 | 0.8021 |
|
| 61 |
+
| 0.7358 | 0.43 | 400 | 0.7313 | 0.805 | 0.6787 | 0.805 |
|
| 62 |
+
| 0.7624 | 0.53 | 500 | 0.6561 | 0.8164 | 0.7134 | 0.8164 |
|
| 63 |
+
| 0.7067 | 0.64 | 600 | 0.6419 | 0.821 | 0.7273 | 0.821 |
|
| 64 |
+
| 0.6298 | 0.75 | 700 | 0.6412 | 0.8254 | 0.7230 | 0.8254 |
|
| 65 |
+
| 0.6544 | 0.85 | 800 | 0.6277 | 0.8217 | 0.7223 | 0.8217 |
|
| 66 |
+
| 0.5781 | 0.96 | 900 | 0.6054 | 0.8305 | 0.7420 | 0.8305 |
|
| 67 |
+
| 0.4674 | 1.07 | 1000 | 0.6210 | 0.8346 | 0.7371 | 0.8346 |
|
| 68 |
+
| 0.4929 | 1.17 | 1100 | 0.5876 | 0.8387 | 0.7423 | 0.8387 |
|
| 69 |
+
| 0.566 | 1.28 | 1200 | 0.5779 | 0.8475 | 0.7633 | 0.8475 |
|
| 70 |
+
| 0.4577 | 1.39 | 1300 | 0.5772 | 0.8435 | 0.7508 | 0.8435 |
|
| 71 |
+
| 0.4233 | 1.49 | 1400 | 0.5581 | 0.8476 | 0.7625 | 0.8476 |
|
| 72 |
+
| 0.4567 | 1.6 | 1500 | 0.5688 | 0.8462 | 0.7576 | 0.8462 |
|
| 73 |
+
| 0.483 | 1.71 | 1600 | 0.5547 | 0.8478 | 0.7609 | 0.8478 |
|
| 74 |
+
| 0.4649 | 1.81 | 1700 | 0.5396 | 0.851 | 0.7680 | 0.851 |
|
| 75 |
+
| 0.4288 | 1.92 | 1800 | 0.5235 | 0.8577 | 0.7759 | 0.8577 |
|
| 76 |
+
| 0.3445 | 2.03 | 1900 | 0.5204 | 0.8603 | 0.7791 | 0.8603 |
|
| 77 |
+
| 0.3014 | 2.13 | 2000 | 0.5269 | 0.8607 | 0.7862 | 0.8607 |
|
| 78 |
+
| 0.3301 | 2.24 | 2100 | 0.5234 | 0.8591 | 0.7826 | 0.8591 |
|
| 79 |
+
| 0.3069 | 2.35 | 2200 | 0.5266 | 0.8624 | 0.7851 | 0.8624 |
|
| 80 |
+
| 0.3095 | 2.45 | 2300 | 0.5155 | 0.8629 | 0.7846 | 0.8629 |
|
| 81 |
+
| 0.3164 | 2.56 | 2400 | 0.5106 | 0.8646 | 0.7909 | 0.8646 |
|
| 82 |
+
| 0.2914 | 2.67 | 2500 | 0.5055 | 0.8647 | 0.7934 | 0.8647 |
|
| 83 |
+
| 0.2946 | 2.77 | 2600 | 0.5027 | 0.8643 | 0.7917 | 0.8643 |
|
| 84 |
+
| 0.3012 | 2.88 | 2700 | 0.5009 | 0.8671 | 0.7953 | 0.8671 |
|
| 85 |
+
| 0.3181 | 2.99 | 2800 | 0.5004 | 0.8664 | 0.7948 | 0.8664 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.39.0.dev0
|
| 91 |
+
- Pytorch 2.2.1+cu121
|
| 92 |
+
- Datasets 2.18.0
|
| 93 |
+
- Tokenizers 0.15.2
|
google_t5/t5_base_ledgar/all_results.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8664,
|
| 4 |
+
"eval_f1_macro": 0.7947908970820687,
|
| 5 |
+
"eval_f1_micro": 0.8664,
|
| 6 |
+
"eval_loss": 0.5004217028617859,
|
| 7 |
+
"eval_runtime": 23.9278,
|
| 8 |
+
"eval_samples": 10000,
|
| 9 |
+
"eval_samples_per_second": 417.924,
|
| 10 |
+
"eval_steps_per_second": 6.561,
|
| 11 |
+
"test_accuracy": 0.871,
|
| 12 |
+
"test_f1_macro": 0.7998698141352754,
|
| 13 |
+
"test_f1_micro": 0.871,
|
| 14 |
+
"test_loss": 0.5104538798332214,
|
| 15 |
+
"test_runtime": 23.9487,
|
| 16 |
+
"test_samples_per_second": 417.56,
|
| 17 |
+
"test_steps_per_second": 6.556,
|
| 18 |
+
"train_loss": 0.5752294131348806,
|
| 19 |
+
"train_runtime": 2000.5798,
|
| 20 |
+
"train_samples": 60000,
|
| 21 |
+
"train_samples_per_second": 89.974,
|
| 22 |
+
"train_steps_per_second": 1.407
|
| 23 |
+
}
|
google_t5/t5_base_ledgar/checkpoint-2800/config.json
ADDED
|
@@ -0,0 +1,267 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-t5/t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"finetuning_task": "text-classification",
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "0",
|
| 18 |
+
"1": "1",
|
| 19 |
+
"2": "10",
|
| 20 |
+
"3": "11",
|
| 21 |
+
"4": "12",
|
| 22 |
+
"5": "13",
|
| 23 |
+
"6": "14",
|
| 24 |
+
"7": "15",
|
| 25 |
+
"8": "16",
|
| 26 |
+
"9": "17",
|
| 27 |
+
"10": "18",
|
| 28 |
+
"11": "19",
|
| 29 |
+
"12": "2",
|
| 30 |
+
"13": "20",
|
| 31 |
+
"14": "21",
|
| 32 |
+
"15": "22",
|
| 33 |
+
"16": "23",
|
| 34 |
+
"17": "24",
|
| 35 |
+
"18": "25",
|
| 36 |
+
"19": "26",
|
| 37 |
+
"20": "27",
|
| 38 |
+
"21": "28",
|
| 39 |
+
"22": "29",
|
| 40 |
+
"23": "3",
|
| 41 |
+
"24": "30",
|
| 42 |
+
"25": "31",
|
| 43 |
+
"26": "32",
|
| 44 |
+
"27": "33",
|
| 45 |
+
"28": "34",
|
| 46 |
+
"29": "35",
|
| 47 |
+
"30": "36",
|
| 48 |
+
"31": "37",
|
| 49 |
+
"32": "38",
|
| 50 |
+
"33": "39",
|
| 51 |
+
"34": "4",
|
| 52 |
+
"35": "40",
|
| 53 |
+
"36": "41",
|
| 54 |
+
"37": "42",
|
| 55 |
+
"38": "43",
|
| 56 |
+
"39": "44",
|
| 57 |
+
"40": "45",
|
| 58 |
+
"41": "46",
|
| 59 |
+
"42": "47",
|
| 60 |
+
"43": "48",
|
| 61 |
+
"44": "49",
|
| 62 |
+
"45": "5",
|
| 63 |
+
"46": "50",
|
| 64 |
+
"47": "51",
|
| 65 |
+
"48": "52",
|
| 66 |
+
"49": "53",
|
| 67 |
+
"50": "54",
|
| 68 |
+
"51": "55",
|
| 69 |
+
"52": "56",
|
| 70 |
+
"53": "57",
|
| 71 |
+
"54": "58",
|
| 72 |
+
"55": "59",
|
| 73 |
+
"56": "6",
|
| 74 |
+
"57": "60",
|
| 75 |
+
"58": "61",
|
| 76 |
+
"59": "62",
|
| 77 |
+
"60": "63",
|
| 78 |
+
"61": "64",
|
| 79 |
+
"62": "65",
|
| 80 |
+
"63": "66",
|
| 81 |
+
"64": "67",
|
| 82 |
+
"65": "68",
|
| 83 |
+
"66": "69",
|
| 84 |
+
"67": "7",
|
| 85 |
+
"68": "70",
|
| 86 |
+
"69": "71",
|
| 87 |
+
"70": "72",
|
| 88 |
+
"71": "73",
|
| 89 |
+
"72": "74",
|
| 90 |
+
"73": "75",
|
| 91 |
+
"74": "76",
|
| 92 |
+
"75": "77",
|
| 93 |
+
"76": "78",
|
| 94 |
+
"77": "79",
|
| 95 |
+
"78": "8",
|
| 96 |
+
"79": "80",
|
| 97 |
+
"80": "81",
|
| 98 |
+
"81": "82",
|
| 99 |
+
"82": "83",
|
| 100 |
+
"83": "84",
|
| 101 |
+
"84": "85",
|
| 102 |
+
"85": "86",
|
| 103 |
+
"86": "87",
|
| 104 |
+
"87": "88",
|
| 105 |
+
"88": "89",
|
| 106 |
+
"89": "9",
|
| 107 |
+
"90": "90",
|
| 108 |
+
"91": "91",
|
| 109 |
+
"92": "92",
|
| 110 |
+
"93": "93",
|
| 111 |
+
"94": "94",
|
| 112 |
+
"95": "95",
|
| 113 |
+
"96": "96",
|
| 114 |
+
"97": "97",
|
| 115 |
+
"98": "98",
|
| 116 |
+
"99": "99"
|
| 117 |
+
},
|
| 118 |
+
"initializer_factor": 1.0,
|
| 119 |
+
"is_encoder_decoder": true,
|
| 120 |
+
"is_gated_act": false,
|
| 121 |
+
"label2id": {
|
| 122 |
+
"0": 0,
|
| 123 |
+
"1": 1,
|
| 124 |
+
"10": 2,
|
| 125 |
+
"11": 3,
|
| 126 |
+
"12": 4,
|
| 127 |
+
"13": 5,
|
| 128 |
+
"14": 6,
|
| 129 |
+
"15": 7,
|
| 130 |
+
"16": 8,
|
| 131 |
+
"17": 9,
|
| 132 |
+
"18": 10,
|
| 133 |
+
"19": 11,
|
| 134 |
+
"2": 12,
|
| 135 |
+
"20": 13,
|
| 136 |
+
"21": 14,
|
| 137 |
+
"22": 15,
|
| 138 |
+
"23": 16,
|
| 139 |
+
"24": 17,
|
| 140 |
+
"25": 18,
|
| 141 |
+
"26": 19,
|
| 142 |
+
"27": 20,
|
| 143 |
+
"28": 21,
|
| 144 |
+
"29": 22,
|
| 145 |
+
"3": 23,
|
| 146 |
+
"30": 24,
|
| 147 |
+
"31": 25,
|
| 148 |
+
"32": 26,
|
| 149 |
+
"33": 27,
|
| 150 |
+
"34": 28,
|
| 151 |
+
"35": 29,
|
| 152 |
+
"36": 30,
|
| 153 |
+
"37": 31,
|
| 154 |
+
"38": 32,
|
| 155 |
+
"39": 33,
|
| 156 |
+
"4": 34,
|
| 157 |
+
"40": 35,
|
| 158 |
+
"41": 36,
|
| 159 |
+
"42": 37,
|
| 160 |
+
"43": 38,
|
| 161 |
+
"44": 39,
|
| 162 |
+
"45": 40,
|
| 163 |
+
"46": 41,
|
| 164 |
+
"47": 42,
|
| 165 |
+
"48": 43,
|
| 166 |
+
"49": 44,
|
| 167 |
+
"5": 45,
|
| 168 |
+
"50": 46,
|
| 169 |
+
"51": 47,
|
| 170 |
+
"52": 48,
|
| 171 |
+
"53": 49,
|
| 172 |
+
"54": 50,
|
| 173 |
+
"55": 51,
|
| 174 |
+
"56": 52,
|
| 175 |
+
"57": 53,
