Training in progress, step 12000, checkpoint

checkpoint-12000/added_tokens.json

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

checkpoint-12000/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-12000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff269d1f568db720dc395c45c693b9e12c0aecd04525e6a5968d90abe0e01bc
+size 932401285

checkpoint-12000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb670aa3995df42e7f4cf8035cf6e3d5ccf8520d5ce2d46c0cb87a295a4c827
+size 466205145

checkpoint-12000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2f0d89d773f6250ebaa058e343068aea31b46d0027bcfd0a06ab93340928bf
+size 14575

checkpoint-12000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3855f2a451bac6955beddcf15cb71fa48f57d8319deeabb353281cbd62af96b5
+size 627

checkpoint-12000/special_tokens_map.json

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

checkpoint-12000/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-12000/trainer_state.json

@@ -0,0 +1,205 @@
+{
+  "best_metric": 1.0867687463760376,
+  "best_model_checkpoint": "/kaggle/output/checkpoint-12000",
+  "epoch": 0.48891786179921776,
+  "eval_steps": 1000,
+  "global_step": 12000,
+  "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
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9436111111111112e-07,
+      "loss": 1.1127,
+      "step": 7000
+    },
+    {
+      "epoch": 0.29,
+      "eval_accuracy": 0.35768463073852297,
+      "eval_loss": 1.094804048538208,
+      "eval_runtime": 50.8322,
+      "eval_samples_per_second": 98.56,
+      "eval_steps_per_second": 12.335,
+      "step": 7000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.2213888888888891e-07,
+      "loss": 1.1095,
+      "step": 8000
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.36407185628742517,
+      "eval_loss": 1.0937609672546387,
+      "eval_runtime": 50.8609,
+      "eval_samples_per_second": 98.504,
+      "eval_steps_per_second": 12.328,
+      "step": 8000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.499166666666667e-07,
+      "loss": 1.1074,
+      "step": 9000
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.34770459081836325,
+      "eval_loss": 1.1025313138961792,
+      "eval_runtime": 50.8052,
+      "eval_samples_per_second": 98.612,
+      "eval_steps_per_second": 12.341,
+      "step": 9000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.776666666666667e-07,
+      "loss": 1.1065,
+      "step": 10000
+    },
+    {
+      "epoch": 0.41,
+      "eval_accuracy": 0.38163672654690617,
+      "eval_loss": 1.0920748710632324,
+      "eval_runtime": 50.8964,
+      "eval_samples_per_second": 98.435,
+      "eval_steps_per_second": 12.319,
+      "step": 10000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.054444444444444e-07,
+      "loss": 1.1026,
+      "step": 11000
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.37944111776447104,
+      "eval_loss": 1.0899525880813599,
+      "eval_runtime": 50.6905,
+      "eval_samples_per_second": 98.835,
+      "eval_steps_per_second": 12.369,
+      "step": 11000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.3319444444444444e-07,
+      "loss": 1.1016,
+      "step": 12000
+    },
+    {
+      "epoch": 0.49,
+      "eval_accuracy": 0.4,
+      "eval_loss": 1.0867687463760376,
+      "eval_runtime": 50.8282,
+      "eval_samples_per_second": 98.567,
+      "eval_steps_per_second": 12.336,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000000,
+  "num_train_epochs": 408,
+  "save_steps": 1000,
+  "total_flos": 2.5084261564416e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba6621b829e7b7a24837f1c8da621351c891fe426b370399b04766c22090faa
+size 4091