Training in progress, epoch 3, checkpoint

checkpoint-73632/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "mnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-73632/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0637825d3efd39494f11d039b74cdee5625a759529af9fadd638227e425b7f
+size 437961724

checkpoint-73632/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1daf386edcad3a34923e6ada5d531d5e5ee8fc7e67bbba9167afd826dbf3be
+size 876044538

checkpoint-73632/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4063f9ea52e754a278439b45604de97ed19e7fc45a0ebcc0becb4ee0703a6cb0
+size 14244

checkpoint-73632/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc56cbb84b16ae0b44da6ee8db0d768c132fffdf1826a148d6a887d53335443
+size 1064

checkpoint-73632/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-73632/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-73632/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 73632,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.612536430358887,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.5193,
+      "step": 24544
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8372898624554254,
+      "eval_loss": 0.4270987808704376,
+      "eval_runtime": 41.8372,
+      "eval_samples_per_second": 234.6,
+      "eval_steps_per_second": 29.328,
+      "step": 24544
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.1507811546325684,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3333,
+      "step": 49088
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8451349974528782,
+      "eval_loss": 0.4371325969696045,
+      "eval_runtime": 41.4112,
+      "eval_samples_per_second": 237.013,
+      "eval_steps_per_second": 29.63,
+      "step": 49088
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 17.64081573486328,
+      "learning_rate": 0.0,
+      "loss": 0.2214,
+      "step": 73632
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8468670402445236,
+      "eval_loss": 0.5565051436424255,
+      "eval_runtime": 41.8267,
+      "eval_samples_per_second": 234.659,
+      "eval_steps_per_second": 29.335,
+      "step": 73632
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 73632,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.099754961058632e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-73632/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64046cfe45f94e7177bdf1fa956b5224d6152e240eefb77af674388d4af9a0f
+size 5240