|
| 176 |
+
"58": 54,
|
| 177 |
+
"59": 55,
|
| 178 |
+
"6": 56,
|
| 179 |
+
"60": 57,
|
| 180 |
+
"61": 58,
|
| 181 |
+
"62": 59,
|
| 182 |
+
"63": 60,
|
| 183 |
+
"64": 61,
|
| 184 |
+
"65": 62,
|
| 185 |
+
"66": 63,
|
| 186 |
+
"67": 64,
|
| 187 |
+
"68": 65,
|
| 188 |
+
"69": 66,
|
| 189 |
+
"7": 67,
|
| 190 |
+
"70": 68,
|
| 191 |
+
"71": 69,
|
| 192 |
+
"72": 70,
|
| 193 |
+
"73": 71,
|
| 194 |
+
"74": 72,
|
| 195 |
+
"75": 73,
|
| 196 |
+
"76": 74,
|
| 197 |
+
"77": 75,
|
| 198 |
+
"78": 76,
|
| 199 |
+
"79": 77,
|
| 200 |
+
"8": 78,
|
| 201 |
+
"80": 79,
|
| 202 |
+
"81": 80,
|
| 203 |
+
"82": 81,
|
| 204 |
+
"83": 82,
|
| 205 |
+
"84": 83,
|
| 206 |
+
"85": 84,
|
| 207 |
+
"86": 85,
|
| 208 |
+
"87": 86,
|
| 209 |
+
"88": 87,
|
| 210 |
+
"89": 88,
|
| 211 |
+
"9": 89,
|
| 212 |
+
"90": 90,
|
| 213 |
+
"91": 91,
|
| 214 |
+
"92": 92,
|
| 215 |
+
"93": 93,
|
| 216 |
+
"94": 94,
|
| 217 |
+
"95": 95,
|
| 218 |
+
"96": 96,
|
| 219 |
+
"97": 97,
|
| 220 |
+
"98": 98,
|
| 221 |
+
"99": 99
|
| 222 |
+
},
|
| 223 |
+
"layer_norm_epsilon": 1e-06,
|
| 224 |
+
"model_type": "t5",
|
| 225 |
+
"n_positions": 512,
|
| 226 |
+
"num_decoder_layers": 12,
|
| 227 |
+
"num_heads": 12,
|
| 228 |
+
"num_layers": 12,
|
| 229 |
+
"output_past": true,
|
| 230 |
+
"pad_token_id": 0,
|
| 231 |
+
"problem_type": "single_label_classification",
|
| 232 |
+
"relative_attention_max_distance": 128,
|
| 233 |
+
"relative_attention_num_buckets": 32,
|
| 234 |
+
"task_specific_params": {
|
| 235 |
+
"summarization": {
|
| 236 |
+
"early_stopping": true,
|
| 237 |
+
"length_penalty": 2.0,
|
| 238 |
+
"max_length": 200,
|
| 239 |
+
"min_length": 30,
|
| 240 |
+
"no_repeat_ngram_size": 3,
|
| 241 |
+
"num_beams": 4,
|
| 242 |
+
"prefix": "summarize: "
|
| 243 |
+
},
|
| 244 |
+
"translation_en_to_de": {
|
| 245 |
+
"early_stopping": true,
|
| 246 |
+
"max_length": 300,
|
| 247 |
+
"num_beams": 4,
|
| 248 |
+
"prefix": "translate English to German: "
|
| 249 |
+
},
|
| 250 |
+
"translation_en_to_fr": {
|
| 251 |
+
"early_stopping": true,
|
| 252 |
+
"max_length": 300,
|
| 253 |
+
"num_beams": 4,
|
| 254 |
+
"prefix": "translate English to French: "
|
| 255 |
+
},
|
| 256 |
+
"translation_en_to_ro": {
|
| 257 |
+
"early_stopping": true,
|
| 258 |
+
"max_length": 300,
|
| 259 |
+
"num_beams": 4,
|
| 260 |
+
"prefix": "translate English to Romanian: "
|
| 261 |
+
}
|
| 262 |
+
},
|
| 263 |
+
"torch_dtype": "float32",
|
| 264 |
+
"transformers_version": "4.39.0.dev0",
|
| 265 |
+
"use_cache": true,
|
| 266 |
+
"vocab_size": 32128
|
| 267 |
+
}
|
google_t5/t5_base_ledgar/checkpoint-2800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bec396a5ee38fb93b45dcbfe6b134f5c7adba0ea2c64f0184a3f24a69faff1e
|
| 3 |
+
size 894318160
|
google_t5/t5_base_ledgar/checkpoint-2800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1189c70b050342748d8acf188a98f72bb43308b8b1a6fd8d7f850b2185ea93c3
|
| 3 |
+
size 1788788090
|
google_t5/t5_base_ledgar/checkpoint-2800/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24ba53d7978dbe7a0c204e81111c055f86c339fdfaab61d75b7ccaed5cd1388d
|
| 3 |
+
size 14512
|
google_t5/t5_base_ledgar/checkpoint-2800/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb62001198093461d4e1250452b59b09d0426f9b616a6c5afff748dc51f021be
|
| 3 |
+
size 14512
|
google_t5/t5_base_ledgar/checkpoint-2800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51e284703b00465acd87a34da92d3e2f6ab78a159fbf2682d3512ef8b4721d1e
|
| 3 |
+
size 1064
|
google_t5/t5_base_ledgar/checkpoint-2800/special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
google_t5/t5_base_ledgar/checkpoint-2800/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
google_t5/t5_base_ledgar/checkpoint-2800/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
google_t5/t5_base_ledgar/checkpoint-2800/tokenizer_config.json
ADDED
|
@@ -0,0 +1,937 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 512,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"tokenizer_class": "T5Tokenizer",
|
| 936 |
+
"unk_token": "<unk>"
|
| 937 |
+
}
|
google_t5/t5_base_ledgar/checkpoint-2800/trainer_state.json
ADDED
|
@@ -0,0 +1,1113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5004217028617859,
|
| 3 |
+
"best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/google_t5/t5_base_ledgar/checkpoint-2800",
|
| 4 |
+
"epoch": 2.9850746268656714,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 2.0540711879730225,
|
| 14 |
+
"learning_rate": 0.0004955579246624023,
|
| 15 |
+
"loss": 4.1527,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 2.241663694381714,
|
| 21 |
+
"learning_rate": 0.0004911158493248046,
|
| 22 |
+
"loss": 2.8808,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 2.093815803527832,
|
| 28 |
+
"learning_rate": 0.00048667377398720687,
|
| 29 |
+
"loss": 1.9075,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 2.396036148071289,
|
| 35 |
+
"learning_rate": 0.0004822316986496091,
|
| 36 |
+
"loss": 1.443,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11,
|
| 41 |
+
"eval_accuracy": 0.7291,
|
| 42 |
+
"eval_f1_macro": 0.5312263291596806,
|
| 43 |
+
"eval_f1_micro": 0.7291,
|
| 44 |
+
"eval_loss": 1.113275408744812,
|
| 45 |
+
"eval_runtime": 24.8696,
|
| 46 |
+
"eval_samples_per_second": 402.097,
|
| 47 |
+
"eval_steps_per_second": 6.313,
|
| 48 |
+
"step": 100
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.13,
|
| 52 |
+
"grad_norm": 2.6226117610931396,
|
| 53 |
+
"learning_rate": 0.0004777896233120114,
|
| 54 |
+
"loss": 1.1778,
|
| 55 |
+
"step": 125
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.16,
|
| 59 |
+
"grad_norm": 2.527249574661255,
|
| 60 |
+
"learning_rate": 0.00047334754797441367,
|
| 61 |
+
"loss": 1.0394,
|
| 62 |
+
"step": 150
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.19,
|
| 66 |
+
"grad_norm": 2.435964584350586,
|
| 67 |
+
"learning_rate": 0.00046890547263681595,
|
| 68 |
+
"loss": 0.9535,
|
| 69 |
+
"step": 175
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.21,
|
| 73 |
+
"grad_norm": 2.0345797538757324,
|
| 74 |
+
"learning_rate": 0.00046446339729921824,
|
| 75 |
+
"loss": 0.8813,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.21,
|
| 80 |
+
"eval_accuracy": 0.7712,
|
| 81 |
+
"eval_f1_macro": 0.6296223926135491,
|
| 82 |
+
"eval_f1_micro": 0.7712,
|
| 83 |
+
"eval_loss": 0.8404093980789185,
|
| 84 |
+
"eval_runtime": 24.3258,
|
| 85 |
+
"eval_samples_per_second": 411.086,
|
| 86 |
+
"eval_steps_per_second": 6.454,
|
| 87 |
+
"step": 200
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24,
|
| 91 |
+
"grad_norm": 4.247000217437744,
|
| 92 |
+
"learning_rate": 0.0004600213219616205,
|
| 93 |
+
"loss": 0.8062,
|
| 94 |
+
"step": 225
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.27,
