gpt-peter-2pt7B-peter_DS-msgs_Ep-1_Bs-2
Browse files- .gitignore +1 -0
- README.md +50 -0
- config.json +82 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
README.md
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: checkpoints
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# checkpoints
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [pszemraj/gpt-peter-2.7B](https://huggingface.co/pszemraj/gpt-peter-2.7B) on the None dataset.
|
| 15 |
+
|
| 16 |
+
## Model description
|
| 17 |
+
|
| 18 |
+
More information needed
|
| 19 |
+
|
| 20 |
+
## Intended uses & limitations
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Training and evaluation data
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
### Training hyperparameters
|
| 31 |
+
|
| 32 |
+
The following hyperparameters were used during training:
|
| 33 |
+
- learning_rate: 6e-05
|
| 34 |
+
- train_batch_size: 2
|
| 35 |
+
- eval_batch_size: 2
|
| 36 |
+
- seed: 42
|
| 37 |
+
- distributed_type: multi-GPU
|
| 38 |
+
- gradient_accumulation_steps: 32
|
| 39 |
+
- total_train_batch_size: 64
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: cosine
|
| 42 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 43 |
+
- num_epochs: 1
|
| 44 |
+
|
| 45 |
+
### Framework versions
|
| 46 |
+
|
| 47 |
+
- Transformers 4.17.0
|
| 48 |
+
- Pytorch 1.10.0+cu113
|
| 49 |
+
- Datasets 2.0.0
|
| 50 |
+
- Tokenizers 0.11.6
|
config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pszemraj/gpt-peter-2.7B",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTNeoForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0,
|
| 8 |
+
"attention_layers": [
|
| 9 |
+
"global",
|
| 10 |
+
"local",
|
| 11 |
+
"global",
|
| 12 |
+
"local",
|
| 13 |
+
"global",
|
| 14 |
+
"local",
|
| 15 |
+
"global",
|
| 16 |
+
"local",
|
| 17 |
+
"global",
|
| 18 |
+
"local",
|
| 19 |
+
"global",
|
| 20 |
+
"local",
|
| 21 |
+
"global",
|
| 22 |
+
"local",
|
| 23 |
+
"global",
|
| 24 |
+
"local",
|
| 25 |
+
"global",
|
| 26 |
+
"local",
|
| 27 |
+
"global",
|
| 28 |
+
"local",
|
| 29 |
+
"global",
|
| 30 |
+
"local",
|
| 31 |
+
"global",
|
| 32 |
+
"local",
|
| 33 |
+
"global",
|
| 34 |
+
"local",
|
| 35 |
+
"global",
|
| 36 |
+
"local",
|
| 37 |
+
"global",
|
| 38 |
+
"local",
|
| 39 |
+
"global",
|
| 40 |
+
"local"
|
| 41 |
+
],
|
| 42 |
+
"attention_types": [
|
| 43 |
+
[
|
| 44 |
+
[
|
| 45 |
+
"global",
|
| 46 |
+
"local"
|
| 47 |
+
],
|
| 48 |
+
16
|
| 49 |
+
]
|
| 50 |
+
],
|
| 51 |
+
"bos_token_id": 50256,
|
| 52 |
+
"embed_dropout": 0,
|
| 53 |
+
"eos_token_id": 50256,
|
| 54 |
+
"gradient_checkpointing": false,
|
| 55 |
+
"hidden_size": 2560,
|
| 56 |
+
"initializer_range": 0.02,
|
| 57 |
+
"intermediate_size": null,
|
| 58 |
+
"layer_norm_epsilon": 1e-05,
|
| 59 |
+
"max_position_embeddings": 2048,
|
| 60 |
+
"model_type": "gpt_neo",
|
| 61 |
+
"num_heads": 20,
|
| 62 |
+
"num_layers": 32,
|
| 63 |
+
"resid_dropout": 0,
|
| 64 |
+
"summary_activation": null,
|
| 65 |
+
"summary_first_dropout": 0.1,
|
| 66 |
+
"summary_proj_to_labels": true,
|
| 67 |
+
"summary_type": "cls_index",
|
| 68 |
+
"summary_use_proj": true,
|
| 69 |
+
"task_specific_params": {
|
| 70 |
+
"text-generation": {
|
| 71 |
+
"do_sample": true,
|
| 72 |
+
"max_length": 50,
|
| 73 |
+
"temperature": 0.9
|
| 74 |
+
}
|
| 75 |
+
},
|
| 76 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 77 |
+
"torch_dtype": "bfloat16",
|
| 78 |
+
"transformers_version": "4.17.0",
|
| 79 |
+
"use_cache": false,
|
| 80 |
+
"vocab_size": 50257,
|
| 81 |
+
"window_size": 256
|
| 82 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cde81870796fb56ea3a0b583362438368eb1e0033898750b368d188c8df5ba83
|
| 3 |
+
size 5571155658
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c9435f9d13e7de946370411fba2d7164d2ba4c8e0d09bb7ef551c5b6a58ee9
|
| 3 |
+
size 4015
|