Training in progress, step 14000, checkpoint

checkpoint-14000/added_tokens.json

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

checkpoint-14000/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": 24,
+  "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-14000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59085c5df85781a03ba63b6f0f64794385b1b6f2ce9c3ceb399bd795686de607
+size 932401285

checkpoint-14000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5f49b65e57465cff58f804e0e37865c018c3540fa60b2367e0e7d9569fd6df
+size 466205145

checkpoint-14000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd88aaa66dca63add58c3614981c25f1ae57810a048fd40556d05020d4cb7b6
+size 14575

checkpoint-14000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e585d6a881eae4c3726131f95c3298d054b4b464b1273a56df4e1d8d9bdc6d4b
+size 627

checkpoint-14000/special_tokens_map.json

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

checkpoint-14000/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-14000/trainer_state.json

@@ -0,0 +1,235 @@
+{
+  "best_metric": 1.0888582468032837,
+  "best_model_checkpoint": "/kaggle/output/checkpoint-12000",
+  "epoch": 0.5704041720990873,
+  "eval_steps": 1000,
+  "global_step": 14000,
+  "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": 1.1506,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.7750000000000004e-08,
+      "loss": 1.1326,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.3331337325349301,
+      "eval_loss": 1.1057127714157104,
+      "eval_runtime": 61.3538,
+      "eval_samples_per_second": 81.657,
+      "eval_steps_per_second": 10.219,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.5527777777777784e-08,
+      "loss": 1.1238,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.33812375249501,
+      "eval_loss": 1.1044437885284424,
+      "eval_runtime": 61.256,
+      "eval_samples_per_second": 81.788,
+      "eval_steps_per_second": 10.236,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.327777777777778e-08,
+      "loss": 1.1251,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.3407185628742515,
+      "eval_loss": 1.1043975353240967,
+      "eval_runtime": 61.2433,
+      "eval_samples_per_second": 81.805,
+      "eval_steps_per_second": 10.238,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1105555555555557e-07,
+      "loss": 1.1205,
+      "step": 4000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.3387225548902196,
+      "eval_loss": 1.100860357284546,
+      "eval_runtime": 61.4457,
+      "eval_samples_per_second": 81.535,
+      "eval_steps_per_second": 10.204,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.3880555555555558e-07,
+      "loss": 1.1192,
+      "step": 5000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.34151696606786425,
+      "eval_loss": 1.1005476713180542,
+      "eval_runtime": 61.2568,
+      "eval_samples_per_second": 81.787,
+      "eval_steps_per_second": 10.236,
+      "step": 5000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.6658333333333335e-07,
+      "loss": 1.1145,
+      "step": 6000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.3508982035928144,
+      "eval_loss": 1.0979759693145752,
+      "eval_runtime": 61.2221,
+      "eval_samples_per_second": 81.833,
+      "eval_steps_per_second": 10.241,
+      "step": 6000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9433333333333334e-07,
+      "loss": 1.1164,
+      "step": 7000
+    },
+    {
+      "epoch": 0.29,
+      "eval_accuracy": 0.35508982035928144,
+      "eval_loss": 1.0955135822296143,
+      "eval_runtime": 61.255,
+      "eval_samples_per_second": 81.789,
+      "eval_steps_per_second": 10.236,
+      "step": 7000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.2211111111111114e-07,
+      "loss": 1.1091,
+      "step": 8000
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.36147704590818364,
+      "eval_loss": 1.0946425199508667,
+      "eval_runtime": 61.3011,
+      "eval_samples_per_second": 81.728,
+      "eval_steps_per_second": 10.228,
+      "step": 8000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.4986111111111113e-07,
+      "loss": 1.107,
+      "step": 9000
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.3471057884231537,
+      "eval_loss": 1.10226309299469,
+      "eval_runtime": 61.3193,
+      "eval_samples_per_second": 81.703,
+      "eval_steps_per_second": 10.225,
+      "step": 9000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.776388888888889e-07,
+      "loss": 1.1055,
+      "step": 10000
+    },
+    {
+      "epoch": 0.41,
+      "eval_accuracy": 0.3774451097804391,
+      "eval_loss": 1.0922847986221313,
+      "eval_runtime": 61.1866,
+      "eval_samples_per_second": 81.881,
+      "eval_steps_per_second": 10.247,
+      "step": 10000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.0541666666666667e-07,
+      "loss": 1.1028,
+      "step": 11000
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.37425149700598803,
+      "eval_loss": 1.0914534330368042,
+      "eval_runtime": 61.341,
+      "eval_samples_per_second": 81.675,
+      "eval_steps_per_second": 10.222,
+      "step": 11000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.3319444444444444e-07,
+      "loss": 1.1024,
+      "step": 12000
+    },
+    {
+      "epoch": 0.49,
+      "eval_accuracy": 0.3872255489021956,
+      "eval_loss": 1.0888582468032837,
+      "eval_runtime": 61.4245,
+      "eval_samples_per_second": 81.564,
+      "eval_steps_per_second": 10.208,
+      "step": 12000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.6094444444444446e-07,
+      "loss": 1.1015,
+      "step": 13000
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.3397205588822355,
+      "eval_loss": 1.096097707748413,
+      "eval_runtime": 61.3257,
+      "eval_samples_per_second": 81.695,
+      "eval_steps_per_second": 10.224,
+      "step": 13000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 3.8872222222222223e-07,
+      "loss": 1.1,
+      "step": 14000
+    },
+    {
+      "epoch": 0.57,
+      "eval_accuracy": 0.36387225548902197,
+      "eval_loss": 1.0940359830856323,
+      "eval_runtime": 61.2945,
+      "eval_samples_per_second": 81.737,
+      "eval_steps_per_second": 10.229,
+      "step": 14000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000000,
+  "num_train_epochs": 408,
+  "save_steps": 1000,
+  "total_flos": 2.9264971825152e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-14000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31537d78ddfb65ec62a3bb3689996ba9eab16c9072c351cad313c78d3b7a608
+size 4091