Training in progress, step 10000, checkpoint

checkpoint-10000/added_tokens.json

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

checkpoint-10000/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": "last",
+  "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-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d2891de25dc82110b608ab8288039af735efc19cea5e34687f30d531ea7535
+size 932401285

checkpoint-10000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbf43eec82160015d3cced3b18dbf22f8ad5c492827da24e02feeebc1b5e948
+size 466205145

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146c47eb87103f8cc809328373c0295bf8202ab19807e559a80500b6835e379f
+size 14575

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1693827ef2c6d5014c4e48e1d368db2565001206a2e1dee05981196602b00b
+size 627

checkpoint-10000/special_tokens_map.json

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

checkpoint-10000/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-10000/trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 1.1056212186813354,
+  "best_model_checkpoint": "/kaggle/output/checkpoint-6000",
+  "epoch": 160.0,
+  "eval_steps": 1000,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.7777777777777777e-11,
+      "loss": 1.5477,
+      "step": 1
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.7750000000000004e-08,
+      "loss": 1.2028,
+      "step": 1000
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.3387225548902196,
+      "eval_loss": 1.1078879833221436,
+      "eval_runtime": 54.1057,
+      "eval_samples_per_second": 92.596,
+      "eval_steps_per_second": 11.588,
+      "step": 1000
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 5.5527777777777784e-08,
+      "loss": 1.1152,
+      "step": 2000
+    },
+    {
+      "epoch": 32.0,
+      "eval_accuracy": 0.3349301397205589,
+      "eval_loss": 1.1080944538116455,
+      "eval_runtime": 54.2029,
+      "eval_samples_per_second": 92.43,
+      "eval_steps_per_second": 11.568,
+      "step": 2000
+    },
+    {
+      "epoch": 48.0,
+      "learning_rate": 8.327777777777778e-08,
+      "loss": 1.1036,
+      "step": 3000
+    },
+    {
+      "epoch": 48.0,
+      "eval_accuracy": 0.3377245508982036,
+      "eval_loss": 1.1081210374832153,
+      "eval_runtime": 54.0467,
+      "eval_samples_per_second": 92.698,
+      "eval_steps_per_second": 11.601,
+      "step": 3000
+    },
+    {
+      "epoch": 64.0,
+      "learning_rate": 1.1105555555555557e-07,
+      "loss": 1.0895,
+      "step": 4000
+    },
+    {
+      "epoch": 64.0,
+      "eval_accuracy": 0.33912175648702597,
+      "eval_loss": 1.1072543859481812,
+      "eval_runtime": 54.1318,
+      "eval_samples_per_second": 92.552,
+      "eval_steps_per_second": 11.583,
+      "step": 4000
+    },
+    {
+      "epoch": 80.0,
+      "learning_rate": 1.3880555555555558e-07,
+      "loss": 1.0748,
+      "step": 5000
+    },
+    {
+      "epoch": 80.0,
+      "eval_accuracy": 0.3435129740518962,
+      "eval_loss": 1.1071943044662476,
+      "eval_runtime": 54.4121,
+      "eval_samples_per_second": 92.075,
+      "eval_steps_per_second": 11.523,
+      "step": 5000
+    },
+    {
+      "epoch": 96.0,
+      "learning_rate": 1.6658333333333335e-07,
+      "loss": 1.055,
+      "step": 6000
+    },
+    {
+      "epoch": 96.0,
+      "eval_accuracy": 0.3459081836327345,
+      "eval_loss": 1.1056212186813354,
+      "eval_runtime": 54.092,
+      "eval_samples_per_second": 92.62,
+      "eval_steps_per_second": 11.591,
+      "step": 6000
+    },
+    {
+      "epoch": 112.0,
+      "learning_rate": 1.9433333333333334e-07,
+      "loss": 1.0352,
+      "step": 7000
+    },
+    {
+      "epoch": 112.0,
+      "eval_accuracy": 0.3469061876247505,
+      "eval_loss": 1.1121071577072144,
+      "eval_runtime": 53.9318,
+      "eval_samples_per_second": 92.895,
+      "eval_steps_per_second": 11.626,
+      "step": 7000
+    },
+    {
+      "epoch": 128.0,
+      "learning_rate": 2.2211111111111114e-07,
+      "loss": 1.0085,
+      "step": 8000
+    },
+    {
+      "epoch": 128.0,
+      "eval_accuracy": 0.3534930139720559,
+      "eval_loss": 1.1201248168945312,
+      "eval_runtime": 54.0094,
+      "eval_samples_per_second": 92.762,
+      "eval_steps_per_second": 11.609,
+      "step": 8000
+    },
+    {
+      "epoch": 144.0,
+      "learning_rate": 2.4986111111111113e-07,
+      "loss": 0.9772,
+      "step": 9000
+    },
+    {
+      "epoch": 144.0,
+      "eval_accuracy": 0.3568862275449102,
+      "eval_loss": 1.1434961557388306,
+      "eval_runtime": 54.0639,
+      "eval_samples_per_second": 92.668,
+      "eval_steps_per_second": 11.597,
+      "step": 9000
+    },
+    {
+      "epoch": 160.0,
+      "learning_rate": 2.7761111111111115e-07,
+      "loss": 0.9323,
+      "step": 10000
+    },
+    {
+      "epoch": 160.0,
+      "eval_accuracy": 0.36087824351297404,
+      "eval_loss": 1.1742260456085205,
+      "eval_runtime": 54.7624,
+      "eval_samples_per_second": 91.486,
+      "eval_steps_per_second": 11.449,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000000,
+  "num_train_epochs": 161291,
+  "save_steps": 1000,
+  "total_flos": 2.090355130368e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c09d25f832c6c38e287ec7a7fe1b191faf603815bb3b91e32f16768a2d7d3ff
+size 4091