|
| 98 |
+
"grad_norm": 1.9799127578735352,
|
| 99 |
+
"learning_rate": 0.00045557924662402275,
|
| 100 |
+
"loss": 0.8654,
|
| 101 |
+
"step": 250
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.29,
|
| 105 |
+
"grad_norm": 2.0902786254882812,
|
| 106 |
+
"learning_rate": 0.000451137171286425,
|
| 107 |
+
"loss": 0.8073,
|
| 108 |
+
"step": 275
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.32,
|
| 112 |
+
"grad_norm": 1.7158573865890503,
|
| 113 |
+
"learning_rate": 0.00044669509594882727,
|
| 114 |
+
"loss": 0.761,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.32,
|
| 119 |
+
"eval_accuracy": 0.8021,
|
| 120 |
+
"eval_f1_macro": 0.6788544961571827,
|
| 121 |
+
"eval_f1_micro": 0.8021,
|
| 122 |
+
"eval_loss": 0.738567590713501,
|
| 123 |
+
"eval_runtime": 24.2955,
|
| 124 |
+
"eval_samples_per_second": 411.599,
|
| 125 |
+
"eval_steps_per_second": 6.462,
|
| 126 |
+
"step": 300
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.35,
|
| 130 |
+
"grad_norm": 2.2180001735687256,
|
| 131 |
+
"learning_rate": 0.00044225302061122956,
|
| 132 |
+
"loss": 0.7375,
|
| 133 |
+
"step": 325
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.37,
|
| 137 |
+
"grad_norm": 2.029712677001953,
|
| 138 |
+
"learning_rate": 0.00043781094527363184,
|
| 139 |
+
"loss": 0.7601,
|
| 140 |
+
"step": 350
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.4,
|
| 144 |
+
"grad_norm": 2.0835516452789307,
|
| 145 |
+
"learning_rate": 0.0004333688699360341,
|
| 146 |
+
"loss": 0.6685,
|
| 147 |
+
"step": 375
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.43,
|
| 151 |
+
"grad_norm": 2.2809343338012695,
|
| 152 |
+
"learning_rate": 0.0004289267945984364,
|
| 153 |
+
"loss": 0.7358,
|
| 154 |
+
"step": 400
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.43,
|
| 158 |
+
"eval_accuracy": 0.805,
|
| 159 |
+
"eval_f1_macro": 0.6786916719278343,
|
| 160 |
+
"eval_f1_micro": 0.805,
|
| 161 |
+
"eval_loss": 0.731271505355835,
|
| 162 |
+
"eval_runtime": 24.2168,
|
| 163 |
+
"eval_samples_per_second": 412.937,
|
| 164 |
+
"eval_steps_per_second": 6.483,
|
| 165 |
+
"step": 400
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.45,
|
| 169 |
+
"grad_norm": 2.0364644527435303,
|
| 170 |
+
"learning_rate": 0.00042448471926083864,
|
| 171 |
+
"loss": 0.7414,
|
| 172 |
+
"step": 425
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.48,
|
| 176 |
+
"grad_norm": 2.7770190238952637,
|
| 177 |
+
"learning_rate": 0.00042004264392324093,
|
| 178 |
+
"loss": 0.8142,
|
| 179 |
+
"step": 450
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.51,
|
| 183 |
+
"grad_norm": 9.388680458068848,
|
| 184 |
+
"learning_rate": 0.0004156005685856432,
|
| 185 |
+
"loss": 0.7282,
|
| 186 |
+
"step": 475
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.53,
|
| 190 |
+
"grad_norm": 2.113584041595459,
|
| 191 |
+
"learning_rate": 0.0004111584932480455,
|
| 192 |
+
"loss": 0.7624,
|
| 193 |
+
"step": 500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.53,
|
| 197 |
+
"eval_accuracy": 0.8164,
|
| 198 |
+
"eval_f1_macro": 0.7134072796381032,
|
| 199 |
+
"eval_f1_micro": 0.8164,
|
| 200 |
+
"eval_loss": 0.6560911536216736,
|
| 201 |
+
"eval_runtime": 24.2135,
|
| 202 |
+
"eval_samples_per_second": 412.993,
|
| 203 |
+
"eval_steps_per_second": 6.484,
|
| 204 |
+
"step": 500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.56,
|
| 208 |
+
"grad_norm": 1.490932822227478,
|
| 209 |
+
"learning_rate": 0.0004067164179104478,
|
| 210 |
+
"loss": 0.7123,
|
| 211 |
+
"step": 525
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.59,
|
| 215 |
+
"grad_norm": 1.1674153804779053,
|
| 216 |
+
"learning_rate": 0.00040227434257285007,
|
| 217 |
+
"loss": 0.692,
|
| 218 |
+
"step": 550
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.61,
|
| 222 |
+
"grad_norm": 2.5101075172424316,
|
| 223 |
+
"learning_rate": 0.00039783226723525235,
|
| 224 |
+
"loss": 0.6392,
|
| 225 |
+
"step": 575
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.64,
|
| 229 |
+
"grad_norm": 1.797776460647583,
|
| 230 |
+
"learning_rate": 0.0003933901918976546,
|
| 231 |
+
"loss": 0.7067,
|
| 232 |
+
"step": 600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.64,
|
| 236 |
+
"eval_accuracy": 0.821,
|
| 237 |
+
"eval_f1_macro": 0.7273350797174626,
|
| 238 |
+
"eval_f1_micro": 0.821,
|
| 239 |
+
"eval_loss": 0.6418954133987427,
|
| 240 |
+
"eval_runtime": 24.1496,
|
| 241 |
+
"eval_samples_per_second": 414.086,
|
| 242 |
+
"eval_steps_per_second": 6.501,
|
| 243 |
+
"step": 600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.67,
|
| 247 |
+
"grad_norm": 1.9408563375473022,
|
| 248 |
+
"learning_rate": 0.00038894811656005687,
|
| 249 |
+
"loss": 0.6762,
|
| 250 |
+
"step": 625
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.69,
|
| 254 |
+
"grad_norm": 1.9674413204193115,
|
| 255 |
+
"learning_rate": 0.00038450604122245916,
|
| 256 |
+
"loss": 0.6784,
|
| 257 |
+
"step": 650
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.72,
|
| 261 |
+
"grad_norm": 2.5168087482452393,
|
| 262 |
+
"learning_rate": 0.00038006396588486144,
|
| 263 |
+
"loss": 0.7106,
|
| 264 |
+
"step": 675
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.75,
|
| 268 |
+
"grad_norm": 1.7439873218536377,
|
| 269 |
+
"learning_rate": 0.0003756218905472637,
|
| 270 |
+
"loss": 0.6298,
|
| 271 |
+
"step": 700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.75,
|
| 275 |
+
"eval_accuracy": 0.8254,
|
| 276 |
+
"eval_f1_macro": 0.7229632924236448,
|
| 277 |
+
"eval_f1_micro": 0.8254,
|
| 278 |
+
"eval_loss": 0.6412187218666077,
|
| 279 |
+
"eval_runtime": 24.0401,
|
| 280 |
+
"eval_samples_per_second": 415.971,
|
| 281 |
+
"eval_steps_per_second": 6.531,
|
| 282 |
+
"step": 700
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.77,
|
| 286 |
+
"grad_norm": 1.6693323850631714,
|
| 287 |
+
"learning_rate": 0.00037117981520966596,
|
| 288 |
+
"loss": 0.6267,
|
| 289 |
+
"step": 725
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8,
|
| 293 |
+
"grad_norm": 2.042109251022339,
|
| 294 |
+
"learning_rate": 0.00036673773987206824,
|
| 295 |
+
"loss": 0.7153,
|
| 296 |
+
"step": 750
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.83,
|
| 300 |
+
"grad_norm": 1.5407096147537231,
|
| 301 |
+
"learning_rate": 0.0003622956645344705,
|
| 302 |
+
"loss": 0.6641,
|
| 303 |
+
"step": 775
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.85,
|
| 307 |
+
"grad_norm": 1.5067718029022217,
|
| 308 |
+
"learning_rate": 0.00035785358919687276,
|
| 309 |
+
"loss": 0.6544,
|
| 310 |
+
"step": 800
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.85,
|
| 314 |
+
"eval_accuracy": 0.8217,
|
| 315 |
+
"eval_f1_macro": 0.7223377361999187,
|
| 316 |
