Upload 11 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": "4.26.1",
+  "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 sha256:8746c9543cfef9df5c8294a65b4ab12a92da1552a49990e3c58183577ac4126e
+size 875988101

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c30a38dd30989be8da164cb4bb3cef3602aa1bbb8d71c59bd31e32bdcf5eb5
+size 438007925

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a95a5e29b9cdc77a2af2f39782b827948d58b741c518a1fe679949ebb3fb8a59
+size 15597

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466f0b6297493eed05f2d1ce63809b3d054e71f229177cc77584e4462fd9dace
+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 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "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 +1,115 @@
+{
+  "best_metric": 0.9523385300668151,
+  "best_model_checkpoint": "finetune-bert-SST2\\checkpoint-948",
+  "epoch": 5.0,
+  "global_step": 4740,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.4725738396624474e-05,
+      "loss": 0.2416,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9523385300668151,
+      "eval_loss": 0.14288583397865295,
+      "eval_runtime": 14.2127,
+      "eval_samples_per_second": 473.874,
+      "eval_steps_per_second": 7.458,
+      "step": 948
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.945147679324895e-05,
+      "loss": 0.166,
+      "step": 1000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.4177215189873416e-05,
+      "loss": 0.1049,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9515961395694135,
+      "eval_loss": 0.15094411373138428,
+      "eval_runtime": 13.8669,
+      "eval_samples_per_second": 485.687,
+      "eval_steps_per_second": 7.644,
+      "step": 1896
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 2.8902953586497894e-05,
+      "loss": 0.0921,
+      "step": 2000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.3628691983122365e-05,
+      "loss": 0.0597,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9518930957683742,
+      "eval_loss": 0.16512708365917206,
+      "eval_runtime": 14.319,
+      "eval_samples_per_second": 470.355,
+      "eval_steps_per_second": 7.403,
+      "step": 2844
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 1.8354430379746836e-05,
+      "loss": 0.053,
+      "step": 3000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 1.308016877637131e-05,
+      "loss": 0.036,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9515961395694135,
+      "eval_loss": 0.21384631097316742,
+      "eval_runtime": 10.989,
+      "eval_samples_per_second": 612.887,
+      "eval_steps_per_second": 9.646,
+      "step": 3792
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 7.805907172995782e-06,
+      "loss": 0.0292,
+      "step": 4000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.531645569620253e-06,
+      "loss": 0.0209,
+      "step": 4500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9505567928730512,
+      "eval_loss": 0.25926005840301514,
+      "eval_runtime": 11.1465,
+      "eval_samples_per_second": 604.227,
+      "eval_steps_per_second": 9.51,
+      "step": 4740
+    }
+  ],
+  "max_steps": 4740,
+  "num_train_epochs": 5,
+  "total_flos": 6931566197923680.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f1ad591a7c9c6d1a0026ed9c9da3e958f04536bce6138f3e945a55414711df
+size 3451