Training in progress, step 13000, checkpoint

checkpoint-13000/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<bos>": 40478,
+  "<eos>": 40479,
+  "<pad>": 40480
+}

checkpoint-13000/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "openai-gpt",
+  "afn": "gelu",
+  "architectures": [
+    "OpenAIGPTForSequenceClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "embd_pdrop": 0.1,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "openai-gpt",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 512,
+  "n_special": 0,
+  "pad_token_id": 40480,
+  "predict_special_tokens": true,
+  "problem_type": "single_label_classification",
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0.dev0",
+  "vocab_size": 40481
+}

checkpoint-13000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ecf02bb493e5750b329268cf6c01742576923aa2ce17ced62436cff8ca1780
+size 932401285

checkpoint-13000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78ebdcdc71cc1d3087d075b844aa8f8ff5a87417f68ae1fa5338f9218ff5fd8
+size 466205145

checkpoint-13000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326b28681c4c95a80f1163556c7b33c6678b6b23895e86373566b2aabc38d1aa
+size 14575

checkpoint-13000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2209544801725bcb4080664e5f3dfeb4d307e48d36c8bea86f7481318f09abe
+size 627

checkpoint-13000/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

checkpoint-13000/tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 512,
+  "padding_side": "left",
+  "tokenizer_class": "OpenAIGPTTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-13000/trainer_state.json

@@ -0,0 +1,220 @@
+{
+  "best_metric": 1.0890672206878662,
+  "best_model_checkpoint": "/kaggle/output/checkpoint-12000",
+  "epoch": 0.5296610169491526,
+  "eval_steps": 1000,
+  "global_step": 13000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.7777777777777777e-11,
+      "loss": 1.1065,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.7750000000000004e-08,
+      "loss": 1.1586,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.32954091816367265,
+      "eval_loss": 1.1065887212753296,
+      "eval_runtime": 54.4372,
+      "eval_samples_per_second": 92.033,
+      "eval_steps_per_second": 11.518,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.5527777777777784e-08,
+      "loss": 1.1259,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.3435129740518962,
+      "eval_loss": 1.1045255661010742,
+      "eval_runtime": 54.458,
+      "eval_samples_per_second": 91.997,
+      "eval_steps_per_second": 11.513,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.327777777777778e-08,
+      "loss": 1.1229,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.3441117764471058,
+      "eval_loss": 1.1050777435302734,
+      "eval_runtime": 54.349,
+      "eval_samples_per_second": 92.182,
+      "eval_steps_per_second": 11.537,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1105555555555557e-07,
+      "loss": 1.1237,
+      "step": 4000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.3411177644710579,
+      "eval_loss": 1.1015312671661377,
+      "eval_runtime": 54.4388,
+      "eval_samples_per_second": 92.03,
+      "eval_steps_per_second": 11.518,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.3883333333333335e-07,
+      "loss": 1.1202,
+      "step": 5000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.3405189620758483,
+      "eval_loss": 1.1006112098693848,
+      "eval_runtime": 54.4109,
+      "eval_samples_per_second": 92.077,
+      "eval_steps_per_second": 11.523,
+      "step": 5000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.6658333333333335e-07,
+      "loss": 1.1182,
+      "step": 6000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.35489021956087824,
+      "eval_loss": 1.0982259511947632,
+      "eval_runtime": 54.3841,
+      "eval_samples_per_second": 92.123,
+      "eval_steps_per_second": 11.529,
+      "step": 6000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9436111111111112e-07,
+      "loss": 1.1125,
+      "step": 7000
+    },
+    {
+      "epoch": 0.29,
+      "eval_accuracy": 0.35748502994011977,
+      "eval_loss": 1.0954252481460571,
+      "eval_runtime": 54.3975,
+      "eval_samples_per_second": 92.1,
+      "eval_steps_per_second": 11.526,
+      "step": 7000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.2213888888888891e-07,
+      "loss": 1.1096,
+      "step": 8000
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.3664670658682635,
+      "eval_loss": 1.0949230194091797,
+      "eval_runtime": 54.3263,
+      "eval_samples_per_second": 92.221,
+      "eval_steps_per_second": 11.541,
+      "step": 8000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.4988888888888893e-07,
+      "loss": 1.1057,
+      "step": 9000
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.34890219560878244,
+      "eval_loss": 1.1037237644195557,
+      "eval_runtime": 54.3657,
+      "eval_samples_per_second": 92.154,
+      "eval_steps_per_second": 11.533,
+      "step": 9000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.776666666666667e-07,
+      "loss": 1.1056,
+      "step": 10000
+    },
+    {
+      "epoch": 0.41,
+      "eval_accuracy": 0.3838323353293413,
+      "eval_loss": 1.0928014516830444,
+      "eval_runtime": 54.6518,
+      "eval_samples_per_second": 91.671,
+      "eval_steps_per_second": 11.473,
+      "step": 10000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.054444444444444e-07,
+      "loss": 1.1036,
+      "step": 11000
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.3838323353293413,
+      "eval_loss": 1.0908663272857666,
+      "eval_runtime": 54.579,
+      "eval_samples_per_second": 91.794,
+      "eval_steps_per_second": 11.488,
+      "step": 11000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.3322222222222225e-07,
+      "loss": 1.1012,
+      "step": 12000
+    },
+    {
+      "epoch": 0.49,
+      "eval_accuracy": 0.3872255489021956,
+      "eval_loss": 1.0890672206878662,
+      "eval_runtime": 54.5139,
+      "eval_samples_per_second": 91.903,
+      "eval_steps_per_second": 11.502,
+      "step": 12000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.609722222222222e-07,
+      "loss": 1.103,
+      "step": 13000
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.34311377245508984,
+      "eval_loss": 1.0942790508270264,
+      "eval_runtime": 54.3951,
+      "eval_samples_per_second": 92.104,
+      "eval_steps_per_second": 11.527,
+      "step": 13000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000000,
+  "num_train_epochs": 408,
+  "save_steps": 1000,
+  "total_flos": 2.7174616694784e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-13000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801932cde7104ce385ac1157cb55104d9d1819c965a9990b2a3d508b76c6c359
+size 4091