Uploaded model file with tokenizer

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google-bert/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,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "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": "4.44.2",
+  "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:c9055401d5b8d7294c841dacf538f5aa81e8385e9474e4aff128577905204b42
+size 437958648

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7adebf14e1421752d45a09e1d3e3eb11e542219e9aded4319cf0eacf91165f6a
+size 876038330

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e90a2955f05b63cfd96b4d5119bfe7f4d26057f6be6c2ba7642a2f471308adb
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a349edb35b5503ce6d135f00b98c525c3a6a2d2acf3c6736b55484bebcbd2d91
+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 +1,56 @@
+{
+  "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",
+  "truncate": true,
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": 0.10429740697145462,
+  "best_model_checkpoint": "./classifier/checkpoint-40",
+  "epoch": 1.2903225806451613,
+  "eval_steps": 10,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 1.5601885318756104,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.1631,
+      "step": 10
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "eval_accuracy": 0.9565217391304348,
+      "eval_f1": 0.8979591836734694,
+      "eval_loss": 0.15750479698181152,
+      "eval_precision": 0.9705882352941176,
+      "eval_recall": 0.8354430379746836,
+      "eval_runtime": 0.9626,
+      "eval_samples_per_second": 358.397,
+      "eval_steps_per_second": 6.233,
+      "step": 10
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 3.452174663543701,
+      "learning_rate": 8.709677419354839e-05,
+      "loss": 0.0953,
+      "step": 20
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "eval_accuracy": 0.9710144927536232,
+      "eval_f1": 0.9375,
+      "eval_loss": 0.11482395976781845,
+      "eval_precision": 0.9259259259259259,
+      "eval_recall": 0.9493670886075949,
+      "eval_runtime": 0.6977,
+      "eval_samples_per_second": 494.448,
+      "eval_steps_per_second": 8.599,
+      "step": 20
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 4.141051769256592,
+      "learning_rate": 8.064516129032258e-05,
+      "loss": 0.0984,
+      "step": 30
+    },
+    {
+      "epoch": 0.967741935483871,
+      "eval_accuracy": 0.9710144927536232,
+      "eval_f1": 0.935064935064935,
+      "eval_loss": 0.11602061241865158,
+      "eval_precision": 0.96,
+      "eval_recall": 0.9113924050632911,
+      "eval_runtime": 0.8289,
+      "eval_samples_per_second": 416.231,
+      "eval_steps_per_second": 7.239,
+      "step": 30
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.5622131824493408,
+      "learning_rate": 7.419354838709677e-05,
+      "loss": 0.0316,
+      "step": 40
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "eval_accuracy": 0.9826086956521739,
+      "eval_f1": 0.9620253164556962,
+      "eval_loss": 0.10429740697145462,
+      "eval_precision": 0.9620253164556962,
+      "eval_recall": 0.9620253164556962,
+      "eval_runtime": 0.6866,
+      "eval_samples_per_second": 502.488,
+      "eval_steps_per_second": 8.739,
+      "step": 40
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 155,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 455444722939380.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ad9775fed237924f766f86149fdd411b355a421294e47ff26768509cc70154
+size 5176