+
"eval_f1_micro": 0.8217,
|
| 317 |
+
"eval_loss": 0.6277242302894592,
|
| 318 |
+
"eval_runtime": 24.1366,
|
| 319 |
+
"eval_samples_per_second": 414.309,
|
| 320 |
+
"eval_steps_per_second": 6.505,
|
| 321 |
+
"step": 800
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.88,
|
| 325 |
+
"grad_norm": 2.1698966026306152,
|
| 326 |
+
"learning_rate": 0.00035341151385927504,
|
| 327 |
+
"loss": 0.7108,
|
| 328 |
+
"step": 825
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.91,
|
| 332 |
+
"grad_norm": 1.2698220014572144,
|
| 333 |
+
"learning_rate": 0.00034896943852167733,
|
| 334 |
+
"loss": 0.5897,
|
| 335 |
+
"step": 850
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.93,
|
| 339 |
+
"grad_norm": 2.0006988048553467,
|
| 340 |
+
"learning_rate": 0.0003445273631840796,
|
| 341 |
+
"loss": 0.6386,
|
| 342 |
+
"step": 875
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.96,
|
| 346 |
+
"grad_norm": 1.7718091011047363,
|
| 347 |
+
"learning_rate": 0.0003400852878464819,
|
| 348 |
+
"loss": 0.5781,
|
| 349 |
+
"step": 900
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.96,
|
| 353 |
+
"eval_accuracy": 0.8305,
|
| 354 |
+
"eval_f1_macro": 0.7420217283556048,
|
| 355 |
+
"eval_f1_micro": 0.8305,
|
| 356 |
+
"eval_loss": 0.6054204702377319,
|
| 357 |
+
"eval_runtime": 24.1901,
|
| 358 |
+
"eval_samples_per_second": 413.393,
|
| 359 |
+
"eval_steps_per_second": 6.49,
|
| 360 |
+
"step": 900
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.99,
|
| 364 |
+
"grad_norm": 1.9609644412994385,
|
| 365 |
+
"learning_rate": 0.00033564321250888413,
|
| 366 |
+
"loss": 0.6415,
|
| 367 |
+
"step": 925
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.01,
|
| 371 |
+
"grad_norm": 1.4652588367462158,
|
| 372 |
+
"learning_rate": 0.0003312011371712864,
|
| 373 |
+
"loss": 0.5699,
|
| 374 |
+
"step": 950
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.04,
|
| 378 |
+
"grad_norm": 1.6652113199234009,
|
| 379 |
+
"learning_rate": 0.0003267590618336887,
|
| 380 |
+
"loss": 0.486,
|
| 381 |
+
"step": 975
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.07,
|
| 385 |
+
"grad_norm": 1.3951687812805176,
|
| 386 |
+
"learning_rate": 0.000322316986496091,
|
| 387 |
+
"loss": 0.4674,
|
| 388 |
+
"step": 1000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.07,
|
| 392 |
+
"eval_accuracy": 0.8346,
|
| 393 |
+
"eval_f1_macro": 0.737133370653897,
|
| 394 |
+
"eval_f1_micro": 0.8346,
|
| 395 |
+
"eval_loss": 0.6210275292396545,
|
| 396 |
+
"eval_runtime": 24.1347,
|
| 397 |
+
"eval_samples_per_second": 414.342,
|
| 398 |
+
"eval_steps_per_second": 6.505,
|
| 399 |
+
"step": 1000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.09,
|
| 403 |
+
"grad_norm": 1.52338445186615,
|
| 404 |
+
"learning_rate": 0.00031787491115849327,
|
| 405 |
+
"loss": 0.4979,
|
| 406 |
+
"step": 1025
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.12,
|
| 410 |
+
"grad_norm": 1.9127336740493774,
|
| 411 |
+
"learning_rate": 0.00031343283582089556,
|
| 412 |
+
"loss": 0.4658,
|
| 413 |
+
"step": 1050
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.15,
|
| 417 |
+
"grad_norm": 1.5914901494979858,
|
| 418 |
+
"learning_rate": 0.00030899076048329784,
|
| 419 |
+
"loss": 0.5625,
|
| 420 |
+
"step": 1075
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.17,
|
| 424 |
+
"grad_norm": 2.0196564197540283,
|
| 425 |
+
"learning_rate": 0.0003045486851457001,
|
| 426 |
+
"loss": 0.4929,
|
| 427 |
+
"step": 1100
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.17,
|
| 431 |
+
"eval_accuracy": 0.8387,
|
| 432 |
+
"eval_f1_macro": 0.7423130077227065,
|
| 433 |
+
"eval_f1_micro": 0.8387,
|
| 434 |
+
"eval_loss": 0.5875550508499146,
|
| 435 |
+
"eval_runtime": 24.1428,
|
| 436 |
+
"eval_samples_per_second": 414.202,
|
| 437 |
+
"eval_steps_per_second": 6.503,
|
| 438 |
+
"step": 1100
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.2,
|
| 442 |
+
"grad_norm": 1.3181229829788208,
|
| 443 |
+
"learning_rate": 0.00030010660980810236,
|
| 444 |
+
"loss": 0.4999,
|
| 445 |
+
"step": 1125
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.23,
|
| 449 |
+
"grad_norm": 1.321296215057373,
|
| 450 |
+
"learning_rate": 0.00029566453447050464,
|
| 451 |
+
"loss": 0.4456,
|
| 452 |
+
"step": 1150
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.25,
|
| 456 |
+
"grad_norm": 1.4967468976974487,
|
| 457 |
+
"learning_rate": 0.0002912224591329069,
|
| 458 |
+
"loss": 0.443,
|
| 459 |
+
"step": 1175
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.28,
|
| 463 |
+
"grad_norm": 1.622883915901184,
|
| 464 |
+
"learning_rate": 0.00028678038379530916,
|
| 465 |
+
"loss": 0.566,
|
| 466 |
+
"step": 1200
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.28,
|
| 470 |
+
"eval_accuracy": 0.8475,
|
| 471 |
+
"eval_f1_macro": 0.7633448680546241,
|
| 472 |
+
"eval_f1_micro": 0.8475,
|
| 473 |
+
"eval_loss": 0.5779463648796082,
|
| 474 |
+
"eval_runtime": 24.1848,
|
| 475 |
+
"eval_samples_per_second": 413.483,
|
| 476 |
+
"eval_steps_per_second": 6.492,
|
| 477 |
+
"step": 1200
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.31,
|
| 481 |
+
"grad_norm": 2.2820820808410645,
|
| 482 |
+
"learning_rate": 0.00028233830845771145,
|
| 483 |
+
"loss": 0.5382,
|
| 484 |
+
"step": 1225
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.33,
|
| 488 |
+
"grad_norm": 1.5108492374420166,
|
| 489 |
+
"learning_rate": 0.00027789623312011373,
|
| 490 |
+
"loss": 0.5314,
|
| 491 |
+
"step": 1250
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.36,
|
| 495 |
+
"grad_norm": 1.2868916988372803,
|
| 496 |
+
"learning_rate": 0.00027345415778251596,
|
| 497 |
+
"loss": 0.4951,
|
| 498 |
+
"step": 1275
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.39,
|
| 502 |
+
"grad_norm": 2.0262043476104736,
|
| 503 |
+
"learning_rate": 0.00026901208244491825,
|
| 504 |
+
"loss": 0.4577,
|
| 505 |
+
"step": 1300
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.39,
|
| 509 |
+
"eval_accuracy": 0.8435,
|
| 510 |
+
"eval_f1_macro": 0.7507843808294652,
|
| 511 |
+
"eval_f1_micro": 0.8435,
|
| 512 |
+
"eval_loss": 0.5771787762641907,
|
| 513 |
+
"eval_runtime": 24.1138,
|
| 514 |
+
"eval_samples_per_second": 414.7,
|
| 515 |
+
"eval_steps_per_second": 6.511,
|
| 516 |
+
"step": 1300
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.41,
|
| 520 |
+
"grad_norm": 1.7890022993087769,
|
| 521 |
+
"learning_rate": 0.00026457000710732053,
|
| 522 |
+
"loss": 0.5097,
|
| 523 |
+
"step": 1325
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.44,
|
| 527 |
+
"grad_norm": 1.5777374505996704,
|
| 528 |
+
"learning_rate": 0.0002601279317697228,
|
| 529 |
+
"loss": 0.4894,
|
| 530 |
+
"step": 1350
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.47,
