Upload folder using huggingface_hub

phobert_checkpoints_seed_42/checkpoint-8877/added_tokens.json

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

phobert_checkpoints_seed_42/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_42/checkpoint-8877/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef9d80c4d44eafa235779f3d09283a5e44d5dbaf888a5c5f96ef8006af7618e
+size 540047992

phobert_checkpoints_seed_42/checkpoint-8877/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f093197518f3f7dd65ef3da2f0850831e3c4694ec47189c63342d1c4d59350e3
+size 1080219019

phobert_checkpoints_seed_42/checkpoint-8877/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b3b2ad3bfc4882d686451005260db50b2732157e98ecf0d51ed6e17d4309fe
+size 14645

phobert_checkpoints_seed_42/checkpoint-8877/scheduler.pt

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

phobert_checkpoints_seed_42/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_42/checkpoint-8877/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_global_step": 8877,
+  "best_metric": 0.9432359719723061,
+  "best_model_checkpoint": "./phobert_checkpoints_seed_42/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": 2.262679100036621,
+      "learning_rate": 1.872420262664165e-05,
+      "loss": 1.050082763671875,
+      "step": 500
+    },
+    {
+      "epoch": 0.33795201081446435,
+      "grad_norm": 1.8289166688919067,
+      "learning_rate": 1.88830297219559e-05,
+      "loss": 0.2674019775390625,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5069280162216965,
+      "grad_norm": 1.7257850170135498,
+      "learning_rate": 1.7684563758389264e-05,
+      "loss": 0.21981884765625,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6759040216289287,
+      "grad_norm": 2.0222976207733154,
+      "learning_rate": 1.648609779482263e-05,
+      "loss": 0.20084834289550782,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8448800270361608,
+      "grad_norm": 3.0854101181030273,
+      "learning_rate": 1.5287631831255994e-05,
+      "loss": 0.19130363464355468,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.940139431710151,
+      "eval_loss": 0.1669241040945053,
+      "eval_macro_auc": 0.9973156638174301,
+      "eval_macro_f1": 0.9342672290676838,
+      "eval_macro_precision": 0.9324432720377134,
+      "eval_macro_recall": 0.9367012617803259,
+      "eval_runtime": 38.7433,
+      "eval_samples_per_second": 2443.52,
+      "eval_steps_per_second": 19.1,
+      "step": 2959
+    },
+    {
+      "epoch": 1.013856032443393,
+      "grad_norm": 2.7165932655334473,
+      "learning_rate": 1.4089165867689358e-05,
+      "loss": 0.178471435546875,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1828320378506252,
+      "grad_norm": 2.3683438301086426,
+      "learning_rate": 1.2890699904122723e-05,
+      "loss": 0.1527028045654297,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3518080432578574,
+      "grad_norm": 2.098846912384033,
+      "learning_rate": 1.1692233940556088e-05,
+      "loss": 0.1492697296142578,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5207840486650896,
+      "grad_norm": 2.6591193675994873,
+      "learning_rate": 1.0493767976989456e-05,
+      "loss": 0.14404000854492188,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6897600540723219,
+      "grad_norm": 1.5924367904663086,
+      "learning_rate": 9.29530201342282e-06,
+      "loss": 0.1441511688232422,
+      "step": 5000
+    },
+    {
+      "epoch": 1.858736059479554,
+      "grad_norm": 1.9645568132400513,
+      "learning_rate": 8.096836049856185e-06,
+      "loss": 0.1391763916015625,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9454631879159184,
+      "eval_loss": 0.15333761274814606,
+      "eval_macro_auc": 0.9977750265373656,
+      "eval_macro_f1": 0.9405771158975395,
+      "eval_macro_precision": 0.9388199242531272,
+      "eval_macro_recall": 0.9427445664830392,
+      "eval_runtime": 38.5717,
+      "eval_samples_per_second": 2454.393,
+      "eval_steps_per_second": 19.185,
+      "step": 5918
+    },
+    {
+      "epoch": 2.027712064886786,
+      "grad_norm": 2.034968137741089,
+      "learning_rate": 6.89837008628955e-06,
+      "loss": 0.13613372802734375,
+      "step": 6000
+    },
+    {
+      "epoch": 2.196688070294018,
+      "grad_norm": 2.9591848850250244,
+      "learning_rate": 5.6999041227229144e-06,
+      "loss": 0.1161927719116211,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3656640757012504,
+      "grad_norm": 1.4868425130844116,
+      "learning_rate": 4.501438159156281e-06,
+      "loss": 0.11392160034179688,
+      "step": 7000
+    },
+    {
+      "epoch": 2.5346400811084826,
+      "grad_norm": 2.0756447315216064,
+      "learning_rate": 3.3029721955896455e-06,
+      "loss": 0.11215515899658203,
+      "step": 7500
+    },
+    {
+      "epoch": 2.703616086515715,
+      "grad_norm": 2.5407309532165527,
+      "learning_rate": 2.104506232023011e-06,
+      "loss": 0.10947681427001953,
+      "step": 8000
+    },
+    {
+      "epoch": 2.872592091922947,
+      "grad_norm": 1.8933261632919312,
+      "learning_rate": 9.060402684563759e-07,
+      "loss": 0.11251821136474609,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9482835111439738,
+      "eval_loss": 0.14608971774578094,
+      "eval_macro_auc": 0.9979769555746527,
+      "eval_macro_f1": 0.9432359719723061,
+      "eval_macro_precision": 0.9419205853816861,
+      "eval_macro_recall": 0.9447251863143948,
+      "eval_runtime": 38.3733,
+      "eval_samples_per_second": 2467.082,
+      "eval_steps_per_second": 19.284,
+      "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_42/checkpoint-8877/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3ba4d159383171c71949d1c8595c042c609c877311e44c3f9de060728e6d3f
+size 5201