初始化项目,由ModelHub XC社区提供模型
Model: mnsm92/English_To_Bengali_Translation Source: Original Platform
This commit is contained in:
49
training_params.json
Normal file
49
training_params.json
Normal file
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"model": "mnsm92/etbl-47",
|
||||
"project_name": "etbl-51",
|
||||
"data_path": "mnsm92/english_to_bengali_translation_l_part_4_09",
|
||||
"train_split": "train",
|
||||
"valid_split": null,
|
||||
"add_eos_token": true,
|
||||
"block_size": 512,
|
||||
"model_max_length": 512,
|
||||
"padding": "right",
|
||||
"trainer": "sft",
|
||||
"use_flash_attention_2": false,
|
||||
"log": "tensorboard",
|
||||
"disable_gradient_checkpointing": false,
|
||||
"logging_steps": -1,
|
||||
"eval_strategy": "epoch",
|
||||
"save_total_limit": 1,
|
||||
"auto_find_batch_size": false,
|
||||
"mixed_precision": "bf16",
|
||||
"lr": 1e-05,
|
||||
"epochs": 1,
|
||||
"batch_size": 8,
|
||||
"warmup_ratio": 0.1,
|
||||
"gradient_accumulation": 2,
|
||||
"optimizer": "paged_adamw_8bit",
|
||||
"scheduler": "cosine",
|
||||
"weight_decay": 0.0,
|
||||
"max_grad_norm": 1.0,
|
||||
"seed": 42,
|
||||
"chat_template": "tokenizer",
|
||||
"quantization": "int8",
|
||||
"target_modules": "all-linear",
|
||||
"merge_adapter": true,
|
||||
"peft": true,
|
||||
"lora_r": 16,
|
||||
"lora_alpha": 32,
|
||||
"lora_dropout": 0.05,
|
||||
"model_ref": null,
|
||||
"dpo_beta": 0.1,
|
||||
"max_prompt_length": 128,
|
||||
"max_completion_length": 512,
|
||||
"prompt_text_column": null,
|
||||
"text_column": "text",
|
||||
"rejected_text_column": null,
|
||||
"push_to_hub": true,
|
||||
"username": "mnsm92",
|
||||
"unsloth": false,
|
||||
"distributed_backend": null
|
||||
}
|
||||
Reference in New Issue
Block a user