Training in progress, epoch 3, checkpoint

checkpoint-12630/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "sst2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 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-12630/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38eb4c788530aa655276d0d962ad919853c14a8a3a960b334be0be5a8683e4e0
+size 437958648

checkpoint-12630/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3710af4f4464d1d98bd4ea5abc178015558427f547810778d6ed8dc924fa7e
+size 876038394

checkpoint-12630/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3cf4272f16e918dbaf3fa79f488f2545519e485367c20bee308d4db56782da
+size 14244

checkpoint-12630/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6000c1c54db0ffa05ab89e68002dd7cbf61eede2fffd13cb24b972c1d2fe1b05
+size 1064

checkpoint-12630/special_tokens_map.json

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

checkpoint-12630/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-12630/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 12630,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.1736228466033936,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.221,
+      "step": 4210
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9254587155963303,
+      "eval_loss": 0.24894081056118011,
+      "eval_runtime": 4.0813,
+      "eval_samples_per_second": 213.657,
+      "eval_steps_per_second": 26.707,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 43.896240234375,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1201,
+      "step": 8420
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.29328054189682007,
+      "eval_runtime": 4.1012,
+      "eval_samples_per_second": 212.62,
+      "eval_steps_per_second": 26.578,
+      "step": 8420
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.12351109832525253,
+      "learning_rate": 0.0,
+      "loss": 0.0746,
+      "step": 12630
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.926605504587156,
+      "eval_loss": 0.31984743475914,
+      "eval_runtime": 4.3274,
+      "eval_samples_per_second": 201.505,
+      "eval_steps_per_second": 25.188,
+      "step": 12630
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12630,
+  "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": 5.316079940232192e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12630/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2c002a2c5947e6fb3d0fbd75b6ee10366079e276ba3005eb7b4bfddcf31fd5
+size 5176