Training in progress, step 6000, checkpoint

checkpoint-6000/added_tokens.json

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

checkpoint-6000/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": 16,
+  "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-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff4fab4d9dd1161f3b64c0ab036e90ddfa1080208f8c6021689f656649d042a
+size 932401285

checkpoint-6000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7cda9bf9677967b12324dfac6211dbe8fdc0a879a3d2d12ae149df156e99ac
+size 466205145

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3cd6d5e22fd6820ed58d6c8b6ce1a7d475d524a1e0ac937775bfa040d8a99a
+size 14575

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5d0e092326b68c93d107e97309f81fdbf3390896c4552134de66006dcbc183
+size 627

checkpoint-6000/special_tokens_map.json

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

checkpoint-6000/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-6000/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 1.0975825786590576,
+  "best_model_checkpoint": "/kaggle/output/checkpoint-6000",
+  "epoch": 0.24445893089960888,
+  "eval_steps": 1000,
+  "global_step": 6000,
+  "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": 1.0722,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.7750000000000004e-08,
+      "loss": 1.1407,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.32914171656686625,
+      "eval_loss": 1.1048731803894043,
+      "eval_runtime": 57.3781,
+      "eval_samples_per_second": 87.316,
+      "eval_steps_per_second": 10.928,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.5527777777777784e-08,
+      "loss": 1.1253,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.3377245508982036,
+      "eval_loss": 1.1033366918563843,
+      "eval_runtime": 57.3237,
+      "eval_samples_per_second": 87.398,
+      "eval_steps_per_second": 10.938,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.327777777777778e-08,
+      "loss": 1.1179,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.3502994011976048,
+      "eval_loss": 1.104222059249878,
+      "eval_runtime": 57.4527,
+      "eval_samples_per_second": 87.202,
+      "eval_steps_per_second": 10.913,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1105555555555557e-07,
+      "loss": 1.1197,
+      "step": 4000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.3457085828343313,
+      "eval_loss": 1.1000728607177734,
+      "eval_runtime": 57.5257,
+      "eval_samples_per_second": 87.091,
+      "eval_steps_per_second": 10.899,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.3883333333333335e-07,
+      "loss": 1.1202,
+      "step": 5000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.3383233532934132,
+      "eval_loss": 1.099381923675537,
+      "eval_runtime": 57.825,
+      "eval_samples_per_second": 86.641,
+      "eval_steps_per_second": 10.843,
+      "step": 5000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.6661111111111112e-07,
+      "loss": 1.1166,
+      "step": 6000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.35409181636726544,
+      "eval_loss": 1.0975825786590576,
+      "eval_runtime": 57.6509,
+      "eval_samples_per_second": 86.902,
+      "eval_steps_per_second": 10.876,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000000,
+  "num_train_epochs": 408,
+  "save_steps": 1000,
+  "total_flos": 1.2542130782208e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8af4e8c39ae573c6926360f2e6c7a6b3b1c14fa26faafd45dd19e679cb946fd
+size 4091