Training in progress, step 20000, checkpoint

checkpoint-20000/added_tokens.json

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

checkpoint-20000/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-20000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73727d261aa0c5e77116029d41ebc410bba89673eb81b9cc451b0cc842016562
+size 932401285

checkpoint-20000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c64cf454a44f6887bd8e70f2a40c9a76862c046a50dc0b12c53905ea3f85f1d
+size 466205145

checkpoint-20000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08dccc0116db77c546d825511dcb56908e20301cb9734fa57260de300e02793
+size 14575

checkpoint-20000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3fb64c5c6a638fa9b64300fa7463debf5aa998ec06747bbe9ddd60f5c49e1ea
+size 627

checkpoint-20000/special_tokens_map.json

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

checkpoint-20000/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-20000/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": 9.993309020996094,
+  "best_model_checkpoint": "/kaggle/output/checkpoint-20000",
+  "epoch": 320.0,
+  "eval_steps": 20000,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6666666666666663e-10,
+      "loss": 1.051,
+      "step": 1
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 1.665e-07,
+      "loss": 1.1135,
+      "step": 1000
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 3.3316666666666664e-07,
+      "loss": 1.0858,
+      "step": 2000
+    },
+    {
+      "epoch": 48.0,
+      "learning_rate": 4.996666666666667e-07,
+      "loss": 1.0483,
+      "step": 3000
+    },
+    {
+      "epoch": 64.0,
+      "learning_rate": 6.661666666666666e-07,
+      "loss": 0.9837,
+      "step": 4000
+    },
+    {
+      "epoch": 80.0,
+      "learning_rate": 8.326666666666666e-07,
+      "loss": 0.874,
+      "step": 5000
+    },
+    {
+      "epoch": 96.0,
+      "learning_rate": 9.993333333333333e-07,
+      "loss": 0.7317,
+      "step": 6000
+    },
+    {
+      "epoch": 112.0,
+      "learning_rate": 1.1656666666666667e-06,
+      "loss": 0.5665,
+      "step": 7000
+    },
+    {
+      "epoch": 128.0,
+      "learning_rate": 1.3323333333333331e-06,
+      "loss": 0.424,
+      "step": 8000
+    },
+    {
+      "epoch": 144.0,
+      "learning_rate": 1.4989999999999998e-06,
+      "loss": 0.2762,
+      "step": 9000
+    },
+    {
+      "epoch": 160.0,
+      "learning_rate": 1.6653333333333332e-06,
+      "loss": 0.1968,
+      "step": 10000
+    },
+    {
+      "epoch": 176.0,
+      "learning_rate": 1.8319999999999998e-06,
+      "loss": 0.1287,
+      "step": 11000
+    },
+    {
+      "epoch": 192.0,
+      "learning_rate": 1.9984999999999996e-06,
+      "loss": 0.0919,
+      "step": 12000
+    },
+    {
+      "epoch": 208.0,
+      "learning_rate": 2.1651666666666666e-06,
+      "loss": 0.0714,
+      "step": 13000
+    },
+    {
+      "epoch": 224.0,
+      "learning_rate": 2.3314999999999996e-06,
+      "loss": 0.0603,
+      "step": 14000
+    },
+    {
+      "epoch": 240.0,
+      "learning_rate": 2.4981666666666662e-06,
+      "loss": 0.0427,
+      "step": 15000
+    },
+    {
+      "epoch": 256.0,
+      "learning_rate": 2.6646666666666663e-06,
+      "loss": 0.0515,
+      "step": 16000
+    },
+    {
+      "epoch": 272.0,
+      "learning_rate": 2.831333333333333e-06,
+      "loss": 0.0469,
+      "step": 17000
+    },
+    {
+      "epoch": 288.0,
+      "learning_rate": 2.9979999999999995e-06,
+      "loss": 0.0374,
+      "step": 18000
+    },
+    {
+      "epoch": 304.0,
+      "learning_rate": 3.1644999999999995e-06,
+      "loss": 0.0467,
+      "step": 19000
+    },
+    {
+      "epoch": 320.0,
+      "learning_rate": 3.3311666666666666e-06,
+      "loss": 0.0405,
+      "step": 20000
+    },
+    {
+      "epoch": 320.0,
+      "eval_accuracy": 0.3499001996007984,
+      "eval_loss": 9.993309020996094,
+      "eval_runtime": 54.6324,
+      "eval_samples_per_second": 91.704,
+      "eval_steps_per_second": 11.477,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000000,
+  "num_train_epochs": 161291,
+  "save_steps": 20000,
+  "total_flos": 4.180710260736e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82fdb43e809880da00721d5dbd81c475c941631afb94f60b76adf6240fa8a52c
+size 4027