Hugging Face's logo

moussaKam
/
frugalscore_medium_bert-base_mover-score

Text Classification
Transformers
PyTorch
bert
Inference Endpoints
Model card Files Community
1
moussaKam commited on
Commit
9ea9fb0
•
1 Parent(s): 7d97b75

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 +76 -76
  7. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,6 +1,14 @@
1
  {
2
  "epoch": 3.0,
3
- "train_runtime": 4486.3535,
 
 
 
 
 
 
 
 
4
  "train_samples": 200000,
5
- "train_samples_per_second": 4.179
6
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 2042978304,
4
+ "init_mem_cpu_peaked_delta": 121016320,
5
+ "init_mem_gpu_alloc_delta": 165904896,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 1035243520,
8
+ "train_mem_cpu_peaked_delta": 125026304,
9
+ "train_mem_gpu_alloc_delta": 497286656,
10
+ "train_mem_gpu_peaked_delta": 9670125056,
11
+ "train_runtime": 4763.7655,
12
  "train_samples": 200000,
13
+ "train_samples_per_second": 3.936
14
  }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "checkpoints/pretraining_checkpoints/summarization_dataset/medium_bert/",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "checkpoints/pretraining_checkpoints/translation_dataset/medium_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 sha256:568b43af52bae16bd888b5287358b1e3c9a9cc651b989e415df3f5b031d84928
3
  size 165557001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ccf06ed86038a8d9be5679261a9cfe5282906b64626ffaaa2adb981d2938d3
3
  size 165557001
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/pretraining_checkpoints/summarization_dataset/medium_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/medium_bert/", "do_basic_tokenize": true, "never_split": null}
train_results.json CHANGED
@@ -1,6 +1,14 @@
1
  {
2
  "epoch": 3.0,
3
- "train_runtime": 4486.3535,
 
 
 
 
 
 
 
