Upload folder using huggingface_hub

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": "4.40.1",
+  "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:fbd683d15e530dc0c16b591f55855e6a3db3da2003a045ed2e81dd692f64d598
+size 437958648

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40591d8603772ed6b635fb9adbd1f63dcf96d8f0c82a12f8d64cd42ab3ebe5b
+size 876038394

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed58c02079d59372ef018baa63cef6c48c254448ac11eeaad1558799ae01087a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7adb6fea2e82693e2d5603b9409e6de30b5b25e21cd1ff4f31766800646500d
+size 1064

trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": 1.0906689167022705,
+  "best_model_checkpoint": "./results/checkpoint-2699",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 10796,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.6147003173828125,
+      "learning_rate": 4.672437244961049e-05,
+      "loss": 0.327,
+      "step": 2699
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7347354138398915,
+      "eval_conf_mat": [
+        [
+          6123,
+          717
+        ],
+        [
+          2802,
+          3624
+        ]
+      ],
+      "eval_f1": 0.673168013374199,
+      "eval_loss": 1.0906689167022705,
+      "eval_precision": 0.8348306841741534,
+      "eval_recall": 0.5639589169000934,
+      "eval_runtime": 50.9369,
+      "eval_samples_per_second": 260.44,
+      "eval_steps_per_second": 8.147,
+      "step": 2699
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.085843563079834,
+      "learning_rate": 4.338691727463831e-05,
+      "loss": 0.14,
+      "step": 5398
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7100105532941354,
+      "eval_conf_mat": [
+        [
+          6405,
+          435
+        ],
+        [
+          3412,
+          3014
+        ]
+      ],
+      "eval_f1": 0.6104303797468354,
+      "eval_loss": 1.5652275085449219,
+      "eval_precision": 0.8738764859379531,
+      "eval_recall": 0.46903205726735137,
+      "eval_runtime": 51.0274,
+      "eval_samples_per_second": 259.978,
+      "eval_steps_per_second": 8.133,
+      "step": 5398
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.21763277053833,
+      "learning_rate": 4.004946209966614e-05,
+      "loss": 0.0959,
+      "step": 8097
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7397105382180009,
+      "eval_conf_mat": [
+        [
+          6322,
+          518
+        ],
+        [
+          2935,
+          3491
+        ]
+      ],
+      "eval_f1": 0.6690943938667945,
+      "eval_loss": 1.292863130569458,
+      "eval_precision": 0.8707907208780244,
+      "eval_recall": 0.5432617491441021,
+      "eval_runtime": 49.9344,
+      "eval_samples_per_second": 265.669,
+      "eval_steps_per_second": 8.311,
+      "step": 8097
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 18.75651741027832,
+      "learning_rate": 3.6712006924693956e-05,
+      "loss": 0.0676,
+      "step": 10796
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7308156188753203,
+      "eval_conf_mat": [
+        [
+          6358,
+          482
+        ],
+        [
+          3089,
+          3337
+        ]
+      ],
+      "eval_f1": 0.6514397266959493,
+      "eval_loss": 1.5299923419952393,
+      "eval_precision": 0.8737889499869076,
+      "eval_recall": 0.5192966075319017,
+      "eval_runtime": 51.18,
+      "eval_samples_per_second": 259.203,
+      "eval_steps_per_second": 8.109,
+      "step": 10796
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 40485,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 4.192333290845046e+16,
+  "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:a9c55328111b05093836a24dc0c88ac2fe08c8d2c0021b421da4c9c9e7333eba
+size 4920