93 lines
2.3 KiB
JSON
93 lines
2.3 KiB
JSON
{
|
|
"tests": [
|
|
{
|
|
"name": "quick_smoke_test_sft",
|
|
"input": {
|
|
"user_id": "user",
|
|
"model_id": "llama-test",
|
|
"run_id": "llama-test",
|
|
"credentials": {
|
|
"wandb_api_key": "",
|
|
"hf_token": ""
|
|
},
|
|
"args": {
|
|
"base_model": "NousResearch/Meta-Llama-3-8B",
|
|
"model_type": "LlamaForCausalLM",
|
|
"tokenizer_type": "AutoTokenizer",
|
|
"load_in_8bit": true,
|
|
"load_in_4bit": false,
|
|
"strict": false,
|
|
"datasets": [
|
|
{
|
|
"path": "mhenrichsen/alpaca_2k_test",
|
|
"type": "alpaca"
|
|
}
|
|
],
|
|
"val_set_size": 0.05,
|
|
"output_dir": "./outputs/lora-out",
|
|
"sequence_len": 4096,
|
|
"sample_packing": true,
|
|
"eval_sample_packing": false,
|
|
"pad_to_sequence_len": true,
|
|
"adapter": "lora",
|
|
"lora_r": 32,
|
|
"lora_alpha": 16,
|
|
"lora_dropout": 0.05,
|
|
"lora_target_linear": true,
|
|
"lora_modules_to_save": [
|
|
"embed_tokens",
|
|
"lm_head"
|
|
],
|
|
"gradient_accumulation_steps": 4,
|
|
"micro_batch_size": 2,
|
|
"num_epochs": 1,
|
|
"optimizer": "adamw_bnb_8bit",
|
|
"lr_scheduler": "cosine",
|
|
"learning_rate": 0.0002,
|
|
"train_on_inputs": false,
|
|
"group_by_length": false,
|
|
"bf16": "auto",
|
|
"tf32": false,
|
|
"gradient_checkpointing": true,
|
|
"logging_steps": 1,
|
|
"flash_attention": true,
|
|
"warmup_steps": 1,
|
|
"evals_per_epoch": 1,
|
|
"eval_max_new_tokens": 128,
|
|
"saves_per_epoch": 1,
|
|
"weight_decay": 0.0,
|
|
"special_tokens": {
|
|
"pad_token": "<|end_of_text|>"
|
|
}
|
|
}
|
|
},
|
|
"timeout": 100000
|
|
}
|
|
],
|
|
"config": {
|
|
"gpuTypeId": "NVIDIA GeForce RTX 4090",
|
|
"gpuCount": 1,
|
|
"containerDiskInGb": 200,
|
|
"env": [
|
|
{
|
|
"key": "TOKENIZER",
|
|
"value": ""
|
|
},
|
|
{
|
|
"key": "DISABLE_LOG_STATS",
|
|
"value": "true"
|
|
}
|
|
],
|
|
"allowedCudaVersions": [
|
|
"12.8",
|
|
"12.7",
|
|
"12.6",
|
|
"12.5",
|
|
"12.4",
|
|
"12.3",
|
|
"12.2",
|
|
"12.1",
|
|
"12.0"
|
|
]
|
|
}
|
|
} |