|
| 534 |
+
"grad_norm": 1.6835675239562988,
|
| 535 |
+
"learning_rate": 0.0002556858564321251,
|
| 536 |
+
"loss": 0.4487,
|
| 537 |
+
"step": 1375
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.49,
|
| 541 |
+
"grad_norm": 1.7419664859771729,
|
| 542 |
+
"learning_rate": 0.0002512437810945274,
|
| 543 |
+
"loss": 0.4233,
|
| 544 |
+
"step": 1400
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.49,
|
| 548 |
+
"eval_accuracy": 0.8476,
|
| 549 |
+
"eval_f1_macro": 0.7624728239220356,
|
| 550 |
+
"eval_f1_micro": 0.8476,
|
| 551 |
+
"eval_loss": 0.5580869913101196,
|
| 552 |
+
"eval_runtime": 24.1623,
|
| 553 |
+
"eval_samples_per_second": 413.868,
|
| 554 |
+
"eval_steps_per_second": 6.498,
|
| 555 |
+
"step": 1400
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.52,
|
| 559 |
+
"grad_norm": 1.6330546140670776,
|
| 560 |
+
"learning_rate": 0.0002468017057569296,
|
| 561 |
+
"loss": 0.4985,
|
| 562 |
+
"step": 1425
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.55,
|
| 566 |
+
"grad_norm": 1.5560388565063477,
|
| 567 |
+
"learning_rate": 0.00024235963041933193,
|
| 568 |
+
"loss": 0.4902,
|
| 569 |
+
"step": 1450
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.57,
|
| 573 |
+
"grad_norm": 1.1412893533706665,
|
| 574 |
+
"learning_rate": 0.0002379175550817342,
|
| 575 |
+
"loss": 0.4811,
|
| 576 |
+
"step": 1475
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.6,
|
| 580 |
+
"grad_norm": 1.4423662424087524,
|
| 581 |
+
"learning_rate": 0.00023347547974413648,
|
| 582 |
+
"loss": 0.4567,
|
| 583 |
+
"step": 1500
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.6,
|
| 587 |
+
"eval_accuracy": 0.8462,
|
| 588 |
+
"eval_f1_macro": 0.7575976290013776,
|
| 589 |
+
"eval_f1_micro": 0.8462,
|
| 590 |
+
"eval_loss": 0.5687991976737976,
|
| 591 |
+
"eval_runtime": 24.159,
|
| 592 |
+
"eval_samples_per_second": 413.925,
|
| 593 |
+
"eval_steps_per_second": 6.499,
|
| 594 |
+
"step": 1500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.63,
|
| 598 |
+
"grad_norm": 1.9873683452606201,
|
| 599 |
+
"learning_rate": 0.00022903340440653876,
|
| 600 |
+
"loss": 0.4455,
|
| 601 |
+
"step": 1525
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.65,
|
| 605 |
+
"grad_norm": 1.4635204076766968,
|
| 606 |
+
"learning_rate": 0.000224591329068941,
|
| 607 |
+
"loss": 0.4457,
|
| 608 |
+
"step": 1550
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.68,
|
| 612 |
+
"grad_norm": 1.56647789478302,
|
| 613 |
+
"learning_rate": 0.00022014925373134328,
|
| 614 |
+
"loss": 0.4223,
|
| 615 |
+
"step": 1575
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.71,
|
| 619 |
+
"grad_norm": 1.8017354011535645,
|
| 620 |
+
"learning_rate": 0.00021570717839374556,
|
| 621 |
+
"loss": 0.483,
|
| 622 |
+
"step": 1600
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.71,
|
| 626 |
+
"eval_accuracy": 0.8478,
|
| 627 |
+
"eval_f1_macro": 0.7608717953670078,
|
| 628 |
+
"eval_f1_micro": 0.8478,
|
| 629 |
+
"eval_loss": 0.5547010898590088,
|
| 630 |
+
"eval_runtime": 24.1023,
|
| 631 |
+
"eval_samples_per_second": 414.897,
|
| 632 |
+
"eval_steps_per_second": 6.514,
|
| 633 |
+
"step": 1600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.73,
|
| 637 |
+
"grad_norm": 1.768385887145996,
|
| 638 |
+
"learning_rate": 0.00021126510305614785,
|
| 639 |
+
"loss": 0.4593,
|
| 640 |
+
"step": 1625
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.76,
|
| 644 |
+
"grad_norm": 1.8453024625778198,
|
| 645 |
+
"learning_rate": 0.0002068230277185501,
|
| 646 |
+
"loss": 0.4378,
|
| 647 |
+
"step": 1650
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.79,
|
| 651 |
+
"grad_norm": 1.5103825330734253,
|
| 652 |
+
"learning_rate": 0.0002023809523809524,
|
| 653 |
+
"loss": 0.455,
|
| 654 |
+
"step": 1675
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.81,
|
| 658 |
+
"grad_norm": 1.8187497854232788,
|
| 659 |
+
"learning_rate": 0.00019793887704335468,
|
| 660 |
+
"loss": 0.4649,
|
| 661 |
+
"step": 1700
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.81,
|
| 665 |
+
"eval_accuracy": 0.851,
|
| 666 |
+
"eval_f1_macro": 0.7680217546192462,
|
| 667 |
+
"eval_f1_micro": 0.851,
|
| 668 |
+
"eval_loss": 0.5395861864089966,
|
| 669 |
+
"eval_runtime": 24.1531,
|
| 670 |
+
"eval_samples_per_second": 414.025,
|
| 671 |
+
"eval_steps_per_second": 6.5,
|
| 672 |
+
"step": 1700
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.84,
|
| 676 |
+
"grad_norm": 2.1151626110076904,
|
| 677 |
+
"learning_rate": 0.00019349680170575694,
|
| 678 |
+
"loss": 0.5057,
|
| 679 |
+
"step": 1725
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.87,
|
| 683 |
+
"grad_norm": 1.4344931840896606,
|
| 684 |
+
"learning_rate": 0.00018905472636815922,
|
| 685 |
+
"loss": 0.4275,
|
| 686 |
+
"step": 1750
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.89,
|
| 690 |
+
"grad_norm": 3.410400152206421,
|
| 691 |
+
"learning_rate": 0.00018461265103056148,
|
| 692 |
+
"loss": 0.4973,
|
| 693 |
+
"step": 1775
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.92,
|
| 697 |
+
"grad_norm": 2.3107552528381348,
|
| 698 |
+
"learning_rate": 0.00018017057569296374,
|
| 699 |
+
"loss": 0.4288,
|
| 700 |
+
"step": 1800
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.92,
|
| 704 |
+
"eval_accuracy": 0.8577,
|
| 705 |
+
"eval_f1_macro": 0.7759139835888773,
|
| 706 |
+
"eval_f1_micro": 0.8577,
|
| 707 |
+
"eval_loss": 0.5235319137573242,
|
| 708 |
+
"eval_runtime": 24.1535,
|
| 709 |
+
"eval_samples_per_second": 414.018,
|
| 710 |
+
"eval_steps_per_second": 6.5,
|
| 711 |
+
"step": 1800
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.95,
|
| 715 |
+
"grad_norm": 1.2763726711273193,
|
| 716 |
+
"learning_rate": 0.00017572850035536602,
|
| 717 |
+
"loss": 0.5008,
|
| 718 |
+
"step": 1825
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.97,
|
| 722 |
+
"grad_norm": 1.5869358777999878,
|
| 723 |
+
"learning_rate": 0.0001712864250177683,
|
| 724 |
+
"loss": 0.4581,
|
| 725 |
+
"step": 1850
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.0,
|
| 729 |
+
"grad_norm": 1.450799822807312,
|
| 730 |
+
"learning_rate": 0.0001668443496801706,
|
| 731 |
+
"loss": 0.4103,
|
| 732 |
+
"step": 1875
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.03,
|
| 736 |
+
"grad_norm": 1.3206963539123535,
|
| 737 |
+
"learning_rate": 0.00016240227434257285,
|
| 738 |
+
"loss": 0.3445,
|
| 739 |
+
"step": 1900
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.03,
|
| 743 |
+
"eval_accuracy": 0.8603,
|
| 744 |
+
"eval_f1_macro": 0.7790782413257752,
|
| 745 |
+
"eval_f1_micro": 0.8603,
|
| 746 |
+
"eval_loss": 0.520423948764801,
|
| 747 |
+
"eval_runtime": 24.0544,
|
| 748 |
+
"eval_samples_per_second": 415.724,
