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": 2,
+  "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 sha256:21e6f3421048aae073db8bbd7ee84e968374e8b512ad49a3d7e617c515e910a1
+size 932401285

checkpoint-6000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3e624d79e9d046c35e609d7ab54bc5893984ccab118a24a02137a25e98e91d
+size 466205145

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd56b12e7fcd8b22acedf845fb82ea706075a8eb7b7d20cc04b14bdfe99fcd9
+size 14575

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a266703dc9c8288151c9776a366636d9d86a921ccb8552bc88d5d11d6f8ebf
+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": 1.0983413457870483,
+  "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": 1.0788,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.7750000000000004e-08,
+      "loss": 1.2063,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.32894211576846305,
+      "eval_loss": 1.109653115272522,
+      "eval_runtime": 50.6057,
+      "eval_samples_per_second": 99.001,
+      "eval_steps_per_second": 12.39,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.5527777777777784e-08,
+      "loss": 1.1293,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.32994011976047904,
+      "eval_loss": 1.1056402921676636,
+      "eval_runtime": 50.7169,
+      "eval_samples_per_second": 98.784,
+      "eval_steps_per_second": 12.363,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.327777777777778e-08,
+      "loss": 1.1263,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.3347305389221557,
+      "eval_loss": 1.1063188314437866,
+      "eval_runtime": 50.8081,
+      "eval_samples_per_second": 98.606,
+      "eval_steps_per_second": 12.341,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1105555555555557e-07,
+      "loss": 1.1211,
+      "step": 4000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.34291417165668664,
+      "eval_loss": 1.1010773181915283,
+      "eval_runtime": 50.6469,
+      "eval_samples_per_second": 98.92,
+      "eval_steps_per_second": 12.38,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.3883333333333335e-07,
+      "loss": 1.1176,
+      "step": 5000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.3395209580838323,
+      "eval_loss": 1.099412441253662,
+      "eval_runtime": 50.7266,
+      "eval_samples_per_second": 98.765,
+      "eval_steps_per_second": 12.36,
+      "step": 5000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.6658333333333335e-07,
+      "loss": 1.1165,
+      "step": 6000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.3596806387225549,
+      "eval_loss": 1.0983413457870483,
+      "eval_runtime": 50.7493,
+      "eval_samples_per_second": 98.721,
+      "eval_steps_per_second": 12.355,
+      "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 sha256:0ba6621b829e7b7a24837f1c8da621351c891fe426b370399b04766c22090faa
+size 4091