kejian commited on
Commit
4d5afe3
1 Parent(s): c1496a3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +182 -0
README.md ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: mit
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - tomekkorbak/detoxify-pile-chunk3-50000-100000
9
+ - tomekkorbak/detoxify-pile-chunk3-100000-150000
10
+ - tomekkorbak/detoxify-pile-chunk3-150000-200000
11
+ - tomekkorbak/detoxify-pile-chunk3-200000-250000
12
+ - tomekkorbak/detoxify-pile-chunk3-250000-300000
13
+ - tomekkorbak/detoxify-pile-chunk3-300000-350000
14
+ - tomekkorbak/detoxify-pile-chunk3-350000-400000
15
+ - tomekkorbak/detoxify-pile-chunk3-400000-450000
16
+ - tomekkorbak/detoxify-pile-chunk3-450000-500000
17
+ - tomekkorbak/detoxify-pile-chunk3-500000-550000
18
+ - tomekkorbak/detoxify-pile-chunk3-550000-600000
19
+ - tomekkorbak/detoxify-pile-chunk3-600000-650000
20
+ - tomekkorbak/detoxify-pile-chunk3-650000-700000
21
+ - tomekkorbak/detoxify-pile-chunk3-700000-750000
22
+ - tomekkorbak/detoxify-pile-chunk3-750000-800000
23
+ - tomekkorbak/detoxify-pile-chunk3-800000-850000
24
+ - tomekkorbak/detoxify-pile-chunk3-850000-900000
25
+ - tomekkorbak/detoxify-pile-chunk3-900000-950000
26
+ - tomekkorbak/detoxify-pile-chunk3-950000-1000000
27
+ - tomekkorbak/detoxify-pile-chunk3-1000000-1050000
28
+ - tomekkorbak/detoxify-pile-chunk3-1050000-1100000
29
+ - tomekkorbak/detoxify-pile-chunk3-1100000-1150000
30
+ - tomekkorbak/detoxify-pile-chunk3-1150000-1200000
31
+ - tomekkorbak/detoxify-pile-chunk3-1200000-1250000
32
+ - tomekkorbak/detoxify-pile-chunk3-1250000-1300000
33
+ - tomekkorbak/detoxify-pile-chunk3-1300000-1350000
34
+ - tomekkorbak/detoxify-pile-chunk3-1350000-1400000
35
+ - tomekkorbak/detoxify-pile-chunk3-1400000-1450000
36
+ - tomekkorbak/detoxify-pile-chunk3-1450000-1500000
37
+ - tomekkorbak/detoxify-pile-chunk3-1500000-1550000
38
+ - tomekkorbak/detoxify-pile-chunk3-1550000-1600000
39
+ - tomekkorbak/detoxify-pile-chunk3-1600000-1650000
40
+ - tomekkorbak/detoxify-pile-chunk3-1650000-1700000
41
+ - tomekkorbak/detoxify-pile-chunk3-1700000-1750000
42
+ - tomekkorbak/detoxify-pile-chunk3-1750000-1800000
43
+ - tomekkorbak/detoxify-pile-chunk3-1800000-1850000
44
+ model-index:
45
+ - name: kejian/cpsc-wmle-1.25
46
+ results: []
47
+ ---
48
+
49
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
50
+ should probably proofread and complete it, then remove this comment. -->
51
+
52
+ # kejian/cpsc-wmle-1.25
53
+
54
+ This model was trained from scratch on the tomekkorbak/detoxify-pile-chunk3-50000-100000, the tomekkorbak/detoxify-pile-chunk3-100000-150000, the tomekkorbak/detoxify-pile-chunk3-150000-200000, the tomekkorbak/detoxify-pile-chunk3-200000-250000, the tomekkorbak/detoxify-pile-chunk3-250000-300000, the tomekkorbak/detoxify-pile-chunk3-300000-350000, the tomekkorbak/detoxify-pile-chunk3-350000-400000, the tomekkorbak/detoxify-pile-chunk3-400000-450000, the tomekkorbak/detoxify-pile-chunk3-450000-500000, the tomekkorbak/detoxify-pile-chunk3-500000-550000, the tomekkorbak/detoxify-pile-chunk3-550000-600000, the