 
4
  "train_samples": 200000,
5
- "train_samples_per_second": 4.179
6
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 2042978304,
4
+ "init_mem_cpu_peaked_delta": 121016320,
5
+ "init_mem_gpu_alloc_delta": 165904896,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 1035243520,
8
+ "train_mem_cpu_peaked_delta": 125026304,
9
+ "train_mem_gpu_alloc_delta": 497286656,
10
+ "train_mem_gpu_peaked_delta": 9670125056,
11
+ "train_runtime": 4763.7655,
12
  "train_samples": 200000,
13
+ "train_samples_per_second": 3.936
14
  }
trainer_state.json CHANGED
@@ -9,232 +9,232 @@
9
  "log_history": [
10
  {
11
  "epoch": 0.08,
12
- "learning_rate": 8.888888888888888e-06,
13
- "loss": 0.0494,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 0.16,
18
- "learning_rate": 1.7777777777777777e-05,
19
- "loss": 0.0015,
20
  "step": 1000
21
  },
22
  {
23
  "epoch": 0.24,
24
- "learning_rate": 1.9574468085106384e-05,
25
- "loss": 0.0011,
26
  "step": 1500
27
  },
28
  {
29
  "epoch": 0.32,
30
- "learning_rate": 1.9007092198581563e-05,
31
- "loss": 0.001,
32
  "step": 2000
33
  },
34
  {
35
  "epoch": 0.4,
36
- "learning_rate": 1.843971631205674e-05,
37
- "loss": 0.0009,
38
  "step": 2500
39
  },
40
  {
41
  "epoch": 0.48,
42
- "learning_rate": 1.7872340425531915e-05,
43
- "loss": 0.0008,
44
  "step": 3000
45
  },
46
  {
47
  "epoch": 0.56,
48
- "learning_rate": 1.7304964539007094e-05,
49
- "loss": 0.0008,
50
  "step": 3500
51
  },
52
  {
53
  "epoch": 0.64,
54
- "learning_rate": 1.673758865248227e-05,
55
- "loss": 0.0008,
56
  "step": 4000
57
  },
58
  {
59
  "epoch": 0.72,
60
- "learning_rate": 1.6170212765957446e-05,
61
- "loss": 0.0008,
62
  "step": 4500
63
  },
64
  {
65
  "epoch": 0.8,
66
- "learning_rate": 1.5602836879432626e-05,
67
- "loss": 0.0007,
68
  "step": 5000
69
  },
70
  {
71
  "epoch": 0.88,
72
- "learning_rate": 1.5035460992907802e-05,
73
- "loss": 0.0007,
74
  "step": 5500
75
  },
76
  {
77
  "epoch": 0.96,
78
- "learning_rate": 1.4468085106382981e-05,
79
- "loss": 0.0007,
80
  "step": 6000
81
  },
82
  {
83
  "epoch": 1.04,
84
- "learning_rate": 1.3900709219858157e-05,
85
- "loss": 0.0006,
86
  "step": 6500
87
  },
88
  {
89
  "epoch": 1.12,
90
- "learning_rate": 1.3333333333333333e-05,
91
- "loss": 0.0005,
92
  "step": 7000
93
  },
94
  {
95
  "epoch": 1.2,
96
- "learning_rate": 1.2765957446808513e-05,
97
- "loss": 0.0006,
98
  "step": 7500
99
  },
100
  {
101
  "epoch": 1.28,
102
- "learning_rate": 1.2198581560283689e-05,
103
- "loss": 0.0005,
104
  "step": 8000
105
  },
106
  {
107
  "epoch": 1.36,
108
- "learning_rate": 1.1631205673758865e-05,
109
- "loss": 0.0005,
110
  "step": 8500
111
  },
112
  {
113
  "epoch": 1.44,