|
| 749 |
+
"eval_steps_per_second": 6.527,
|
| 750 |
+
"step": 1900
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.05,
|
| 754 |
+
"grad_norm": 1.3110324144363403,
|
| 755 |
+
"learning_rate": 0.00015796019900497514,
|
| 756 |
+
"loss": 0.3278,
|
| 757 |
+
"step": 1925
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.08,
|
| 761 |
+
"grad_norm": 1.4223313331604004,
|
| 762 |
+
"learning_rate": 0.00015351812366737742,
|
| 763 |
+
"loss": 0.3376,
|
| 764 |
+
"step": 1950
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.11,
|
| 768 |
+
"grad_norm": 1.6518670320510864,
|
| 769 |
+
"learning_rate": 0.00014907604832977968,
|
| 770 |
+
"loss": 0.3519,
|
| 771 |
+
"step": 1975
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.13,
|
| 775 |
+
"grad_norm": 1.5389341115951538,
|
| 776 |
+
"learning_rate": 0.00014463397299218194,
|
| 777 |
+
"loss": 0.3014,
|
| 778 |
+
"step": 2000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.13,
|
| 782 |
+
"eval_accuracy": 0.8607,
|
| 783 |
+
"eval_f1_macro": 0.786161944348828,
|
| 784 |
+
"eval_f1_micro": 0.8607,
|
| 785 |
+
"eval_loss": 0.5268532037734985,
|
| 786 |
+
"eval_runtime": 24.1182,
|
| 787 |
+
"eval_samples_per_second": 414.624,
|
| 788 |
+
"eval_steps_per_second": 6.51,
|
| 789 |
+
"step": 2000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.16,
|
| 793 |
+
"grad_norm": 1.810062289237976,
|
| 794 |
+
"learning_rate": 0.00014019189765458422,
|
| 795 |
+
"loss": 0.3184,
|
| 796 |
+
"step": 2025
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.19,
|
| 800 |
+
"grad_norm": 1.4731919765472412,
|
| 801 |
+
"learning_rate": 0.00013574982231698648,
|
| 802 |
+
"loss": 0.3457,
|
| 803 |
+
"step": 2050
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.21,
|
| 807 |
+
"grad_norm": 1.8230247497558594,
|
| 808 |
+
"learning_rate": 0.00013130774697938877,
|
| 809 |
+
"loss": 0.3107,
|
| 810 |
+
"step": 2075
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.24,
|
| 814 |
+
"grad_norm": 1.9620997905731201,
|
| 815 |
+
"learning_rate": 0.00012686567164179105,
|
| 816 |
+
"loss": 0.3301,
|
| 817 |
+
"step": 2100
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.24,
|
| 821 |
+
"eval_accuracy": 0.8591,
|
| 822 |
+
"eval_f1_macro": 0.7826263587368261,
|
| 823 |
+
"eval_f1_micro": 0.8591,
|
| 824 |
+
"eval_loss": 0.5233541131019592,
|
| 825 |
+
"eval_runtime": 24.1529,
|
| 826 |
+
"eval_samples_per_second": 414.03,
|
| 827 |
+
"eval_steps_per_second": 6.5,
|
| 828 |
+
"step": 2100
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.27,
|
| 832 |
+
"grad_norm": 1.9270436763763428,
|
| 833 |
+
"learning_rate": 0.0001224235963041933,
|
| 834 |
+
"loss": 0.3273,
|
| 835 |
+
"step": 2125
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.29,
|
| 839 |
+
"grad_norm": 1.2540065050125122,
|
| 840 |
+
"learning_rate": 0.0001179815209665956,
|
| 841 |
+
"loss": 0.2682,
|
| 842 |
+
"step": 2150
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.32,
|
| 846 |
+
"grad_norm": 0.6836864948272705,
|
| 847 |
+
"learning_rate": 0.00011353944562899787,
|
| 848 |
+
"loss": 0.2787,
|
| 849 |
+
"step": 2175
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.35,
|
| 853 |
+
"grad_norm": 1.7758402824401855,
|
| 854 |
+
"learning_rate": 0.00010909737029140014,
|
| 855 |
+
"loss": 0.3069,
|
| 856 |
+
"step": 2200
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.35,
|
| 860 |
+
"eval_accuracy": 0.8624,
|
| 861 |
+
"eval_f1_macro": 0.785058711126236,
|
| 862 |
+
"eval_f1_micro": 0.8624,
|
| 863 |
+
"eval_loss": 0.5265922546386719,
|
| 864 |
+
"eval_runtime": 24.117,
|
| 865 |
+
"eval_samples_per_second": 414.644,
|
| 866 |
+
"eval_steps_per_second": 6.51,
|
| 867 |
+
"step": 2200
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.37,
|
| 871 |
+
"grad_norm": 1.3381538391113281,
|
| 872 |
+
"learning_rate": 0.00010465529495380242,
|
| 873 |
+
"loss": 0.2866,
|
| 874 |
+
"step": 2225
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.4,
|
| 878 |
+
"grad_norm": 1.759792685508728,
|
| 879 |
+
"learning_rate": 0.0001002132196162047,
|
| 880 |
+
"loss": 0.3031,
|
| 881 |
+
"step": 2250
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 2.43,
|
| 885 |
+
"grad_norm": 1.2064933776855469,
|
| 886 |
+
"learning_rate": 9.577114427860697e-05,
|
| 887 |
+
"loss": 0.3182,
|
| 888 |
+
"step": 2275
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 2.45,
|
| 892 |
+
"grad_norm": 1.0604907274246216,
|
| 893 |
+
"learning_rate": 9.132906894100924e-05,
|
| 894 |
+
"loss": 0.3095,
|
| 895 |
+
"step": 2300
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 2.45,
|
| 899 |
+
"eval_accuracy": 0.8629,
|
| 900 |
+
"eval_f1_macro": 0.7846414495209991,
|
| 901 |
+
"eval_f1_micro": 0.8629,
|
| 902 |
+
"eval_loss": 0.5154865980148315,
|
| 903 |
+
"eval_runtime": 24.1319,
|
| 904 |
+
"eval_samples_per_second": 414.389,
|
| 905 |
+
"eval_steps_per_second": 6.506,
|
| 906 |
+
"step": 2300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.48,
|
| 910 |
+
"grad_norm": 1.9324097633361816,
|
| 911 |
+
"learning_rate": 8.688699360341151e-05,
|
| 912 |
+
"loss": 0.3321,
|
| 913 |
+
"step": 2325
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.51,
|
| 917 |
+
"grad_norm": 1.9070733785629272,
|
| 918 |
+
"learning_rate": 8.24449182658138e-05,
|
| 919 |
+
"loss": 0.3165,
|
| 920 |
+
"step": 2350
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.53,
|
| 924 |
+
"grad_norm": 1.3031100034713745,
|
| 925 |
+
"learning_rate": 7.800284292821607e-05,
|
| 926 |
+
"loss": 0.2939,
|
| 927 |
+
"step": 2375
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.56,
|
| 931 |
+
"grad_norm": 1.479374647140503,
|
| 932 |
+
"learning_rate": 7.356076759061834e-05,
|
| 933 |
+
"loss": 0.3164,
|
| 934 |
+
"step": 2400
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.56,
|
| 938 |
+
"eval_accuracy": 0.8646,
|
| 939 |
+
"eval_f1_macro": 0.7909189563960074,
|
| 940 |
+
"eval_f1_micro": 0.8646,
|
| 941 |
+
"eval_loss": 0.5106394290924072,
|
| 942 |
+
"eval_runtime": 24.1589,
|
| 943 |
+
"eval_samples_per_second": 413.927,
|
| 944 |
+
"eval_steps_per_second": 6.499,
|
| 945 |
+
"step": 2400
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.59,
|
| 949 |
+
"grad_norm": 1.6215256452560425,
|
| 950 |
+
"learning_rate": 6.911869225302061e-05,
|
| 951 |
+
"loss": 0.3524,
|
| 952 |
+
"step": 2425
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 2.61,
|
| 956 |
+
"grad_norm": 1.5538333654403687,
|
| 957 |
+
"learning_rate": 6.467661691542288e-05,
|
| 958 |
+
"loss": 0.3354,
|
| 959 |
+
"step": 2450
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 2.64,
|
| 963 |
+
"grad_norm": 1.515882134437561,
|
| 964 |
+
"learning_rate": 6.023454157782516e-05,
|
| 965 |
