First commit

README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: language-modeling
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# language-modeling
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4229
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: tpu
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.16.0.dev0
+- Pytorch 1.8.1+cu102
+- Datasets 1.13.3
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.422879934310913,
+    "eval_runtime": 543.4644,
+    "eval_samples": 179869,
+    "eval_samples_per_second": 330.967,
+    "eval_steps_per_second": 5.172,
+    "perplexity": 4.1490522485207775,
+    "train_loss": 1.7074700184427065,
+    "train_runtime": 2192.338,
+    "train_samples": 179869,
+    "train_samples_per_second": 246.133,
+    "train_steps_per_second": 3.847
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.422879934310913,
+    "eval_runtime": 543.4644,
+    "eval_samples": 179869,
+    "eval_samples_per_second": 330.967,
+    "eval_steps_per_second": 5.172,
+    "perplexity": 4.1490522485207775
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc010a9a1455299babe2ec5aacf6769030e72ab4d1678bf4d5edc0a000be35a
+size 498862438

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.7074700184427065,
+    "train_runtime": 2192.338,
+    "train_samples": 179869,
+    "train_samples_per_second": 246.133,
+    "train_steps_per_second": 3.847
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 8433,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.7035455946875374e-05,
+      "loss": 2.3765,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.4070911893750746e-05,
+      "loss": 2.0326,
+      "step": 1000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.110636784062611e-05,
+      "loss": 1.9006,
+      "step": 1500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.8141823787501484e-05,
+      "loss": 1.8182,
+      "step": 2000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.5177279734376856e-05,
+      "loss": 1.763,
+      "step": 2500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.221273568125223e-05,
+      "loss": 1.7162,
+      "step": 3000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.9248191628127597e-05,
+      "loss": 1.6754,
+      "step": 3500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.628364757500297e-05,
+      "loss": 1.6466,
+      "step": 4000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3319103521878334e-05,
+      "loss": 1.6309,
+      "step": 4500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.0354559468753706e-05,
+      "loss": 1.5998,
+      "step": 5000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.7390015415629078e-05,
+      "loss": 1.5846,
+      "step": 5500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.4425471362504448e-05,
+      "loss": 1.5677,
+      "step": 6000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.1460927309379819e-05,
+      "loss": 1.5562,
+      "step": 6500
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.496383256255189e-06,
+      "loss": 1.5459,
+      "step": 7000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.531839203130558e-06,
+      "loss": 1.5372,
+      "step": 7500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.567295150005929e-06,
+      "loss": 1.5282,
+      "step": 8000
+    },
+    {
+      "epoch": 3.0,
+      "step": 8433,
+      "total_flos": 1.7760941215801344e+16,
+      "train_loss": 1.7074700184427065,
+      "train_runtime": 2192.338,
+      "train_samples_per_second": 246.133,
+      "train_steps_per_second": 3.847
+    }
+  ],
+  "max_steps": 8433,
+  "num_train_epochs": 3,
+  "total_flos": 1.7760941215801344e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22d69cc722820e2b2a51be2dd469823a0259822affe8e3dec86efe81060f562
+size 3055