Upload 12 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "vinai/phobert-base-v2",
+  "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": 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": "4.41.2",
+  "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:e4fe0b66d6f038defd7d3a394c36e342cde455ffae6687191af608af05f004a3
+size 540023384

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf24703a90a2edaa8b31f260cac590b2ff924981dcfb4c1d83cbd9547bd370a8
+size 1080166586

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa741a4325efd47dbfa3e799daf8a5b1a1bc1a5cc58717ba589ac8dc35699624
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d858e6a7a5419952cfa1ddff4354cf829800013d19fee2e1eae579cbcf9908
+size 1064

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 0.4026155173778534,
+  "best_model_checkpoint": "phobert-base-v2-finetuned-cola/checkpoint-168",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7915254237288135,
+      "eval_f1": 0.7893721715117984,
+      "eval_loss": 0.47239404916763306,
+      "eval_precision": 0.8028524325530298,
+      "eval_recall": 0.7915254237288135,
+      "eval_runtime": 1.8809,
+      "eval_samples_per_second": 941.062,
+      "eval_steps_per_second": 7.443,
+      "step": 56
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8305084745762712,
+      "eval_f1": 0.8304238301271201,
+      "eval_loss": 0.40563058853149414,
+      "eval_precision": 0.8314630699298234,
+      "eval_recall": 0.8305084745762712,
+      "eval_runtime": 1.9014,
+      "eval_samples_per_second": 930.917,
+      "eval_steps_per_second": 7.363,
+      "step": 112
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8468926553672317,
+      "eval_f1": 0.8468474301103891,
+      "eval_loss": 0.4026155173778534,
+      "eval_precision": 0.8471404512621079,
+      "eval_recall": 0.8468926553672317,
+      "eval_runtime": 1.8754,
+      "eval_samples_per_second": 943.782,
+      "eval_steps_per_second": 7.465,
+      "step": 168
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.848587570621469,
+      "eval_f1": 0.8485736509993659,
+      "eval_loss": 0.40611279010772705,
+      "eval_precision": 0.8488718847691179,
+      "eval_recall": 0.848587570621469,
+      "eval_runtime": 1.8854,
+      "eval_samples_per_second": 938.79,
+      "eval_steps_per_second": 7.425,
+      "step": 224
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8564971751412429,
+      "eval_f1": 0.8564870964602922,
+      "eval_loss": 0.40367403626441956,
+      "eval_precision": 0.8565317097754656,
+      "eval_recall": 0.8564971751412429,
+      "eval_runtime": 1.8903,
+      "eval_samples_per_second": 936.352,
+      "eval_steps_per_second": 7.406,
+      "step": 280
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8508474576271187,
+      "eval_f1": 0.8507729476716981,
+      "eval_loss": 0.4181285500526428,
+      "eval_precision": 0.8513274224982177,
+      "eval_recall": 0.8508474576271187,
+      "eval_runtime": 1.8867,
+      "eval_samples_per_second": 938.139,
+      "eval_steps_per_second": 7.42,
+      "step": 336
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8502824858757062,
+      "eval_f1": 0.8502669536796478,
+      "eval_loss": 0.4214802384376526,
+      "eval_precision": 0.8505908206321785,
+      "eval_recall": 0.8502824858757062,
+      "eval_runtime": 1.9061,
+      "eval_samples_per_second": 928.618,
+      "eval_steps_per_second": 7.345,
+      "step": 392
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8536723163841808,
+      "eval_f1": 0.8536290937217372,
+      "eval_loss": 0.42303475737571716,
+      "eval_precision": 0.8539268289850389,
+      "eval_recall": 0.8536723163841808,
+      "eval_runtime": 1.8896,
+      "eval_samples_per_second": 936.69,
+      "eval_steps_per_second": 7.409,
+      "step": 448
+    },
+    {
+      "epoch": 8.928571428571429,
+      "grad_norm": 3.3562204837799072,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.3421,
+      "step": 500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8531073446327684,
+      "eval_f1": 0.8530482335798589,
+      "eval_loss": 0.42434096336364746,
+      "eval_precision": 0.8534799563816656,
+      "eval_recall": 0.8531073446327684,
+      "eval_runtime": 1.8787,
+      "eval_samples_per_second": 942.117,
+      "eval_steps_per_second": 7.452,
+      "step": 504
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8531073446327684,
+      "eval_f1": 0.8530902740380235,
+      "eval_loss": 0.42681607604026794,
+      "eval_precision": 0.8531799918482982,
+      "eval_recall": 0.8531073446327684,
+      "eval_runtime": 1.8871,
+      "eval_samples_per_second": 937.958,
+      "eval_steps_per_second": 7.419,
+      "step": 560
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 995766400116240.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e364e43838ae9aa9c6aee005033b08d7ce8771874b8cdb8dc2757d426569776
+size 5176