+
"loss": 0.2992,
|
| 966 |
+
"step": 2475
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 2.67,
|
| 970 |
+
"grad_norm": 2.216226100921631,
|
| 971 |
+
"learning_rate": 5.579246624022743e-05,
|
| 972 |
+
"loss": 0.2914,
|
| 973 |
+
"step": 2500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 2.67,
|
| 977 |
+
"eval_accuracy": 0.8647,
|
| 978 |
+
"eval_f1_macro": 0.7934095832580423,
|
| 979 |
+
"eval_f1_micro": 0.8647,
|
| 980 |
+
"eval_loss": 0.5055064558982849,
|
| 981 |
+
"eval_runtime": 24.1523,
|
| 982 |
+
"eval_samples_per_second": 414.039,
|
| 983 |
+
"eval_steps_per_second": 6.5,
|
| 984 |
+
"step": 2500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.69,
|
| 988 |
+
"grad_norm": 2.8203630447387695,
|
| 989 |
+
"learning_rate": 5.135039090262971e-05,
|
| 990 |
+
"loss": 0.321,
|
| 991 |
+
"step": 2525
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.72,
|
| 995 |
+
"grad_norm": 2.173407793045044,
|
| 996 |
+
"learning_rate": 4.690831556503199e-05,
|
| 997 |
+
"loss": 0.3,
|
| 998 |
+
"step": 2550
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.75,
|
| 1002 |
+
"grad_norm": 1.960857629776001,
|
| 1003 |
+
"learning_rate": 4.2466240227434255e-05,
|
| 1004 |
+
"loss": 0.3181,
|
| 1005 |
+
"step": 2575
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.77,
|
| 1009 |
+
"grad_norm": 1.7531359195709229,
|
| 1010 |
+
"learning_rate": 3.802416488983653e-05,
|
| 1011 |
+
"loss": 0.2946,
|
| 1012 |
+
"step": 2600
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.77,
|
| 1016 |
+
"eval_accuracy": 0.8643,
|
| 1017 |
+
"eval_f1_macro": 0.7917093314024903,
|
| 1018 |
+
"eval_f1_micro": 0.8643,
|
| 1019 |
+
"eval_loss": 0.502694308757782,
|
| 1020 |
+
"eval_runtime": 24.1319,
|
| 1021 |
+
"eval_samples_per_second": 414.389,
|
| 1022 |
+
"eval_steps_per_second": 6.506,
|
| 1023 |
+
"step": 2600
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.8,
|
| 1027 |
+
"grad_norm": 1.2817922830581665,
|
| 1028 |
+
"learning_rate": 3.3582089552238805e-05,
|
| 1029 |
+
"loss": 0.2963,
|
| 1030 |
+
"step": 2625
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 2.83,
|
| 1034 |
+
"grad_norm": 2.3058297634124756,
|
| 1035 |
+
"learning_rate": 2.9140014214641083e-05,
|
| 1036 |
+
"loss": 0.33,
|
| 1037 |
+
"step": 2650
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 2.85,
|
| 1041 |
+
"grad_norm": 1.1777921915054321,
|
| 1042 |
+
"learning_rate": 2.4697938877043355e-05,
|
| 1043 |
+
"loss": 0.3122,
|
| 1044 |
+
"step": 2675
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.88,
|
| 1048 |
+
"grad_norm": 1.6172949075698853,
|
| 1049 |
+
"learning_rate": 2.025586353944563e-05,
|
| 1050 |
+
"loss": 0.3012,
|
| 1051 |
+
"step": 2700
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.88,
|
| 1055 |
+
"eval_accuracy": 0.8671,
|
| 1056 |
+
"eval_f1_macro": 0.7953004112768677,
|
| 1057 |
+
"eval_f1_micro": 0.8671,
|
| 1058 |
+
"eval_loss": 0.500918984413147,
|
| 1059 |
+
"eval_runtime": 24.1653,
|
| 1060 |
+
"eval_samples_per_second": 413.817,
|
| 1061 |
+
"eval_steps_per_second": 6.497,
|
| 1062 |
+
"step": 2700
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.91,
|
| 1066 |
+
"grad_norm": 1.0941059589385986,
|
| 1067 |
+
"learning_rate": 1.5813788201847902e-05,
|
| 1068 |
+
"loss": 0.2869,
|
| 1069 |
+
"step": 2725
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.93,
|
| 1073 |
+
"grad_norm": 1.700844168663025,
|
| 1074 |
+
"learning_rate": 1.1371712864250177e-05,
|
| 1075 |
+
"loss": 0.2968,
|
| 1076 |
+
"step": 2750
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.96,
|
| 1080 |
+
"grad_norm": 1.8403632640838623,
|
| 1081 |
+
"learning_rate": 6.929637526652452e-06,
|
| 1082 |
+
"loss": 0.272,
|
| 1083 |
+
"step": 2775
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.99,
|
| 1087 |
+
"grad_norm": 1.8172844648361206,
|
| 1088 |
+
"learning_rate": 2.4875621890547264e-06,
|
| 1089 |
+
"loss": 0.3181,
|
| 1090 |
+
"step": 2800
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.99,
|
| 1094 |
+
"eval_accuracy": 0.8664,
|
| 1095 |
+
"eval_f1_macro": 0.7947908970820687,
|
| 1096 |
+
"eval_f1_micro": 0.8664,
|
| 1097 |
+
"eval_loss": 0.5004217028617859,
|
| 1098 |
+
"eval_runtime": 24.1769,
|
| 1099 |
+
"eval_samples_per_second": 413.617,
|
| 1100 |
+
"eval_steps_per_second": 6.494,
|
| 1101 |
+
"step": 2800
|
| 1102 |
+
}
|
| 1103 |
+
],
|
| 1104 |
+
"logging_steps": 25,
|
| 1105 |
+
"max_steps": 2814,
|
| 1106 |
+
"num_input_tokens_seen": 0,
|
| 1107 |
+
"num_train_epochs": 3,
|
| 1108 |
+
"save_steps": 100,
|
| 1109 |
+
"total_flos": 2.737317734462259e+16,
|
| 1110 |
+
"train_batch_size": 32,
|
| 1111 |
+
"trial_name": null,
|
| 1112 |
+
"trial_params": null
|
| 1113 |
+
}
|
google_t5/t5_base_ledgar/checkpoint-2800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:986d82ea9721f626a5daebec5a86078b62c60c449ec04e11dee9e747b5a7de49
|
| 3 |
+
size 5048
|
google_t5/t5_base_ledgar/config.json
ADDED
|
@@ -0,0 +1,267 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-t5/t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"finetuning_task": "text-classification",
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "0",
|
| 18 |
+
"1": "1",
|
| 19 |
+
"2": "10",
|
| 20 |
+
"3": "11",
|
| 21 |
+
"4": "12",
|
| 22 |
+
"5": "13",
|
| 23 |
+
"6": "14",
|
| 24 |
+
"7": "15",
|
| 25 |
+
"8": "16",
|
| 26 |
+
"9": "17",
|
| 27 |
+
"10": "18",
|
| 28 |
+
"11": "19",
|
| 29 |
+
"12": "2",
|
| 30 |
+
"13": "20",
|
| 31 |
+
"14": "21",
|
| 32 |
+
"15": "22",
|
| 33 |
+
"16": "23",
|
| 34 |
+
"17": "24",
|
| 35 |
+
"18": "25",
|
| 36 |
+
"19": "26",
|
| 37 |
+
"20": "27",
|
| 38 |
+
"21": "28",
|
| 39 |
+
"22": "29",
|
| 40 |
+
"23": "3",
|
| 41 |
+
"24": "30",
|
| 42 |
+
"25": "31",
|
| 43 |
+
"26": "32",
|
| 44 |
+
"27": "33",
|
| 45 |
+
"28": "34",
|
| 46 |
+
"29": "35",
|
| 47 |
+
"30": "36",
|
| 48 |
+
"31": "37",
|
| 49 |
+
"32": "38",
|
| 50 |
+
"33": "39",
|
| 51 |
+
"34": "4",
|
| 52 |
+
"35": "40",
|
| 53 |
+
"36": "41",
|
| 54 |
+
"37": "42",
|
| 55 |
+
"38": "43",
|
| 56 |
+
"39": "44",
|
| 57 |
+
"40": "45",
|
| 58 |
+
"41": "46",
|
| 59 |
+
"42": "47",
|
| 60 |
+
"43": "48",
|
| 61 |
+
"44": "49",
|
| 62 |
+
"45": "5",
|
| 63 |
+
"46": "50",
|
| 64 |
+
"47": "51",
|
| 65 |
+
"48": "52",
|
| 66 |
+
"49": "53",
|
| 67 |
+
"50": "54",
|
| 68 |
+
"51": "55",
|
| 69 |
+
"52": "56",
|
| 70 |
+
"53": "57",
|
| 71 |
+
"54": "58",
|
| 72 |
+
"55": "59",
|
| 73 |
+
"56": "6",
|
| 74 |
+
"57": "60",
|
| 75 |
+
"58": "61",
|
| 76 |
+
"59": "62",
|
| 77 |
+
"60": "63",
|
| 78 |
+
"61": "64",
|
| 79 |
+
"62": "65",
|
| 80 |
+
"63": "66",
|
| 81 |
+
"64": "67",
|
| 82 |
+
"65": "68",
|
| 83 |
+
"66": "69",
|
| 84 |
+
"67": "7",
|
| 85 |
+
"68": "70",
|
| 86 |
+
"69": "71",