114
- "learning_rate": 1.1063829787234044e-05,
115
- "loss": 0.0005,
116
  "step": 9000
117
  },
118
  {
119
  "epoch": 1.52,
120
- "learning_rate": 1.049645390070922e-05,
121
- "loss": 0.0005,
122
  "step": 9500
123
  },
124
  {
125
  "epoch": 1.6,
126
- "learning_rate": 9.929078014184398e-06,
127
- "loss": 0.0005,
128
  "step": 10000
129
  },
130
  {
131
  "epoch": 1.68,
132
- "learning_rate": 9.362836879432625e-06,
133
- "loss": 0.0005,
134
  "step": 10500
135
  },
136
  {
137
  "epoch": 1.76,
138
- "learning_rate": 8.795460992907802e-06,
139
- "loss": 0.0005,
140
  "step": 11000
141
  },
142
  {
143
  "epoch": 1.84,
144
- "learning_rate": 8.22808510638298e-06,
145
- "loss": 0.0005,
146
  "step": 11500
147
  },
148
  {
149
  "epoch": 1.92,
150
- "learning_rate": 7.660709219858156e-06,
151
- "loss": 0.0005,
152
  "step": 12000
153
  },
154
  {
155
  "epoch": 2.0,
156
- "learning_rate": 7.094468085106384e-06,
157
- "loss": 0.0005,
158
  "step": 12500
159
  },
160
  {
161
  "epoch": 2.08,
162
- "learning_rate": 6.5270921985815606e-06,
163
- "loss": 0.0004,
164
  "step": 13000
165
  },
166
  {
167
  "epoch": 2.16,
168
- "learning_rate": 5.959716312056738e-06,
169
- "loss": 0.0004,
170
  "step": 13500
171
  },
172
  {
173
  "epoch": 2.24,
174
- "learning_rate": 5.392340425531916e-06,
175
- "loss": 0.0004,
176
  "step": 14000
177
  },
178
  {
179
  "epoch": 2.32,
180
- "learning_rate": 4.826099290780143e-06,
181
- "loss": 0.0004,
182
  "step": 14500
183
  },
184
  {
185
  "epoch": 2.4,
186
- "learning_rate": 4.25872340425532e-06,
187
- "loss": 0.0004,
188
  "step": 15000
189
  },
190
  {
191
  "epoch": 2.48,
192
- "learning_rate": 3.691347517730497e-06,
193
- "loss": 0.0004,
194
  "step": 15500
195
  },
196
  {
197
  "epoch": 2.56,
198
- "learning_rate": 3.1239716312056738e-06,
199
- "loss": 0.0004,
200
  "step": 16000
201
  },
202
  {
203
  "epoch": 2.64,
204
- "learning_rate": 2.5565957446808515e-06,
205
- "loss": 0.0004,
206
  "step": 16500
207
  },
208
  {
209
  "epoch": 2.72,
210
- "learning_rate": 1.9892198581560283e-06,
211
- "loss": 0.0004,
212
  "step": 17000
213
  },
214
  {
215
  "epoch": 2.8,
216
- "learning_rate": 1.4218439716312058e-06,
217
- "loss": 0.0004,
218
  "step": 17500
219
  },
220
  {
221
  "epoch": 2.88,
222
- "learning_rate": 8.54468085106383e-07,
223
- "loss": 0.0004,
224
  "step": 18000
225
  },
226
  {
227
  "epoch": 2.96,
228
- "learning_rate": 2.870921985815603e-07,
229
- "loss": 0.0004,
230
  "step": 18500
231
  },
232
  {
233
  "epoch": 3.0,
234
  "step": 18750,
235
  "total_flos": 0,
236
- "train_runtime": 4486.3535,
237
- "train_samples_per_second": 4.179
238
  }
239
  ],
240
  "max_steps": 18750,
 
