Initial model upload

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": "4.27.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a33c26d7040bf2acc1b529b44ae64c63c22f2fcdad871053abafd4f1018ed0
+size 875982277

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd03f5e24d474d459a6d2164ca0536f56cbd1feae13422db3c13c87dbda2a5ca
+size 438005109

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6005d0b43f6886d0e79ddefeaa5e3a123b6145495050bdab8de20f32abc5c313
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:774d04b2dcf03201bd2602a1cb915e72a7872edbe0cd966a84361a859043a1a3
+size 627

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 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4916,
+      "step": 12
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9361702127659575,
+      "eval_f1": 0.9362281082645824,
+      "eval_loss": 0.2990593910217285,
+      "eval_precision": 0.9371338267036695,
+      "eval_recall": 0.9361702127659575,
+      "eval_runtime": 20.3046,
+      "eval_samples_per_second": 2.315,
+      "eval_steps_per_second": 0.148,
+      "step": 12
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.2834,
+      "step": 24
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9574468085106383,
+      "eval_f1": 0.957485353068147,
+      "eval_loss": 0.1967730075120926,
+      "eval_precision": 0.9609929078014184,
+      "eval_recall": 0.9574468085106383,
+      "eval_runtime": 21.6345,
+      "eval_samples_per_second": 2.172,
+      "eval_steps_per_second": 0.139,
+      "step": 24
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.185,
+      "step": 36
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9574468085106383,
+      "eval_f1": 0.957485353068147,
+      "eval_loss": 0.15521566569805145,
+      "eval_precision": 0.9609929078014184,
+      "eval_recall": 0.9574468085106383,
+      "eval_runtime": 19.4305,
+      "eval_samples_per_second": 2.419,
+      "eval_steps_per_second": 0.154,
+      "step": 36
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1162,
+      "step": 48
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9787234042553191,
+      "eval_f1": 0.9787427027548607,
+      "eval_loss": 0.09382404386997223,
+      "eval_precision": 0.9796484736355227,
+      "eval_recall": 0.9787234042553191,
+      "eval_runtime": 20.1514,
+      "eval_samples_per_second": 2.332,
+      "eval_steps_per_second": 0.149,
+      "step": 48
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.0842,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9787234042553191,
+      "eval_f1": 0.9787427027548607,
+      "eval_loss": 0.09307459741830826,
+      "eval_precision": 0.9796484736355227,
+      "eval_recall": 0.9787234042553191,
+      "eval_runtime": 22.1003,
+      "eval_samples_per_second": 2.127,
+      "eval_steps_per_second": 0.136,
+      "step": 60
+    }
+  ],
+  "max_steps": 60,
+  "num_train_epochs": 5,
+  "total_flos": 60515542732800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545641e34bac4bf92d5455de55c9c35c3eba533194ef158ed108a3427c6305ab
+size 3515