|
| 87 |
+
"70": "72",
|
| 88 |
+
"71": "73",
|
| 89 |
+
"72": "74",
|
| 90 |
+
"73": "75",
|
| 91 |
+
"74": "76",
|
| 92 |
+
"75": "77",
|
| 93 |
+
"76": "78",
|
| 94 |
+
"77": "79",
|
| 95 |
+
"78": "8",
|
| 96 |
+
"79": "80",
|
| 97 |
+
"80": "81",
|
| 98 |
+
"81": "82",
|
| 99 |
+
"82": "83",
|
| 100 |
+
"83": "84",
|
| 101 |
+
"84": "85",
|
| 102 |
+
"85": "86",
|
| 103 |
+
"86": "87",
|
| 104 |
+
"87": "88",
|
| 105 |
+
"88": "89",
|
| 106 |
+
"89": "9",
|
| 107 |
+
"90": "90",
|
| 108 |
+
"91": "91",
|
| 109 |
+
"92": "92",
|
| 110 |
+
"93": "93",
|
| 111 |
+
"94": "94",
|
| 112 |
+
"95": "95",
|
| 113 |
+
"96": "96",
|
| 114 |
+
"97": "97",
|
| 115 |
+
"98": "98",
|
| 116 |
+
"99": "99"
|
| 117 |
+
},
|
| 118 |
+
"initializer_factor": 1.0,
|
| 119 |
+
"is_encoder_decoder": true,
|
| 120 |
+
"is_gated_act": false,
|
| 121 |
+
"label2id": {
|
| 122 |
+
"0": 0,
|
| 123 |
+
"1": 1,
|
| 124 |
+
"10": 2,
|
| 125 |
+
"11": 3,
|
| 126 |
+
"12": 4,
|
| 127 |
+
"13": 5,
|
| 128 |
+
"14": 6,
|
| 129 |
+
"15": 7,
|
| 130 |
+
"16": 8,
|
| 131 |
+
"17": 9,
|
| 132 |
+
"18": 10,
|
| 133 |
+
"19": 11,
|
| 134 |
+
"2": 12,
|
| 135 |
+
"20": 13,
|
| 136 |
+
"21": 14,
|
| 137 |
+
"22": 15,
|
| 138 |
+
"23": 16,
|
| 139 |
+
"24": 17,
|
| 140 |
+
"25": 18,
|
| 141 |
+
"26": 19,
|
| 142 |
+
"27": 20,
|
| 143 |
+
"28": 21,
|
| 144 |
+
"29": 22,
|
| 145 |
+
"3": 23,
|
| 146 |
+
"30": 24,
|
| 147 |
+
"31": 25,
|
| 148 |
+
"32": 26,
|
| 149 |
+
"33": 27,
|
| 150 |
+
"34": 28,
|
| 151 |
+
"35": 29,
|
| 152 |
+
"36": 30,
|
| 153 |
+
"37": 31,
|
| 154 |
+
"38": 32,
|
| 155 |
+
"39": 33,
|
| 156 |
+
"4": 34,
|
| 157 |
+
"40": 35,
|
| 158 |
+
"41": 36,
|
| 159 |
+
"42": 37,
|
| 160 |
+
"43": 38,
|
| 161 |
+
"44": 39,
|
| 162 |
+
"45": 40,
|
| 163 |
+
"46": 41,
|
| 164 |
+
"47": 42,
|
| 165 |
+
"48": 43,
|
| 166 |
+
"49": 44,
|
| 167 |
+
"5": 45,
|
| 168 |
+
"50": 46,
|
| 169 |
+
"51": 47,
|
| 170 |
+
"52": 48,
|
| 171 |
+
"53": 49,
|
| 172 |
+
"54": 50,
|
| 173 |
+
"55": 51,
|
| 174 |
+
"56": 52,
|
| 175 |
+
"57": 53,
|
| 176 |
+
"58": 54,
|
| 177 |
+
"59": 55,
|
| 178 |
+
"6": 56,
|
| 179 |
+
"60": 57,
|
| 180 |
+
"61": 58,
|
| 181 |
+
"62": 59,
|
| 182 |
+
"63": 60,
|
| 183 |
+
"64": 61,
|
| 184 |
+
"65": 62,
|
| 185 |
+
"66": 63,
|
| 186 |
+
"67": 64,
|
| 187 |
+
"68": 65,
|
| 188 |
+
"69": 66,
|
| 189 |
+
"7": 67,
|
| 190 |
+
"70": 68,
|
| 191 |
+
"71": 69,
|
| 192 |
+
"72": 70,
|
| 193 |
+
"73": 71,
|
| 194 |
+
"74": 72,
|
| 195 |
+
"75": 73,
|
| 196 |
+
"76": 74,
|
| 197 |
+
"77": 75,
|
| 198 |
+
"78": 76,
|
| 199 |
+
"79": 77,
|
| 200 |
+
"8": 78,
|
| 201 |
+
"80": 79,
|
| 202 |
+
"81": 80,
|
| 203 |
+
"82": 81,
|
| 204 |
+
"83": 82,
|
| 205 |
+
"84": 83,
|
| 206 |
+
"85": 84,
|
| 207 |
+
"86": 85,
|
| 208 |
+
"87": 86,
|
| 209 |
+
"88": 87,
|
| 210 |
+
"89": 88,
|
| 211 |
+
"9": 89,
|
| 212 |
+
"90": 90,
|
| 213 |
+
"91": 91,
|
| 214 |
+
"92": 92,
|
| 215 |
+
"93": 93,
|
| 216 |
+
"94": 94,
|
| 217 |
+
"95": 95,
|
| 218 |
+
"96": 96,
|
| 219 |
+
"97": 97,
|
| 220 |
+
"98": 98,
|
| 221 |
+
"99": 99
|
| 222 |
+
},
|
| 223 |
+
"layer_norm_epsilon": 1e-06,
|
| 224 |
+
"model_type": "t5",
|
| 225 |
+
"n_positions": 512,
|
| 226 |
+
"num_decoder_layers": 12,
|
| 227 |
+
"num_heads": 12,
|
| 228 |
+
"num_layers": 12,
|
| 229 |
+
"output_past": true,
|
| 230 |
+
"pad_token_id": 0,
|
| 231 |
+
"problem_type": "single_label_classification",
|
| 232 |
+
"relative_attention_max_distance": 128,
|
| 233 |
+
"relative_attention_num_buckets": 32,
|
| 234 |
+
"task_specific_params": {
|
| 235 |
+
"summarization": {
|
| 236 |
+
"early_stopping": true,
|
| 237 |
+
"length_penalty": 2.0,
|
| 238 |
+
"max_length": 200,
|
| 239 |
+
"min_length": 30,
|
| 240 |
+
"no_repeat_ngram_size": 3,
|
| 241 |
+
"num_beams": 4,
|
| 242 |
+
"prefix": "summarize: "
|
| 243 |
+
},
|
| 244 |
+
"translation_en_to_de": {
|
| 245 |
+
"early_stopping": true,
|
| 246 |
+
"max_length": 300,
|
| 247 |
+
"num_beams": 4,
|
| 248 |
+
"prefix": "translate English to German: "
|
| 249 |
+
},
|
| 250 |
+
"translation_en_to_fr": {
|
| 251 |
+
"early_stopping": true,
|
| 252 |
+
"max_length": 300,
|
| 253 |
+
"num_beams": 4,
|
| 254 |
+
"prefix": "translate English to French: "
|
| 255 |
+
},
|
| 256 |
+
"translation_en_to_ro": {
|
| 257 |
+
"early_stopping": true,
|
| 258 |
+
"max_length": 300,
|
| 259 |
+
"num_beams": 4,
|
| 260 |
+
"prefix": "translate English to Romanian: "
|
| 261 |
+
}
|
| 262 |
+
},
|
| 263 |
+
"torch_dtype": "float32",
|
| 264 |
+
"transformers_version": "4.39.0.dev0",
|
| 265 |
+
"use_cache": true,
|
| 266 |
+
"vocab_size": 32128
|
| 267 |
+
}
|
google_t5/t5_base_ledgar/eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8664,
|
| 4 |
+
"eval_f1_macro": 0.7947908970820687,
|
| 5 |
+
"eval_f1_micro": 0.8664,
|
| 6 |
+
"eval_loss": 0.5004217028617859,
|
| 7 |
+
"eval_runtime": 23.9278,
|
| 8 |
+
"eval_samples": 10000,
|
| 9 |
+
"eval_samples_per_second": 417.924,
|
| 10 |
+
"eval_steps_per_second": 6.561
|
| 11 |
+
}
|
google_t5/t5_base_ledgar/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bec396a5ee38fb93b45dcbfe6b134f5c7adba0ea2c64f0184a3f24a69faff1e
|
| 3 |
+
size 894318160
|
google_t5/t5_base_ledgar/run.log
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
03/15/2024 18:45:09 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False
|
| 2 |
+
03/15/2024 18:45:09 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, 16-bits training: False
|
| 3 |
+
03/15/2024 18:45:13 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
|
| 4 |
+
03/15/2024 18:45:13 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
|
google_t5/t5_base_ledgar/special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
google_t5/t5_base_ledgar/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
google_t5/t5_base_ledgar/test_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"test_accuracy": 0.871,
|
| 4 |
+
"test_f1_macro": 0.7998698141352754,
|
| 5 |
+
"test_f1_micro": 0.871,
|
| 6 |
+
"test_loss": 0.5104538798332214,
|
| 7 |
+
"test_runtime": 23.9487,
|
| 8 |
+
"test_samples_per_second": 417.56,
|
| 9 |
+
"test_steps_per_second": 6.556
|
| 10 |
+
}
|
google_t5/t5_base_ledgar/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
google_t5/t5_base_ledgar/tokenizer_config.json
ADDED
|
@@ -0,0 +1,937 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 512,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"tokenizer_class": "T5Tokenizer",
|
| 936 |
+
"unk_token": "<unk>"
|
| 937 |
+
}
|
google_t5/t5_base_ledgar/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.5752294131348806,
|
| 4 |
+
"train_runtime": 2000.5798,
|
| 5 |
+
"train_samples": 60000,
|
| 6 |
+
"train_samples_per_second": 89.974,
|
| 7 |
+
"train_steps_per_second": 1.407
|
| 8 |
+
}
|