Upload 11 files

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/kaggle/input/bart-pho-train/checkpoint-9945",
+  "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": "4.47.0",
+  "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": "4.47.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07de4c415a8e7b8406552dc96121a596a111a125307c58b8ca850d74e13dbab8
+size 1583480280

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3696f9b43770d919c4114bb562b999df6deefa0c3bba5b35a6bf0694bd260b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15bbd906ed12f13508b6efa42648aa2c492ef1ede34c9e464f4454c4437972a
+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 +1,56 @@
+{
+  "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
+    },
+    "40029": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "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>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BartphoTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.011942805722355843,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-9945",
+  "epoch": 0.9999497260067367,
+  "eval_steps": 500,
+  "global_step": 9945,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10054798652656981,
+      "grad_norm": 2.2476389408111572,
+      "learning_rate": 8.994469582704878e-06,
+      "loss": 0.0235,
+      "step": 1000
+    },
+    {
+      "epoch": 0.20109597305313962,
+      "grad_norm": 2.1006860733032227,
+      "learning_rate": 7.98994469582705e-06,
+      "loss": 0.0249,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3016439595797094,
+      "grad_norm": 1.7575879096984863,
+      "learning_rate": 6.984414278531926e-06,
+      "loss": 0.0245,
+      "step": 3000
+    },
+    {
+      "epoch": 0.40219194610627923,
+      "grad_norm": 2.2406935691833496,
+      "learning_rate": 5.979889391654098e-06,
+      "loss": 0.0245,
+      "step": 4000
+    },
+    {
+      "epoch": 0.502739932632849,
+      "grad_norm": 1.5336138010025024,
+      "learning_rate": 4.974358974358975e-06,
+      "loss": 0.0236,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6032879191594188,
+      "grad_norm": 2.5202527046203613,
+      "learning_rate": 3.968828557063851e-06,
+      "loss": 0.0231,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7038359056859886,
+      "grad_norm": 1.9651978015899658,
+      "learning_rate": 2.9632981397687283e-06,
+      "loss": 0.0229,
+      "step": 7000
+    },
+    {
+      "epoch": 0.8043838922125585,
+      "grad_norm": 1.8106822967529297,
+      "learning_rate": 1.957767722473605e-06,
+      "loss": 0.0221,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9049318787391283,
+      "grad_norm": 1.9274195432662964,
+      "learning_rate": 9.532428355957768e-07,
+      "loss": 0.0221,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9999497260067367,
+      "eval_loss": 0.011942805722355843,
+      "eval_processing_time_ms": 148038.60187530518,
+      "eval_runtime": 2020.6048,
+      "eval_sacrebleu": 35.57162442858833,
+      "eval_samples_per_second": 26.251,
+      "eval_steps_per_second": 0.547,
+      "step": 9945
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 9945,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 1.0607417906783846e+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 sha256:48a87fa4f8d017bb8eced56fe85a506a69a2c730afbb3d66d8afffc6fc7cfcee
+size 5496