Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7adcc81e9ddc5e14e2165ed0a5d7e7c1e49425bc28acf532cc673c794087197
+size 498612824

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7671a6ee3d2585ec2fb8098f21f26b2bc36951d825e1c5f91e4918a4e6c8a945
+size 997345530

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40198e46221feb04b50eb80c751f2626eba39f13a83c6b03978b72f99e7b1b2
+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 +1,158 @@
+{
+  "best_metric": 0.659783124923706,
+  "best_model_checkpoint": "./results/claim_onlyroberta-base/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": 13.100720405578613,
+      "learning_rate": 4.672437244961049e-05,
+      "loss": 0.579,
+      "step": 2699
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6555103271521182,
+      "eval_conf_mat": [
+        [
+          4360,
+          2480
+        ],
+        [
+          2090,
+          4336
+        ]
+      ],
+      "eval_f1": 0.6548859688868751,
+      "eval_loss": 0.659783124923706,
+      "eval_precision": 0.636150234741784,
+      "eval_recall": 0.6747587924058512,
+      "eval_runtime": 9.813,
+      "eval_samples_per_second": 1351.875,
+      "eval_steps_per_second": 42.291,
+      "step": 2699
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.234604835510254,
+      "learning_rate": 4.338691727463831e-05,
+      "loss": 0.4956,
+      "step": 5398
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6427709935172622,
+      "eval_conf_mat": [
+        [
+          5881,
+          959
+        ],
+        [
+          3780,
+          2646
+        ]
+      ],
+      "eval_f1": 0.5275645498953245,
+      "eval_loss": 0.8142257928848267,
+      "eval_precision": 0.7339805825242719,
+      "eval_recall": 0.4117647058823529,
+      "eval_runtime": 9.7643,
+      "eval_samples_per_second": 1358.627,
+      "eval_steps_per_second": 42.502,
+      "step": 5398
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.444439888000488,
+      "learning_rate": 4.004946209966614e-05,
+      "loss": 0.4613,
+      "step": 8097
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6129202472486055,
+      "eval_conf_mat": [
+        [
+          5950,
+          890
+        ],
+        [
+          4245,
+          2181
+        ]
+      ],
+      "eval_f1": 0.45930293776982206,
+      "eval_loss": 0.7507337331771851,
+      "eval_precision": 0.7101921198306741,
+      "eval_recall": 0.33940242763772177,
+      "eval_runtime": 9.7395,
+      "eval_samples_per_second": 1362.083,
+      "eval_steps_per_second": 42.61,
+      "step": 8097
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0880028009414673,
+      "learning_rate": 3.6712006924693956e-05,
+      "loss": 0.6596,
+      "step": 10796
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5156037991858887,
+      "eval_conf_mat": [
+        [
+          6840,
+          0
+        ],
+        [
+          6426,
+          0
+        ]
+      ],
+      "eval_f1": 0.0,
+      "eval_loss": 0.6927554607391357,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 9.7891,
+      "eval_samples_per_second": 1355.186,
+      "eval_steps_per_second": 42.394,
+      "step": 10796
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 40485,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7272246195180780.0,
+  "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 sha256:00d0af0874b6482fbe688ab9c8f95d7f6c8e1bdac79f5099a0e92ca0d0abf8b6
+size 5048