cringe-bot/parameter-map.json at main · hotspoons/cringe-bot · GitHub

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
{
    "qlora":{
        "r": 32,
        "lora_alpha": 32,
        "lora_dropout": 0.1,
        "target_modules": [
            "q_proj",
            "k_proj",
            "v_proj",
            "o_proj",
            "gate_proj",
            "up_proj",
            "down_proj",
            "lm_head"
        ],
        "bias": "none",
        "task_type": "CAUSAL_LM"
    },
    "tokenizer":{
        "trust_remote_code": true,
        "add_eos_token": true,
        "pad_token": "<unk>",
        "padding_side": "right"
    },
    "model": {
    },
    "training":{
        "output_dir": "./results",
        "num_train_epochs": 10,
        "fp16": false,
        "bf16": false,
        "per_device_train_batch_size": 32,
        "per_device_eval_batch_size": 32,
        "gradient_accumulation_steps": 1,
        "gradient_checkpointing": true,
        "max_grad_norm": 0.3,
        "learning_rate": 1.8e-5,
        "weight_decay": 0.001,
        "optim": "paged_adamw_32bit",
        "lr_scheduler_type": "constant",
        "max_steps": -1,
        "warmup_ratio": 0.03,
        "group_by_length": true,
        "evaluation_strategy": "steps",
        "eval_steps": 25,
        "save_steps": 25,
        "logging_steps": 25,
        "do_eval": true,
        "report_to": "wandb"
    },
    "sft":{
        "max_seq_length": null,
        "packing": false
    }
}