PhiCookBook/code/03.Finetuning/olive-ort-example/phrase-classification.json at main · microsoft/PhiCookBook · 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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
{
    "$schema": "https://microsoft.github.io/Olive/schema.json",
    "input_model":{
        "type": "PyTorchModel",
        "config": {
            "hf_config": {
                "model_name": "microsoft/Phi-3-mini-4k-instruct",
                "task": "text-generation",
                "from_pretrained_args": {
                    "trust_remote_code": true
                }
            }
        }
    },
    "systems": {
        "local_system": {
            "type": "LocalSystem",
            "config": {
                "accelerators": [
                    {
                        "device": "gpu",
                        "execution_providers": [
                            "CUDAExecutionProvider"
                        ]
                    }
                ]
            }
        }
    },
    "data_configs": [
        {
            "name": "dataset_default_train",
            "type": "HuggingfaceContainer",
            "params_config": {
                "data_name": "json",
                "data_files":"dataset/dataset-classification.json",
                "split": "train",
                "component_kwargs": {
                    "pre_process_data": {
                        "dataset_type": "corpus",
                        "text_cols": ["phrase","tone"],
                        "text_template": "<|user|>\n{phrase}<|end|>\n<|assistant|>\n{tone}<|end|>",
                        "corpus_strategy": "join",
                        "source_max_len": 1024,
                        "pad_to_max_len": false,
                        "use_attention_mask": false
                    }
                }
            }
        }
    ],
    "passes": {
        "lora": {
            "type": "LoRA",
            "config": {
                "target_modules": [
                    "o_proj",
                    "qkv_proj"
                ],
                "lora_r": 64,
                "lora_alpha": 64,
                "lora_dropout": 0.1,
                "train_data_config": "dataset_default_train",
                "eval_dataset_size": 0.3,
                "training_args": {
                    "seed": 0,
                    "data_seed": 42,
                    "per_device_train_batch_size": 1,
                    "per_device_eval_batch_size": 1,
                    "gradient_accumulation_steps": 4,
                    "gradient_checkpointing": false,
                    "learning_rate": 0.0001,
                    "max_steps": 150,
                    "evaluation_strategy": "steps",
                    "adam_beta2": 0.999,
                    "max_grad_norm": 0.3
                }
            }
        },
        "merge": {
            "type": "MergeAdapterWeights"
        },
        "mb": {
            "type": "ModelBuilder",
            "config": {
                "precision": "int4"
            }
        }
    },
    "engine": {
        "cache_dir": "cache",
        "output_dir": "models",
        "host": "local_system",
        "target": "local_system"
    }
}