Upload 5 files

upload json files

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "bartpho-syllable",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "MBartForQuestionAnswering"
+  ],
+  "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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 40031
+}

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "added_tokens_decoder": {
+    "40030": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.3250207813798838,
+  "eval_steps": 2000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8312551953449709,
+      "grad_norm": 16.231958389282227,
+      "learning_rate": 1.584026622296173e-05,
+      "loss": 2.784,
+      "step": 500
+    },
+    {
+      "epoch": 1.6625103906899419,
+      "grad_norm": 22.48409080505371,
+      "learning_rate": 1.1680532445923463e-05,
+      "loss": 1.8476,
+      "step": 1000
+    },
+    {
+      "epoch": 2.493765586034913,
+      "grad_norm": 12.915149688720703,
+      "learning_rate": 7.520798668885192e-06,
+      "loss": 1.1381,
+      "step": 1500
+    },
+    {
+      "epoch": 3.3250207813798838,
+      "grad_norm": 12.136582374572754,
+      "learning_rate": 3.3610648918469217e-06,
+      "loss": 0.9397,
+      "step": 2000
+    },
+    {
+      "epoch": 3.3250207813798838,
+      "eval_loss": 0.7907648682594299,
+      "eval_runtime": 93.7355,
+      "eval_samples_per_second": 15.181,
+      "eval_steps_per_second": 0.949,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3863209696980992e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}