File size: 1,759 Bytes
9078c5e deb8e2a 9078c5e deb8e2a 9078c5e deb8e2a 9078c5e deb8e2a 9078c5e 85bc0c5 9078c5e deb8e2a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
{
"model_name": "unsloth/gemma-2-2b",
"max_seq_length": 2048,
"dtype": null,
"load_in_4bit": false,
"lora_params": {
"r": 16,
"target_modules": [
"q_proj",
"k_proj",
"v_proj",
"o_proj",
"gate_proj",
"up_proj",
"down_proj"
],
"lora_alpha": 16,
"lora_dropout": 0,
"bias": "none",
"use_gradient_checkpointing": "unsloth",
"random_state": 3407,
"use_rslora": false,
"loftq_config": null
},
"training_args": {
"per_device_train_batch_size": 4,
"gradient_accumulation_steps": 4,
"warmup_steps": 5,
"num_train_epochs": 1,
"learning_rate": 0.0002,
"fp16": false,
"bf16": true,
"logging_steps": 1,
"optim": "adamw_8bit",
"weight_decay": 0.01,
"lr_scheduler_type": "linear",
"seed": 3407,
"output_dir": "outputs",
"report_to": "none"
},
"data_config": {
"dataset_name": "marmikpandya/mental-health",
"dataset_split": "train",
"dataset_rows": null,
"conversation_format": {
"instruction": "Provide an instruction to the model, e.g., 'Provide advice on coping with stress.'",
"input": "Include user details or context, e.g., 'I've been feeling overwhelmed with work and personal responsibilities.'",
"response": "The model's response based on the instruction and input."
},
"max_seq_length": 2048,
"train_on_responses_only": false
},
"inference_config": {
"temperature": 1.0,
"min_p": 0.9,
"max_new_tokens": 512
},
"alpaca_prompt": {
"template": "If you are a licensed psychologist, please provide this patient with a helpful response to their concern.\n\n### Instruction:\n{}\n\n### Input:\n{}\n\n### Response:\n{}",
"eos_token": true
}
} |