Upload 10 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
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1a51ab7d8fb20b5ed64c04cde25e139712ed15f595722019891a6886dc37eb
+size 1080166586

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3648a170f779ef4c4a87c186a836c0e5b015f4ed55ae1d9f08eae0befde055d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23366dd2077e77e9960923dac80b1c815fe4ea3820809a8f5282b8410b251e6b
+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 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.861111111111111,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 7.35616397857666,
+      "learning_rate": 1.7222222222222224e-05,
+      "loss": 0.2334,
+      "step": 500
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 4.325047969818115,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 0.1592,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 3.574897289276123,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.1443,
+      "step": 1500
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 2.2505545616149902,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.1236,
+      "step": 2000
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 2.264756202697754,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 0.1174,
+      "step": 2500
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.6259239315986633,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1174,
+      "step": 3000
+    },
+    {
+      "epoch": 4.861111111111111,
+      "grad_norm": 0.2633063793182373,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.0999,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 763827838151040.0,
+  "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:d13f77d9a24c7759b93fdf467ffd3e011229905c93f5927c9da0625ab947b845
+size 5112