Upload 11 files

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "vinai/bartpho-syllable",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "tokenizer_class": "BartphoTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 40030
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2764db94734dd5047142ce5c3be06ab4e7ea1ac88111ac79eb60096da46cb1dd
+size 1583480280

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e4e19f123300dab2338c83cf138c1d32fc6a037b376cf975ee0f446f1c38e7
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c217cde7544d321309999c61b6444065c558b71fbb0af7453fabff6d944be852
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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
+    },
+    "40029": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "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>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BartphoTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,227 @@
+{
+  "best_metric": 0.11493609100580215,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-11812",
+  "epoch": 8.999619047619047,
+  "eval_steps": 500,
+  "global_step": 11812,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.9151228666305542,
+      "learning_rate": 9.240091463414634e-06,
+      "loss": 0.5245,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9996190476190476,
+      "eval_avg_time_per_word": 0.2856894375340317,
+      "eval_bleu": 0.3241854207405991,
+      "eval_cer": 0.6666666865348816,
+      "eval_loss": 0.20001943409442902,
+      "eval_runtime": 241.8615,
+      "eval_sacrebleu": 32.41854207405989,
+      "eval_samples_per_second": 28.942,
+      "eval_steps_per_second": 0.604,
+      "eval_wer": 0.6888888888888889,
+      "step": 1312
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 2.0819993019104004,
+      "learning_rate": 8.478658536585368e-06,
+      "loss": 0.2796,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_avg_time_per_word": 0.2867684533090989,
+      "eval_bleu": 0.33444843598328117,
+      "eval_cer": 0.6666666865348816,
+      "eval_loss": 0.15544836223125458,
+      "eval_runtime": 242.1808,
+      "eval_sacrebleu": 33.44484359832811,
+      "eval_samples_per_second": 28.904,
+      "eval_steps_per_second": 0.603,
+      "eval_wer": 0.6888888888888889,
+      "step": 2625
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 1.885176181793213,
+      "learning_rate": 7.716463414634146e-06,
+      "loss": 0.2149,
+      "step": 3000
+    },
+    {
+      "epoch": 2.9996190476190474,
+      "eval_avg_time_per_word": 0.2856631360126506,
+      "eval_bleu": 0.3407651434588302,
+      "eval_cer": 0.6666666865348816,
+      "eval_loss": 0.13238175213336945,
+      "eval_runtime": 243.4299,
+      "eval_sacrebleu": 34.076514345883034,
+      "eval_samples_per_second": 28.756,
+      "eval_steps_per_second": 0.6,
+      "eval_wer": 0.6888888888888889,
+      "step": 3937
+    },
+    {
+      "epoch": 3.0476190476190474,
+      "grad_norm": 1.629309892654419,
+      "learning_rate": 6.954268292682927e-06,
+      "loss": 0.1782,
+      "step": 4000
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 1.4296305179595947,
+      "learning_rate": 6.192073170731708e-06,
+      "loss": 0.1498,
+      "step": 5000
+    },
+    {
+      "epoch": 4.0,
+      "eval_avg_time_per_word": 0.28190079163009985,
+      "eval_bleu": 0.342484737426721,
+      "eval_cer": 0.6666666865348816,
+      "eval_loss": 0.12768897414207458,
+      "eval_runtime": 240.7041,
+      "eval_sacrebleu": 34.248473742672104,
+      "eval_samples_per_second": 29.081,
+      "eval_steps_per_second": 0.607,
+      "eval_wer": 0.6888888888888889,
+      "step": 5250
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 1.3963040113449097,
+      "learning_rate": 5.429878048780488e-06,
+      "loss": 0.1318,
+      "step": 6000
+    },
+    {
+      "epoch": 4.999619047619047,
+      "eval_avg_time_per_word": 0.2839514807375623,
+      "eval_bleu": 0.3428596484328475,
+      "eval_cer": 0.6666666865348816,
+      "eval_loss": 0.12459039688110352,
+      "eval_runtime": 243.3533,
+      "eval_sacrebleu": 34.28596484328476,
+      "eval_samples_per_second": 28.765,
+      "eval_steps_per_second": 0.6,
+      "eval_wer": 0.6888888888888889,
+      "step": 6562
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 1.245492935180664,
+      "learning_rate": 4.667682926829269e-06,
+      "loss": 0.1188,
+      "step": 7000
+    },
+    {
+      "epoch": 6.0,
+      "eval_avg_time_per_word": 0.2730801561768131,
+      "eval_bleu": 0.3446570827661078,
+      "eval_cer": 0.6666666865348816,
+      "eval_loss": 0.11544822156429291,
+      "eval_runtime": 241.1081,
+      "eval_sacrebleu": 34.46570827661079,
+      "eval_samples_per_second": 29.033,
+      "eval_steps_per_second": 0.606,
+      "eval_wer": 0.6888888888888889,
+      "step": 7875
+    },
+    {
+      "epoch": 6.095238095238095,
+      "grad_norm": 1.6760395765304565,
+      "learning_rate": 3.90625e-06,
+      "loss": 0.109,
+      "step": 8000
+    },
+    {
+      "epoch": 6.857142857142857,
+      "grad_norm": 1.5629112720489502,
+      "learning_rate": 3.1440548780487807e-06,
+      "loss": 0.0996,
+      "step": 9000
+    },
+    {
+      "epoch": 6.999619047619047,
+      "eval_avg_time_per_word": 0.2809329230335656,
+      "eval_bleu": 0.34531231334616685,
+      "eval_cer": 0.6666666865348816,
+      "eval_loss": 0.11558092385530472,
+      "eval_runtime": 240.4449,
+      "eval_sacrebleu": 34.5312313346167,
+      "eval_samples_per_second": 29.113,
+      "eval_steps_per_second": 0.607,
+      "eval_wer": 0.6888888888888889,
+      "step": 9187
+    },
+    {
+      "epoch": 7.619047619047619,
+      "grad_norm": 1.3507906198501587,
+      "learning_rate": 2.3818597560975614e-06,
+      "loss": 0.092,
+      "step": 10000
+    },
+    {
+      "epoch": 8.0,
+      "eval_avg_time_per_word": 0.27973620380425623,
+      "eval_bleu": 0.34567075563975486,
+      "eval_cer": 0.6666666865348816,
+      "eval_loss": 0.11671777069568634,
+      "eval_runtime": 240.0499,
+      "eval_sacrebleu": 34.56707556397547,
+      "eval_samples_per_second": 29.161,
+      "eval_steps_per_second": 0.608,
+      "eval_wer": 0.6888888888888889,
+      "step": 10500
+    },
+    {
+      "epoch": 8.380952380952381,
+      "grad_norm": 1.3803397417068481,
+      "learning_rate": 1.6196646341463414e-06,
+      "loss": 0.0873,
+      "step": 11000
+    },
+    {
+      "epoch": 8.999619047619047,
+      "eval_avg_time_per_word": 0.27570831504890414,
+      "eval_bleu": 0.3461272171150006,
+      "eval_cer": 0.6666666865348816,
+      "eval_loss": 0.11493609100580215,
+      "eval_runtime": 241.1666,
+      "eval_sacrebleu": 34.61272171150005,
+      "eval_samples_per_second": 29.026,
+      "eval_steps_per_second": 0.605,
+      "eval_wer": 0.6888888888888889,
+      "step": 11812
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 13120,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0292481466328678e+17,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0aa8bf75dcc4ba5cd0daa415dc258ad2bfa2cd79a6a188f5a37cdfc835b1f0
+size 5368