tomekkorbak/detoxify-pile-chunk3-600000-650000, the tomekkorbak/detoxify-pile-chunk3-650000-700000, the tomekkorbak/detoxify-pile-chunk3-700000-750000, the tomekkorbak/detoxify-pile-chunk3-750000-800000, the tomekkorbak/detoxify-pile-chunk3-800000-850000, the tomekkorbak/detoxify-pile-chunk3-850000-900000, the tomekkorbak/detoxify-pile-chunk3-900000-950000, the tomekkorbak/detoxify-pile-chunk3-950000-1000000, the tomekkorbak/detoxify-pile-chunk3-1000000-1050000, the tomekkorbak/detoxify-pile-chunk3-1050000-1100000, the tomekkorbak/detoxify-pile-chunk3-1100000-1150000, the tomekkorbak/detoxify-pile-chunk3-1150000-1200000, the tomekkorbak/detoxify-pile-chunk3-1200000-1250000, the tomekkorbak/detoxify-pile-chunk3-1250000-1300000, the tomekkorbak/detoxify-pile-chunk3-1300000-1350000, the tomekkorbak/detoxify-pile-chunk3-1350000-1400000, the tomekkorbak/detoxify-pile-chunk3-1400000-1450000, the tomekkorbak/detoxify-pile-chunk3-1450000-1500000, the tomekkorbak/detoxify-pile-chunk3-1500000-1550000, the tomekkorbak/detoxify-pile-chunk3-1550000-1600000, the tomekkorbak/detoxify-pile-chunk3-1600000-1650000, the tomekkorbak/detoxify-pile-chunk3-1650000-1700000, the tomekkorbak/detoxify-pile-chunk3-1700000-1750000, the tomekkorbak/detoxify-pile-chunk3-1750000-1800000 and the tomekkorbak/detoxify-pile-chunk3-1800000-1850000 datasets.
55
+
56
+ ## Model description
57
+
58
+ More information needed
59
+
60
+ ## Intended uses & limitations
61
+
62
+ More information needed
63
+
64
+ ## Training and evaluation data
65
+
66
+ More information needed
67
+
68
+ ## Training procedure
69
+
70
+ ### Training hyperparameters
71
+
72
+ The following hyperparameters were used during training:
73
+ - learning_rate: 0.0007
74
+ - train_batch_size: 32
75
+ - eval_batch_size: 16
76
+ - seed: 42
77
+ - gradient_accumulation_steps: 2
78
+ - total_train_batch_size: 64
79
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
80
+ - lr_scheduler_type: linear
81
+ - lr_scheduler_warmup_ratio: 0.01
82
+ - training_steps: 42724
83
+ - mixed_precision_training: Native AMP
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.23.0
88
+ - Pytorch 1.13.0+cu116
89
+ - Datasets 2.0.0
90
+ - Tokenizers 0.12.1
91
+
92
+
93
+ # Full config
94
+ {'dataset': {'datasets': ['tomekkorbak/detoxify-pile-chunk3-50000-100000',
95
+ 'tomekkorbak/detoxify-pile-chunk3-100000-150000',
96
+ 'tomekkorbak/detoxify-pile-chunk3-150000-200000',
97
+ 'tomekkorbak/detoxify-pile-chunk3-200000-250000',
98
+ 'tomekkorbak/detoxify-pile-chunk3-250000-300000',
99
+ 'tomekkorbak/detoxify-pile-chunk3-300000-350000',
100
+ 'tomekkorbak/detoxify-pile-chunk3-350000-400000',
101
+ 'tomekkorbak/detoxify-pile-chunk3-400000-450000',
102
+ 'tomekkorbak/detoxify-pile-chunk3-450000-500000',
103
+ 'tomekkorbak/detoxify-pile-chunk3-500000-550000',
104
+ 'tomekkorbak/detoxify-pile-chunk3-550000-600000',
105
+ 'tomekkorbak/detoxify-pile-chunk3-600000-650000',
106
+ 'tomekkorbak/detoxify-pile-chunk3-650000-700000',
107
+ 'tomekkorbak/detoxify-pile-chunk3-700000-750000',
108
+ 'tomekkorbak/detoxify-pile-chunk3-750000-800000',