9
  "log_history": [
10
  {
11
  "epoch": 0.08,
12
+ "learning_rate": 2.2222222222222223e-05,
13
+ "loss": 0.0104,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 0.16,
18
+ "learning_rate": 4.4444444444444447e-05,
19
+ "loss": 0.0027,
20
  "step": 1000
21
  },
22
  {
23
  "epoch": 0.24,
24
+ "learning_rate": 4.893617021276596e-05,
25
+ "loss": 0.0026,
26
  "step": 1500
27
  },
28
  {
29
  "epoch": 0.32,
30
+ "learning_rate": 4.751773049645391e-05,
31
+ "loss": 0.0024,
32
  "step": 2000
33
  },
34
  {
35
  "epoch": 0.4,
36
+ "learning_rate": 4.609929078014185e-05,
37
+ "loss": 0.0026,
38
  "step": 2500
39
  },
40
  {
41
  "epoch": 0.48,
42
+ "learning_rate": 4.468085106382979e-05,
43
+ "loss": 0.0025,
44
  "step": 3000
45
  },
46
  {
47
  "epoch": 0.56,
48
+ "learning_rate": 4.3262411347517734e-05,
49
+ "loss": 0.0025,
50
  "step": 3500
51
  },
52
  {
53
  "epoch": 0.64,
54
+ "learning_rate": 4.1843971631205674e-05,
55
+ "loss": 0.0025,
56
  "step": 4000
57
  },
58
  {
59
  "epoch": 0.72,
60
+ "learning_rate": 4.0425531914893614e-05,
61
+ "loss": 0.0024,
62
  "step": 4500
63
  },
64
  {
65
  "epoch": 0.8,
66
+ "learning_rate": 3.900709219858156e-05,
67
+ "loss": 0.0024,
68
  "step": 5000
69
  },
70
  {
71
  "epoch": 0.88,
72
+ "learning_rate": 3.75886524822695e-05,
73
+ "loss": 0.0023,
74
  "step": 5500
75
  },
76
  {
77
  "epoch": 0.96,
78
+ "learning_rate": 3.617021276595745e-05,
79
+ "loss": 0.0023,
80
  "step": 6000
81
  },
82
  {
83
  "epoch": 1.04,
84
+ "learning_rate": 3.4751773049645395e-05,
85
+ "loss": 0.002,
86
  "step": 6500
87
  },
88
  {
89
  "epoch": 1.12,
90
+ "learning_rate": 3.3333333333333335e-05,
91
+ "loss": 0.0015,
92
  "step": 7000
93
  },
94
  {
95
  "epoch": 1.2,
96
+ "learning_rate": 3.191489361702128e-05,
97
+ "loss": 0.0015,
98
  "step": 7500
99
  },
100
  {
101
  "epoch": 1.28,
102
+ "learning_rate": 3.0496453900709222e-05,
103
+ "loss": 0.0015,
104
  "step": 8000
105
  },
106
  {
107
  "epoch": 1.36,
108
+ "learning_rate": 2.9078014184397162e-05,
109
+ "loss": 0.0015,
110
  "step": 8500
111
  },
112
  {
113
  "epoch": 1.44,
114
+ "learning_rate": 2.765957446808511e-05,
115
+ "loss": 0.0015,
116
  "step": 9000
117
  },
118
  {
119
  "epoch": 1.52,
120
+ "learning_rate": 2.6243971631205678e-05,
121
+ "loss": 0.0015,
122
  "step": 9500
123
  },
124
  {
125
  "epoch": 1.6,
126
+ "learning_rate": 2.4825531914893618e-05,
127
+ "loss": 0.0015,
128
  "step": 10000
129
  },
130
  {
131
  "epoch": 1.68,
132
+ "learning_rate": 2.340709219858156e-05,
133
+ "loss": 0.0015,
134
  "step": 10500
135
  },
136
  {
137
  "epoch": 1.76,
138
+ "learning_rate": 2.1988652482269505e-05,
139
+ "loss": 0.0015,
140
  "step": 11000
141
  },
142
  {
143
  "epoch": 1.84,
144
+ "learning_rate": 2.057021276595745e-05,
145
+ "loss": 0.0014,
146
  "step": 11500
147
  },
148
  {
149
  "epoch": 1.92,
150
+ "learning_rate": 1.9151773049645392e-05,
151
+ "loss": 0.0014,
152
  "step": 12000
153
  },
154
  {
155
  "epoch": 2.0,
156
+ "learning_rate": 1.7733333333333335e-05,
157
+ "loss": 0.0014,
158
  "step": 12500
159
  },
160
  {
161
  "epoch": 2.08,
162
+ "learning_rate": 1.6314893617021275e-05,
163
+ "loss": 0.001,
164
  "step": 13000
165
  },
166
  {
167
  "epoch": 2.16,
168
+ "learning_rate": 1.4899290780141845e-05,
169
+ "loss": 0.001,
170
  "step": 13500
171
  },
172
  {
173
  "epoch": 2.24,
174
+ "learning_rate": 1.3480851063829788e-05,
175
+ "loss": 0.001,
176
  "step": 14000
177
  },
178
  {
179
  "epoch": 2.32,
180
+ "learning_rate": 1.2062411347517732e-05,
181
+ "loss": 0.001,
182
  "step": 14500
183
  },
184
  {
185
  "epoch": 2.4,
186
+ "learning_rate": 1.0643971631205673e-05,
187
+ "loss": 0.001,
188
  "step": 15000
189
  },
190
  {
191
  "epoch": 2.48,
192
+ "learning_rate": 9.228368794326241e-06,
193
+ "loss": 0.001,
194
  "step": 15500
195
  },
196
  {
197
  "epoch": 2.56,
198
+ "learning_rate": 7.809929078014185e-06,
199
+ "loss": 0.001,
200
  "step": 16000
201
  },
202
  {
203
  "epoch": 2.64,
204
+ "learning_rate": 6.391489361702129e-06,
205
+ "loss": 0.0009,
206
  "step": 16500
207
  },
208
  {
209
  "epoch": 2.72,
210
+ "learning_rate": 4.973049645390071e-06,
211
+ "loss": 0.0009,
212
  "step": 17000
213
  },
214
  {
215
  "epoch": 2.8,
216
+ "learning_rate": 3.557446808510639e-06,
217
+ "loss": 0.0009,
218
  "step": 17500
219
  },
220
  {
221
  "epoch": 2.88,
222
+ "learning_rate": 2.1390070921985814e-06,
223
+ "loss": 0.0009,
224
  "step": 18000
225
  },
226
  {
227
  "epoch": 2.96,
228
+ "learning_rate": 7.205673758865249e-07,
229
+ "loss": 0.0009,
230
  "step": 18500
231
  },
232
  {
233
  "epoch": 3.0,
234
  "step": 18750,
235
  "total_flos": 0,
236
+ "train_runtime": 4763.7655,
237
+ "train_samples_per_second": 3.936
238
  }
239
  ],
240
  "max_steps": 18750,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a0e800d9edf3fdf5c9726cdf7c0dd495bf7f0e0b3d11887556b9bc89f2bbbf4
3
  size 2479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c661bd4e99ec3e576c861e36134129d1f4746165ae4d7cefa82ed887f86b5db
3
  size 2479