Hugging Face's logo

Spaces:
inflaton
/
machine-translation
Build error

App Files Community
machine-translation
File size: 13,046 Bytes 
3f6b774
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
 
Qwen/Qwen2-7B-Instruct None False datasets/mac/mac.tsv results/mac-results.csv False 300
loading env vars from: /Users/inflaton/code/engd/papers/rapget-translation/.env
workding dir: /Users/inflaton/code/engd/papers/rapget-translation
Python 3.11.9
Name: torch
Version: 2.4.0
Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration
Home-page: https://pytorch.org/
Author: PyTorch Team
Author-email: packages@pytorch.org
License: BSD-3
Location: /Users/inflaton/anaconda3/envs/rapget/lib/python3.11/site-packages
Requires: filelock, fsspec, jinja2, networkx, sympy, typing-extensions
Required-by: accelerate, peft, torchaudio, torchvision, trl
---
Name: transformers
Version: 4.43.3
Summary: State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
Home-page: https://github.com/huggingface/transformers
Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors)
Author-email: transformers@huggingface.co
License: Apache 2.0 License
Location: /Users/inflaton/anaconda3/envs/rapget/lib/python3.11/site-packages
Requires: filelock, huggingface-hub, numpy, packaging, pyyaml, regex, requests, safetensors, tokenizers, tqdm
Required-by: llamafactory, peft, trl
CPU times: user 8.97 ms, sys: 13.7 ms, total: 22.7 ms
Wall time: 1.91 s
MPS is available
loading existing data from: logs/openai-training-sample.jsonl
messages
0	[{'role': 'system', 'content': 'Marv is a fact...
1	[{'role': 'system', 'content': 'Marv is a fact...
2	[{'role': 'system', 'content': 'Marv is a fact...
FileObject(id='file-IokPHn4YWcniXL4wGnK4xVmn', bytes=3413094, created_at=1723269681, filename='openai-training.jsonl', object='file', purpose='fine-tune', status='processed', status_details=None)
FineTuningJob(id='ftjob-TcCo4KtDd3Gp5cnOVky2Rxhh', created_at=1723270136, error=Error(code=None, message=None, param=None), fine_tuned_model=None, finished_at=None, hyperparameters=Hyperparameters(n_epochs=6, batch_size='auto', learning_rate_multiplier='auto'), model='gpt-4o-mini-2024-07-18', object='fine_tuning.job', organization_id='org-RXHVnD8cqPvqTPdXgZ5rQdl3', result_files=[], seed=1046194933, status='validating_files', trained_tokens=None, training_file='file-IokPHn4YWcniXL4wGnK4xVmn', validation_file=None, estimated_finish=None, integrations=[], user_provided_suffix=None)
FineTuningJob(id='ftjob-TcCo4KtDd3Gp5cnOVky2Rxhh', created_at=1723270136, error=Error(code=None, message=None, param=None), fine_tuned_model='ft:gpt-4o-mini-2024-07-18:mastercard::9uaCEFTs', finished_at=1723272532, hyperparameters=Hyperparameters(n_epochs=6, batch_size=18, learning_rate_multiplier=1.8), model='gpt-4o-mini-2024-07-18', object='fine_tuning.job', organization_id='org-RXHVnD8cqPvqTPdXgZ5rQdl3', result_files=['file-aCppW0GWhhytwe4yKwymNUZl'], seed=1046194933, status='succeeded', trained_tokens=3640956, training_file='file-IokPHn4YWcniXL4wGnK4xVmn', validation_file=None, estimated_finish=None, integrations=[], user_provided_suffix=None)
Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ufuULvy
loading train/test data files
DatasetDict({
    train: Dataset({
        features: ['chinese', 'english'],
        num_rows: 4528
    })
    test: Dataset({
        features: ['chinese', 'english'],
        num_rows: 1133
    })
})
--------------------------------------------------
chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。
--------------------------------------------------
english: Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.
*** Evaluating with num_shots: 0
100%|██████████| 1133/1133 [16:48<00:00,  1.12it/s]
gpt-4o-mini/epochs-01 metrics: {'meteor': 0.3785370331806402, 'sacrebleu': {'score': 12.052844230027103, 'counts': [12818, 4623, 2153, 1081], 'totals': [29097, 27964, 26850, 25740], 'precisions': [44.05265147609719, 16.53196967529681, 8.018621973929237, 4.1996891996892], 'bp': 0.9631327655852462, 'sys_len': 29097, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.12052844230027103, 'precisions': [0.44052651476097193, 0.1653196967529681, 0.08018621973929237, 0.041996891996891994], 'brevity_penalty': 0.9631327655852462, 'length_ratio': 0.9637959589267969, 'translation_length': 29097, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.4244007719128182, 'rouge2': 0.17601540674784633, 'rougeL': 0.3693615986543504, 'rougeLsum': 0.3696442718692141}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}
Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ug0Gt3w
loading train/test data files
DatasetDict({
    train: Dataset({
        features: ['chinese', 'english'],
        num_rows: 4528
    })
    test: Dataset({
        features: ['chinese', 'english'],
        num_rows: 1133
    })
})
--------------------------------------------------
chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。
--------------------------------------------------
english: Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.
*** Evaluating with num_shots: 0
100%|██████████| 1133/1133 [17:56<00:00,  1.05it/s]
gpt-4o-mini/epochs-02 metrics: {'meteor': 0.3785921332515917, 'sacrebleu': {'score': 12.033706874864837, 'counts': [12801, 4628, 2150, 1076], 'totals': [29076, 27943, 26830, 25722], 'precisions': [44.02600082542303, 16.562287513867517, 8.013417815877748, 4.183189487598165], 'bp': 0.9624112877781842, 'sys_len': 29076, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.12033706874864836, 'precisions': [0.4402600082542303, 0.16562287513867516, 0.08013417815877749, 0.04183189487598165], 'brevity_penalty': 0.9624112877781842, 'length_ratio': 0.9631003643590593, 'translation_length': 29076, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.4235104923203792, 'rouge2': 0.1758318317686482, 'rougeL': 0.36922125683186846, 'rougeLsum': 0.3693808162149962}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}
Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ug5PhpZ
loading train/test data files
DatasetDict({
    train: Dataset({
        features: ['chinese', 'english'],
        num_rows: 4528
    })
    test: Dataset({
        features: ['chinese', 'english'],
        num_rows: 1133
    })
})
--------------------------------------------------
chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。
--------------------------------------------------
english: Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.
*** Evaluating with num_shots: 0
100%|██████████| 1133/1133 [17:02<00:00,  1.11it/s]
gpt-4o-mini/epochs-03 metrics: {'meteor': 0.37736228106121694, 'sacrebleu': {'score': 11.933111335430906, 'counts': [12779, 4601, 2124, 1061], 'totals': [29096, 27963, 26848, 25737], 'precisions': [43.920126477866376, 16.453885491542394, 7.911203814064362, 4.122469596301046], 'bp': 0.9630984208616785, 'sys_len': 29096, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.11933111335430906, 'precisions': [0.4392012647786637, 0.16453885491542394, 0.07911203814064362, 0.041224695963010455], 'brevity_penalty': 0.9630984208616785, 'length_ratio': 0.9637628353759523, 'translation_length': 29096, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.4235319934194407, 'rouge2': 0.17493309683581332, 'rougeL': 0.3685697120399035, 'rougeLsum': 0.3689298428303013}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}
Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ugPThQI
loading train/test data files
DatasetDict({
    train: Dataset({
        features: ['chinese', 'english'],
        num_rows: 4528
    })
    test: Dataset({
        features: ['chinese', 'english'],
        num_rows: 1133
    })
})
--------------------------------------------------
chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。
--------------------------------------------------
english: Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.
*** Evaluating with num_shots: 0
100%|██████████| 1133/1133 [18:35<00:00,  1.02it/s]
gpt-4o-mini/epochs-04 metrics: {'meteor': 0.37818535038887346, 'sacrebleu': {'score': 11.933285526593995, 'counts': [12797, 4601, 2121, 1061], 'totals': [29110, 27977, 26861, 25749], 'precisions': [43.960838199931295, 16.445651785395146, 7.896206395889952, 4.120548370810517], 'bp': 0.9635791436286372, 'sys_len': 29110, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.11933285526593994, 'precisions': [0.43960838199931296, 0.16445651785395146, 0.07896206395889951, 0.041205483708105166], 'brevity_penalty': 0.9635791436286371, 'length_ratio': 0.9642265650877774, 'translation_length': 29110, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.42372801674771476, 'rouge2': 0.17487358435014705, 'rougeL': 0.36931437347367646, 'rougeLsum': 0.36934766241132383}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}

Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ugVLmcB
loading train/test data files
DatasetDict({
    train: Dataset({
        features: ['chinese', 'english'],
        num_rows: 4528
    })
    test: Dataset({
        features: ['chinese', 'english'],
        num_rows: 1133
    })
})
--------------------------------------------------
chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。
--------------------------------------------------
english: Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.
*** Evaluating with num_shots: 0
100%|██████████| 1133/1133 [15:47<00:00,  1.20it/s]
gpt-4o-mini/epochs-05 metrics: {'meteor': 0.3790673551140706, 'sacrebleu': {'score': 11.955698498650582, 'counts': [12808, 4609, 2126, 1064], 'totals': [29209, 28076, 26959, 25846], 'precisions': [43.849498442260945, 16.416156147599374, 7.88604918580066, 4.116691170780778], 'bp': 0.9669721941455759, 'sys_len': 29209, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.11955698498650584, 'precisions': [0.4384949844226095, 0.16416156147599373, 0.0788604918580066, 0.041166911707807785], 'brevity_penalty': 0.9669721941455759, 'length_ratio': 0.9675057966213978, 'translation_length': 29209, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.42476082012412075, 'rouge2': 0.17559955520032905, 'rougeL': 0.3700113513462385, 'rougeLsum': 0.37012014201963733}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}
Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9uaCEFTs
loading train/test data files
DatasetDict({
    train: Dataset({
        features: ['chinese', 'english'],
        num_rows: 4528
    })
    test: Dataset({
        features: ['chinese', 'english'],
        num_rows: 1133
    })
})
--------------------------------------------------
chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。
--------------------------------------------------
english: Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.
*** Evaluating with num_shots: 0
100%|██████████| 1133/1133 [15:43<00:00,  1.20it/s]
gpt-4o-mini/epochs-06 metrics: {'meteor': 0.3792226866395673, 'sacrebleu': {'score': 11.982811850915233, 'counts': [12810, 4617, 2137, 1066], 'totals': [29116, 27983, 26868, 25757], 'precisions': [43.996428080780326, 16.499303148340065, 7.95369956825964, 4.138680746981403], 'bp': 0.9637850995333245, 'sys_len': 29116, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.11982811850915229, 'precisions': [0.43996428080780325, 0.16499303148340064, 0.0795369956825964, 0.04138680746981403], 'brevity_penalty': 0.9637850995333245, 'length_ratio': 0.9644253063928453, 'translation_length': 29116, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.4251187202203103, 'rouge2': 0.17553224521896635, 'rougeL': 0.37003282393672954, 'rougeLsum': 0.370114181474168}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}