olive-recipes/tencent-HY-MT1.5-1.8B/baseline/tencent-HY-MT1.5-1.8B_pytorch_with_eval.json at 75717a022866dcb28d9d100f150ff0f2c6bc6046 · microsoft/olive-recipes · 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
{
    "input_model": {
        "type": "HfModel",
        "model_path": "tencent/HY-MT1.5-1.8B",
        "load_kwargs": {
            "torch_dtype": "float16"
        }
    },
    "systems": {
        "local_system": {
            "type": "LocalSystem",
            "accelerators": [
                {
                    "device": "gpu"
                }
            ]
        }
    },
    "evaluators": {
        "zh_en_translation": {
            "type": "LMEvaluator",
            "tasks": [
                {
                    "task": "wmt18-zh-en",
                    "dataset_path": "wmt/wmt18",
                    "dataset_name": "zh-en",
                    "output_type": "generate_until",
                    "training_split": "train",
                    "validation_split": "validation",
                    "fewshot_split": "validation",
                    "test_split": "test",
                    "doc_to_text": "Translate the following segment into English, without additional explanation.\n\n{{translation[\"zh\"]}}\nEnglish translation:",
                    "doc_to_target": "{{translation[\"en\"]}}",
                    "metric_list": [
                        {
                            "metric": "bleu",
                            "aggregation": "bleu",
                            "higher_is_better": true
                        },
                        {
                            "metric": "ter",
                            "aggregation": "ter",
                            "higher_is_better": false
                        },
                        {
                            "metric": "chrf",
                            "aggregation": "chrf",
                            "higher_is_better": true
                        }
                    ],
                    "generation_kwargs": {
                        "until": [
                            "\n"
                        ],
                        "do_sample": false,
                        "temperature": 0.0
                    },
                    "repeats": 1,
                    "metadata": {
                        "version": 1.0
                    }
                }
            ],
            "batch_size": 32,
            "bootstrap_iters": 0,
            "max_length": 2048,
            "device": "gpu"
        }
    },
    "evaluator": "zh_en_translation",
    "target": "local_system",
    "log_severity_level": 0,
    "output_dir": "model_pytorch",
    "cache_dir": "cache_pytorch"
}