Upload 12 files

added_tokens.json

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

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": "4.52.4",
+  "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:e40f48b9ebd8278bd8c2275b805dac17b2084f25f1452177eadd99aa79352001
+size 540026460

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5073c57ce48ca4c49395db32c1cdfac71cadbe107168c9d1872cb4ee61462c
+size 1080172730

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b4fc0681e01f324de66bb6b3e243a127d38f57845745be4846144609d77d98
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550b077a6ca4f3c360188d03489bb9b5005d557d0a4456cb7ad89cf4c6650f31
+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 +1,55 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_global_step": 716,
+  "best_metric": 0.20679529011249542,
+  "best_model_checkpoint": "./sentiment_model/checkpoint-716",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.934301958307012,
+      "eval_f1": 0.9310534001387455,
+      "eval_loss": 0.2211858481168747,
+      "eval_runtime": 12.4736,
+      "eval_samples_per_second": 126.908,
+      "eval_steps_per_second": 4.008,
+      "step": 358
+    },
+    {
+      "epoch": 1.3966480446927374,
+      "grad_norm": 7.75230598449707,
+      "learning_rate": 1.4424581005586593e-05,
+      "loss": 0.2821,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9418825015792799,
+      "eval_f1": 0.940750568688658,
+      "eval_loss": 0.20679529011249542,
+      "eval_runtime": 12.5058,
+      "eval_samples_per_second": 126.581,
+      "eval_steps_per_second": 3.998,
+      "step": 716
+    },
+    {
+      "epoch": 2.793296089385475,
+      "grad_norm": 3.6269500255584717,
+      "learning_rate": 8.837988826815643e-06,
+      "loss": 0.1522,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9444093493367025,
+      "eval_f1": 0.9414769686480463,
+      "eval_loss": 0.21175681054592133,
+      "eval_runtime": 12.5136,
+      "eval_samples_per_second": 126.502,
+      "eval_steps_per_second": 3.996,
+      "step": 1074
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9456727732154138,
+      "eval_f1": 0.943473191123415,
+      "eval_loss": 0.23586392402648926,
+      "eval_runtime": 12.4727,
+      "eval_samples_per_second": 126.917,
+      "eval_steps_per_second": 4.009,
+      "step": 1432
+    },
+    {
+      "epoch": 4.189944134078212,
+      "grad_norm": 6.93758487701416,
+      "learning_rate": 3.251396648044693e-06,
+      "loss": 0.1029,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9456727732154138,
+      "eval_f1": 0.9431961768989716,
+      "eval_loss": 0.2388758659362793,
+      "eval_runtime": 12.517,
+      "eval_samples_per_second": 126.468,
+      "eval_steps_per_second": 3.995,
+      "step": 1790
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1790,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7515834777400320.0,
+  "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 sha256:59200b91a0c066775ccafa5f30c8c3808e11c327c96eae4033fccd2038ffdcc8
+size 5304