Hugging Face's logo

moussaKam
/
frugalscore_small_bert-base_mover-score

Text Classification
Transformers
PyTorch
bert
Inference Endpoints
Model card Files Community
1
moussaKam commited on
Commit
3437e3a
•
1 Parent(s): b326957

fix model

Browse files
Files changed (7) hide show
  1. all_results.json +10 -2
  2. config.json +1 -1
  3. pytorch_model.bin +1 -1
  4. tokenizer_config.json +1 -1
  5. train_results.json +10 -2
  6. trainer_state.json +245 -0
  7. training_args.bin +2 -2
all_results.json CHANGED
@@ -1,6 +1,14 @@
1
  {
2
  "epoch": 3.0,
3
- "train_runtime": 2848.8824,
 
 
 
 
 
 
 
 
4
  "train_samples": 200000,
5
- "train_samples_per_second": 13.163
6
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 2085175296,
4
+ "init_mem_cpu_peaked_delta": 87703552,
5
+ "init_mem_gpu_alloc_delta": 115466752,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 1008685056,
8
+ "train_mem_cpu_peaked_delta": 124854272,
9
+ "train_mem_gpu_alloc_delta": 346377728,
10
+ "train_mem_gpu_peaked_delta": 5012993536,
11
+ "train_runtime": 2733.1751,
12
  "train_samples": 200000,
13
+ "train_samples_per_second": 6.86
14
  }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "checkpoints/small_bert",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "checkpoints/pretraining_checkpoints/translation_dataset/small_bert/",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:388266de501bae987cc6768b8455f773d178ef05413e0d2cabdcd5b003034586
3
  size 115091721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7307bf968df2acd6a244fc367749913ad7ce57f4406cd1896e0a8c359369a4
3
  size 115091721
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "checkpoints/small_bert", "do_basic_tokenize": true, "never_split": null}
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "checkpoints/pretraining_checkpoints/translation_dataset/small_bert/", "do_basic_tokenize": true, "never_split": null}
train_results.json CHANGED
@@ -1,6 +1,14 @@
1
  {
2
  "epoch": 3.0,
3
- "train_runtime": 2848.8824,
 
 
 
 
 
 
 
 
4
  "train_samples": 200000,
5
- "train_samples_per_second": 13.163
6
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 2085175296,
4
+ "init_mem_cpu_peaked_delta": 87703552,
5
+ "init_mem_gpu_alloc_delta": 115466752,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 1008685056,
8
+ "train_mem_cpu_peaked_delta": 124854272,
9
+ "train_mem_gpu_alloc_delta": 346377728,
10
+ "train_mem_gpu_peaked_delta": 5012993536,
11
+ "train_runtime": 2733.1751,
12
  "train_samples": 200000,
13
+ "train_samples_per_second": 6.86
14
  }
trainer_state.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 18750,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 2.2222222222222223e-05,
13
+ "loss": 0.0109,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 4.4444444444444447e-05,
19
+ "loss": 0.0035,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.24,
24
+ "learning_rate": 4.893617021276596e-05,
25
+ "loss": 0.0034,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.32,
30
+ "learning_rate": 4.751773049645391e-05,
31
+ "loss": 0.0032,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.4,
36
+ "learning_rate": 4.609929078014185e-05,
37
+ "loss": 0.0033,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.48,
42
+ "learning_rate": 4.468085106382979e-05,
43
+ "loss": 0.0032,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.56,
48
+ "learning_rate": 4.3262411347517734e-05,
49
+ "loss": 0.0032,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.64,
54
+ "learning_rate": 4.1843971631205674e-05,
55
+ "loss": 0.0031,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.72,
60
+ "learning_rate": 4.0425531914893614e-05,
61
+ "loss": 0.0031,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.8,
66
+ "learning_rate": 3.900709219858156e-05,
67
+ "loss": 0.003,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.88,
72
+ "learning_rate": 3.75886524822695e-05,
73
+ "loss": 0.0031,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.96,
78
+ "learning_rate": 3.617021276595745e-05,
79
+ "loss": 0.0029,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.04,
84
+ "learning_rate": 3.4751773049645395e-05,
85
+ "loss": 0.0026,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.12,
90
+ "learning_rate": 3.3333333333333335e-05,
91
+ "loss": 0.0022,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.2,
96
+ "learning_rate": 3.191489361702128e-05,
97
+ "loss": 0.0022,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.28,
102
+ "learning_rate": 3.0496453900709222e-05,
103
+ "loss": 0.0022,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.36,
108
+ "learning_rate": 2.9080851063829788e-05,
109
+ "loss": 0.0022,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.44,
114
+ "learning_rate": 2.766241134751773e-05,
115
+ "loss": 0.0021,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.52,
120
+ "learning_rate": 2.6243971631205678e-05,
121
+ "loss": 0.0022,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.6,
126
+ "learning_rate": 2.4825531914893618e-05,
127
+ "loss": 0.0022,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.68,
132
+ "learning_rate": 2.3409929078014188e-05,
133
+ "loss": 0.0021,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.76,
138
+ "learning_rate": 2.1991489361702128e-05,
139
+ "loss": 0.0022,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.84,
144
+ "learning_rate": 2.057304964539007e-05,
145
+ "loss": 0.0022,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.92,
150
+ "learning_rate": 1.9154609929078015e-05,
151
+ "loss": 0.0021,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.0,
156
+ "learning_rate": 1.7736170212765958e-05,
157
+ "loss": 0.0021,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.08,
162
+ "learning_rate": 1.63177304964539e-05,
163
+ "loss": 0.0016,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.16,
168
+ "learning_rate": 1.4899290780141845e-05,
169
+ "loss": 0.0016,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.24,
174
+ "learning_rate": 1.3480851063829788e-05,
175
+ "loss": 0.0016,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.32,
180
+ "learning_rate": 1.2065248226950356e-05,
181
+ "loss": 0.0016,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.4,
186
+ "learning_rate": 1.0646808510638298e-05,
187
+ "loss": 0.0015,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.48,
192
+ "learning_rate": 9.228368794326241e-06,
193
+ "loss": 0.0016,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.56,
198
+ "learning_rate": 7.809929078014185e-06,
199
+ "loss": 0.0016,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 2.64,
204
+ "learning_rate": 6.394326241134752e-06,
205
+ "loss": 0.0015,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 2.72,
210
+ "learning_rate": 4.975886524822695e-06,
211
+ "loss": 0.0015,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 2.8,
216
+ "learning_rate": 3.557446808510639e-06,
217
+ "loss": 0.0016,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 2.88,
222
+ "learning_rate": 2.1390070921985814e-06,
223
+ "loss": 0.0015,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 2.96,
228
+ "learning_rate": 7.23404255319149e-07,
229
+ "loss": 0.0015,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 3.0,
234
+ "step": 18750,
235
+ "total_flos": 0,
236
+ "train_runtime": 2733.1751,
237
+ "train_samples_per_second": 6.86
238
+ }
239
+ ],
240
+ "max_steps": 18750,
241
+ "num_train_epochs": 3,
242
+ "total_flos": 0,
243
+ "trial_name": null,
244
+ "trial_params": null
245
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bb3eb39378bb5d83d3a8f66c6004d26a4b1302fe1989695a3309afb635e7cb0
3
- size 2415
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536d5c94756a71f61b2d20baed8ab5f03c53ac7c8886325b067a3a92f7b3e5e0
3
+ size 2479