Upload folder using huggingface_hub

phobert_checkpoints_seed_202/checkpoint-8877/added_tokens.json

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

phobert_checkpoints_seed_202/checkpoint-8877/config.json

@@ -0,0 +1,55 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "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",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "tokenizer_class": "PhobertTokenizer",
+  "transformers_version": "5.13.1",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 64001
+}

phobert_checkpoints_seed_202/checkpoint-8877/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b2155866e8faa6757668b7d99d93cbbfcd56e5b81205831bb862fb6d0aaeac
+size 540047992

phobert_checkpoints_seed_202/checkpoint-8877/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18c2c17fc1af05c9e54a79a15ca73dffced6a8766b96b3e06d7716ffba579e5
+size 1080219019

phobert_checkpoints_seed_202/checkpoint-8877/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97359513ad8175cd183db7e7d3ecca8f27c84f1b470bfddf41897d364463d42
+size 14645

phobert_checkpoints_seed_202/checkpoint-8877/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3f573dbcd947b4d041ec724825ffe6251cc22b67c220b658e47f75c63acd84
+size 1465

phobert_checkpoints_seed_202/checkpoint-8877/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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
+    }
+  },
+  "backend": "custom",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

phobert_checkpoints_seed_202/checkpoint-8877/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_global_step": 8877,
+  "best_metric": 0.9439453465084873,
+  "best_model_checkpoint": "./phobert_checkpoints_seed_202/checkpoint-8877",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 8877,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16897600540723218,
+      "grad_norm": 2.073317289352417,
+      "learning_rate": 1.872420262664165e-05,
+      "loss": 1.040810302734375,
+      "step": 500
+    },
+    {
+      "epoch": 0.33795201081446435,
+      "grad_norm": 2.042790174484253,
+      "learning_rate": 1.88830297219559e-05,
+      "loss": 0.2647199401855469,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5069280162216965,
+      "grad_norm": 1.9712027311325073,
+      "learning_rate": 1.7684563758389264e-05,
+      "loss": 0.21766294860839844,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6759040216289287,
+      "grad_norm": 1.6683423519134521,
+      "learning_rate": 1.648609779482263e-05,
+      "loss": 0.1981204528808594,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8448800270361608,
+      "grad_norm": 2.5705699920654297,
+      "learning_rate": 1.5287631831255994e-05,
+      "loss": 0.18299937438964844,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9399176085349108,
+      "eval_loss": 0.16653311252593994,
+      "eval_macro_auc": 0.9973434911641442,
+      "eval_macro_f1": 0.9337037500693992,
+      "eval_macro_precision": 0.9337652084744701,
+      "eval_macro_recall": 0.9340027849838975,
+      "eval_runtime": 38.2674,
+      "eval_samples_per_second": 2473.909,
+      "eval_steps_per_second": 19.338,
+      "step": 2959
+    },
+    {
+      "epoch": 1.013856032443393,
+      "grad_norm": 2.476914167404175,
+      "learning_rate": 1.4089165867689358e-05,
+      "loss": 0.17316848754882813,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1828320378506252,
+      "grad_norm": 1.8834567070007324,
+      "learning_rate": 1.2890699904122723e-05,
+      "loss": 0.14776710510253907,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3518080432578574,
+      "grad_norm": 2.1828575134277344,
+      "learning_rate": 1.1692233940556088e-05,
+      "loss": 0.143662109375,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5207840486650896,
+      "grad_norm": 2.147624969482422,
+      "learning_rate": 1.0493767976989456e-05,
+      "loss": 0.14104629516601563,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6897600540723219,
+      "grad_norm": 1.8826537132263184,
+      "learning_rate": 9.29530201342282e-06,
+      "loss": 0.13816148376464843,
+      "step": 5000
+    },
+    {
+      "epoch": 1.858736059479554,
+      "grad_norm": 1.8232485055923462,
+      "learning_rate": 8.096836049856185e-06,
+      "loss": 0.13870445251464844,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9456427590577796,
+      "eval_loss": 0.1501767635345459,
+      "eval_macro_auc": 0.9978839315175858,
+      "eval_macro_f1": 0.9406072242238915,
+      "eval_macro_precision": 0.9393961454005693,
+      "eval_macro_recall": 0.9421283384148383,
+      "eval_runtime": 38.2691,
+      "eval_samples_per_second": 2473.799,
+      "eval_steps_per_second": 19.337,
+      "step": 5918
+    },
+    {
+      "epoch": 2.027712064886786,
+      "grad_norm": 1.925161600112915,
+      "learning_rate": 6.89837008628955e-06,
+      "loss": 0.13169293212890626,
+      "step": 6000
+    },
+    {
+      "epoch": 2.196688070294018,
+      "grad_norm": 2.5986270904541016,
+      "learning_rate": 5.6999041227229144e-06,
+      "loss": 0.11186366271972656,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3656640757012504,
+      "grad_norm": 2.3255836963653564,
+      "learning_rate": 4.501438159156281e-06,
+      "loss": 0.11105248260498046,
+      "step": 7000
+    },
+    {
+      "epoch": 2.5346400811084826,
+      "grad_norm": 1.785477638244629,
+      "learning_rate": 3.3029721955896455e-06,
+      "loss": 0.10888949584960937,
+      "step": 7500
+    },
+    {
+      "epoch": 2.703616086515715,
+      "grad_norm": 1.8736659288406372,
+      "learning_rate": 2.104506232023011e-06,
+      "loss": 0.1088877944946289,
+      "step": 8000
+    },
+    {
+      "epoch": 2.872592091922947,
+      "grad_norm": 2.713252067565918,
+      "learning_rate": 9.060402684563759e-07,
+      "loss": 0.10581453704833985,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9487482835111439,
+      "eval_loss": 0.14489392936229706,
+      "eval_macro_auc": 0.9980283202500969,
+      "eval_macro_f1": 0.9439453465084873,
+      "eval_macro_precision": 0.9426453510802947,
+      "eval_macro_recall": 0.9454110513073586,
+      "eval_runtime": 38.2865,
+      "eval_samples_per_second": 2472.673,
+      "eval_steps_per_second": 19.328,
+      "step": 8877
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8877,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.9892457450779034e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

phobert_checkpoints_seed_202/checkpoint-8877/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ec266094489576ff7cbb19ad9a7467d7b8c3025937880daa72c4b7a785c290b
+size 5201