109
+ 'tomekkorbak/detoxify-pile-chunk3-800000-850000',
110
+ 'tomekkorbak/detoxify-pile-chunk3-850000-900000',
111
+ 'tomekkorbak/detoxify-pile-chunk3-900000-950000',
112
+ 'tomekkorbak/detoxify-pile-chunk3-950000-1000000',
113
+ 'tomekkorbak/detoxify-pile-chunk3-1000000-1050000',
114
+ 'tomekkorbak/detoxify-pile-chunk3-1050000-1100000',
115
+ 'tomekkorbak/detoxify-pile-chunk3-1100000-1150000',
116
+ 'tomekkorbak/detoxify-pile-chunk3-1150000-1200000',
117
+ 'tomekkorbak/detoxify-pile-chunk3-1200000-1250000',
118
+ 'tomekkorbak/detoxify-pile-chunk3-1250000-1300000',
119
+ 'tomekkorbak/detoxify-pile-chunk3-1300000-1350000',
120
+ 'tomekkorbak/detoxify-pile-chunk3-1350000-1400000',
121
+ 'tomekkorbak/detoxify-pile-chunk3-1400000-1450000',
122
+ 'tomekkorbak/detoxify-pile-chunk3-1450000-1500000',
123
+ 'tomekkorbak/detoxify-pile-chunk3-1500000-1550000',
124
+ 'tomekkorbak/detoxify-pile-chunk3-1550000-1600000',
125
+ 'tomekkorbak/detoxify-pile-chunk3-1600000-1650000',
126
+ 'tomekkorbak/detoxify-pile-chunk3-1650000-1700000',
127
+ 'tomekkorbak/detoxify-pile-chunk3-1700000-1750000',
128
+ 'tomekkorbak/detoxify-pile-chunk3-1750000-1800000',
129
+ 'tomekkorbak/detoxify-pile-chunk3-1800000-1850000'],
130
+ 'is_split_by_sentences': True},
131
+ 'generation': {'force_call_on': [42724],
132
+ 'metrics_configs': [{}, {'n': 1}, {'n': 2}, {'n': 5}],
133
+ 'scenario_configs': [{'generate_kwargs': {'do_sample': True,
134
+ 'max_length': 128,
135
+ 'min_length': 10,
136
+ 'temperature': 0.7,
137
+ 'top_k': 0,
138
+ 'top_p': 0.9},
139
+ 'name': 'unconditional',
140
+ 'num_samples': 2048},
141
+ {'generate_kwargs': {'do_sample': True,
142
+ 'max_length': 128,
143
+ 'min_length': 10,
144
+ 'temperature': 0.7,
145
+ 'top_k': 0,
146
+ 'top_p': 0.9},
147
+ 'name': 'challenging_rtp',
148
+ 'num_samples': 2048,
149
+ 'prompts_path': 'resources/challenging_rtp.jsonl'}],
150
+ 'scorer_config': {'device': 'cuda:0'}},
151
+ 'kl_gpt3_callback': {'force_call_on': [42724],
152
+ 'gpt3_kwargs': {'model_name': 'davinci'},
153
+ 'max_tokens': 64,
154
+ 'num_samples': 2048},
155
+ 'model': {'from_scratch': True,
156
+ 'gpt2_config_kwargs': {'reorder_and_upcast_attn': True,
157
+ 'scale_attn_by': True},
158
+ 'path_or_name': 'gpt2'},
159
+ 'objective': {'beta': 1.25, 'exponential': False, 'name': 'WeightedMLE'},
160
+ 'tokenizer': {'path_or_name': 'gpt2'},
161
+ 'training': {'dataloader_num_workers': 0,
162
+ 'effective_batch_size': 64,
163
+ 'evaluation_strategy': 'no',
164
+ 'fp16': True,
165
+ 'hub_model_id': 'kejian/cpsc-wmle-1.25',
166
+ 'hub_strategy': 'all_checkpoints',
167
+ 'learning_rate': 0.0007,
168
+ 'logging_first_step': True,
169
+ 'logging_steps': 50,
170
+ 'num_tokens': 2800000000.0,
171
+ 'output_dir': 'training_output_1.25',
172
+ 'per_device_train_batch_size': 16,
173
+ 'push_to_hub': True,
174
+ 'remove_unused_columns': False,
175
+ 'save_steps': 21362,
176
+ 'save_strategy': 'steps',
177
+ 'seed': 42,
178
+ 'warmup_ratio': 0.01,
179
+ 'weight_decay': 0.1}}
180
+
181
+ # Wandb URL:
182
+ https://wandb.ai/kejian/uncategorized/runs/38oxb2oc