Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,39 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Positive",
+    "1": "Negative"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "Negative": 1,
+    "Positive": 0
+  },
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b660daa7d1637708f7e7cc00f7bac1a80d1bf7d9dfc95673032c63824283c1b
+size 437958624

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0d4b45535b5f5ea334579e040774e6c494a58cbbb382838c249169c2e8c1c7
+size 15597

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb7e7f0e32311ea4a34bdd12b1dc8ec66d46164a59b314eea8415d8682591cf
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8457a345e0d53a37b5f1ebb6db1120270f6a7f4b99a871d4acda8980a58382cc
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3026a6862398ced41e03f502f101f7ea90db137e7358354f2ae702c428eaf49c
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "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]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 782,
+  "best_metric": 1.3505207300186157,
+  "best_model_checkpoint": "./bert-imdb-cp/checkpoint-782",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 782,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.639386189258312,
+      "grad_norm": 2.8213236331939697,
+      "learning_rate": 1.7447570332480818e-05,
+      "loss": 1.383798095703125,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.3505207300186157,
+      "eval_runtime": 427.2488,
+      "eval_samples_per_second": 58.514,
+      "eval_steps_per_second": 1.83,
+      "step": 782
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3910,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6575737273320960.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3efe3b88791da124abe68a3d5201ca5d762d3f8f30b2bdebb5050a9036093793
+size 5201