Upload 10 files

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ca0161ff280c9ce95474508e88abe175fa07b0fba3ce452bf4a25af0e4cde4
+size 437958648

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb7c69fda590bdeb20519d7acccb80dcf6f360cb130adbbc6c46fc45e2e03ed
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b2a985d49ef6745e2d1c2355a929aa37f8fa92b9d4eb0f08d80cd8e17ba3f0
+size 1064

special_tokens_map.json

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

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]"
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.2658565044403076,
+  "best_model_checkpoint": "./results/checkpoint-300",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3161751329898834,
+      "eval_runtime": 9.883,
+      "eval_samples_per_second": 121.42,
+      "eval_steps_per_second": 15.178,
+      "step": 150
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.2658565044403076,
+      "eval_runtime": 9.8592,
+      "eval_samples_per_second": 121.714,
+      "eval_steps_per_second": 15.214,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.26993614435195923,
+      "eval_runtime": 9.8656,
+      "eval_samples_per_second": 121.634,
+      "eval_steps_per_second": 15.204,
+      "step": 450
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.281,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.2938203513622284,
+      "eval_runtime": 9.8632,
+      "eval_samples_per_second": 121.664,
+      "eval_steps_per_second": 15.208,
+      "step": 600
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.31206923723220825,
+      "eval_runtime": 9.8546,
+      "eval_samples_per_second": 121.771,
+      "eval_steps_per_second": 15.221,
+      "step": 750
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 6314665328640000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a87edd683644fbe7da20f14c9b992b61675c036117b248f04e2e6fd803c204
+size 4664