Upload folder using huggingface_hub

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363d6bbeca0086e9c6bcf7e2a079f4caf8d97641bc08f147aaa834ef376629f9
+size 540026460

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f45b27a55b9624e4425ae8314e71c39befafa187493dc4219a753d0671d9ec7
+size 4747538

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b00f4537225976e5aed0c2334907d59b72160ff76c57cfce8b0fdc2d12479d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28197a115345acdbf6fb4fcb9672e8184f20c4dce55380cee75400109be024cf
+size 1064

trainer_state.json

@@ -0,0 +1,162 @@
+{
+  "best_global_step": 2632,
+  "best_metric": 0.4779825967353135,
+  "best_model_checkpoint": "./segment-base-freezed-results-6969/checkpoint-2632",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 2632,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8237275449101796,
+      "eval_f1": 0.3313072949886817,
+      "eval_loss": 0.5073999762535095,
+      "eval_precision": 0.5454317269076305,
+      "eval_recall": 0.34907830204633855,
+      "eval_runtime": 4.5501,
+      "eval_samples_per_second": 587.239,
+      "eval_steps_per_second": 9.231,
+      "step": 376
+    },
+    {
+      "epoch": 1.3297872340425532,
+      "grad_norm": 0.5485729575157166,
+      "learning_rate": 9.98e-05,
+      "loss": 0.5835,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8304640718562875,
+      "eval_f1": 0.39590410126027326,
+      "eval_loss": 0.482469379901886,
+      "eval_precision": 0.6605972418855854,
+      "eval_recall": 0.38597765077906376,
+      "eval_runtime": 4.5616,
+      "eval_samples_per_second": 585.765,
+      "eval_steps_per_second": 9.207,
+      "step": 752
+    },
+    {
+      "epoch": 2.6595744680851063,
+      "grad_norm": 0.6865694522857666,
+      "learning_rate": 9.727322404371585e-05,
+      "loss": 0.4701,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8383233532934131,
+      "eval_f1": 0.46028878960226666,
+      "eval_loss": 0.46620744466781616,
+      "eval_precision": 0.6894544615241363,
+      "eval_recall": 0.4443744036963646,
+      "eval_runtime": 4.561,
+      "eval_samples_per_second": 585.832,
+      "eval_steps_per_second": 9.208,
+      "step": 1128
+    },
+    {
+      "epoch": 3.9893617021276597,
+      "grad_norm": 0.7495972514152527,
+      "learning_rate": 9.454098360655738e-05,
+      "loss": 0.4695,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8409431137724551,
+      "eval_f1": 0.4762458332322515,
+      "eval_loss": 0.4532054364681244,
+      "eval_precision": 0.6477548490754955,
+      "eval_recall": 0.45254045291953454,
+      "eval_runtime": 4.555,
+      "eval_samples_per_second": 586.614,
+      "eval_steps_per_second": 9.221,
+      "step": 1504
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8390718562874252,
+      "eval_f1": 0.47448273231679866,
+      "eval_loss": 0.4566827714443207,
+      "eval_precision": 0.63084183828443,
+      "eval_recall": 0.4594250276812524,
+      "eval_runtime": 4.5703,
+      "eval_samples_per_second": 584.641,
+      "eval_steps_per_second": 9.19,
+      "step": 1880
+    },
+    {
+      "epoch": 5.319148936170213,
+      "grad_norm": 0.6681276559829712,
+      "learning_rate": 9.180874316939892e-05,
+      "loss": 0.4604,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8413173652694611,
+      "eval_f1": 0.4747950596602187,
+      "eval_loss": 0.45092836022377014,
+      "eval_precision": 0.6538129274551482,
+      "eval_recall": 0.4443024483948064,
+      "eval_runtime": 4.5601,
+      "eval_samples_per_second": 585.954,
+      "eval_steps_per_second": 9.21,
+      "step": 2256
+    },
+    {
+      "epoch": 6.648936170212766,
+      "grad_norm": 0.5326411128044128,
+      "learning_rate": 8.907650273224044e-05,
+      "loss": 0.4577,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8413173652694611,
+      "eval_f1": 0.4779825967353135,
+      "eval_loss": 0.449787437915802,
+      "eval_precision": 0.6573432134465932,
+      "eval_recall": 0.4501210955075003,
+      "eval_runtime": 4.5584,
+      "eval_samples_per_second": 586.176,
+      "eval_steps_per_second": 9.214,
+      "step": 2632
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 18800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5534590741908480.0,
+  "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 sha256:9c6fc0f1d54b8a8b397bee4217945bf85f213ad1ac8979afb217da12713f013b
+size 5368