Hugging Face's logo

moussaKam
/
frugalscore_small_deberta_bert-score

Text Classification
Transformers
PyTorch
bert
Inference Endpoints
Model card Files Community
moussaKam commited on
Commit
12bfa17
•
1 Parent(s): 12964c8

Add model

Browse files
Files changed (10) hide show
  1. all_results.json +14 -0
  2. config.json +30 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +1 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +1 -0
  7. train_results.json +14 -0
  8. trainer_state.json +245 -0
  9. training_args.bin +3 -0
  10. vocab.txt +0 -0
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 2074243072,
4
+ "init_mem_cpu_peaked_delta": 94711808,
5
+ "init_mem_gpu_alloc_delta": 115466752,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 856477696,
8
+ "train_mem_cpu_peaked_delta": 124870656,
9
+ "train_mem_gpu_alloc_delta": 346377728,
10
+ "train_mem_gpu_peaked_delta": 5012993536,
11
+ "train_runtime": 5557.9976,
12
+ "train_samples": 200000,
13
+ "train_samples_per_second": 3.374
14
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-4_H-512_A-8",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 512,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2048,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 8,
23
+ "num_hidden_layers": 4,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "transformers_version": "4.6.0.dev0",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
+ "vocab_size": 30522
30
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb63d6308eb2e1ebb2bb61f9a5f8656b60926debdfe97c894a3948111fa3b333
3
+ size 115091721
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +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": "google/bert_uncased_L-4_H-512_A-8", "do_basic_tokenize": true, "never_split": null}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 2074243072,
4
+ "init_mem_cpu_peaked_delta": 94711808,
5
+ "init_mem_gpu_alloc_delta": 115466752,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 856477696,
8
+ "train_mem_cpu_peaked_delta": 124870656,
9
+ "train_mem_gpu_alloc_delta": 346377728,
10
+ "train_mem_gpu_peaked_delta": 5012993536,
11
+ "train_runtime": 5557.9976,
12
+ "train_samples": 200000,
13
+ "train_samples_per_second": 3.374
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": 2.92032e-05,
13
+ "loss": 0.0311,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 2.8403200000000003e-05,
19
+ "loss": 0.0075,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.24,
24
+ "learning_rate": 2.76032e-05,
25
+ "loss": 0.0042,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.32,
30
+ "learning_rate": 2.68032e-05,
31
+ "loss": 0.003,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.4,
36
+ "learning_rate": 2.60032e-05,
37
+ "loss": 0.0026,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.48,
42
+ "learning_rate": 2.52032e-05,
43
+ "loss": 0.0022,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.56,
48
+ "learning_rate": 2.4403200000000004e-05,
49
+ "loss": 0.0021,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.64,
54
+ "learning_rate": 2.36032e-05,
55
+ "loss": 0.0019,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.72,
60
+ "learning_rate": 2.2803200000000002e-05,
61
+ "loss": 0.0018,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.8,
66
+ "learning_rate": 2.20032e-05,
67
+ "loss": 0.0018,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.88,
72
+ "learning_rate": 2.12032e-05,
73
+ "loss": 0.0017,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.96,
78
+ "learning_rate": 2.0403199999999998e-05,
79
+ "loss": 0.0016,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.04,
84
+ "learning_rate": 1.9603200000000002e-05,
85
+ "loss": 0.0015,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.12,
90
+ "learning_rate": 1.88032e-05,
91
+ "loss": 0.0014,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.2,
96
+ "learning_rate": 1.80032e-05,
97
+ "loss": 0.0013,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.28,
102
+ "learning_rate": 1.7203199999999998e-05,
103
+ "loss": 0.0014,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.36,
108
+ "learning_rate": 1.64032e-05,
109
+ "loss": 0.0013,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.44,
114
+ "learning_rate": 1.5603200000000003e-05,
115
+ "loss": 0.0013,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.52,
120
+ "learning_rate": 1.48032e-05,
121
+ "loss": 0.0013,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.6,
126
+ "learning_rate": 1.40032e-05,
127
+ "loss": 0.0012,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.68,
132
+ "learning_rate": 1.32032e-05,
133
+ "loss": 0.0013,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.76,
138
+ "learning_rate": 1.24032e-05,
139
+ "loss": 0.0012,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.84,
144
+ "learning_rate": 1.1603200000000001e-05,
145
+ "loss": 0.0012,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.92,
150
+ "learning_rate": 1.08032e-05,
151
+ "loss": 0.0011,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.0,
156
+ "learning_rate": 1.0003200000000001e-05,
157
+ "loss": 0.0012,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.08,
162
+ "learning_rate": 9.2032e-06,
163
+ "loss": 0.001,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.16,
168
+ "learning_rate": 8.403200000000001e-06,
169
+ "loss": 0.0011,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.24,
174
+ "learning_rate": 7.6032e-06,
175
+ "loss": 0.001,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.32,
180
+ "learning_rate": 6.8048000000000005e-06,
181
+ "loss": 0.001,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.4,
186
+ "learning_rate": 6.0048000000000005e-06,
187
+ "loss": 0.001,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.48,
192
+ "learning_rate": 5.2048e-06,
193
+ "loss": 0.001,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.56,
198
+ "learning_rate": 4.4048e-06,
199
+ "loss": 0.001,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 2.64,
204
+ "learning_rate": 3.6064000000000003e-06,
205
+ "loss": 0.001,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 2.72,
210
+ "learning_rate": 2.8064e-06,
211
+ "loss": 0.001,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 2.8,
216
+ "learning_rate": 2.0064e-06,
217
+ "loss": 0.001,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 2.88,
222
+ "learning_rate": 1.2064e-06,
223
+ "loss": 0.001,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 2.96,
228
+ "learning_rate": 4.08e-07,
229
+ "loss": 0.0009,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 3.0,
234
+ "step": 18750,
235
+ "total_flos": 0,
236
+ "train_runtime": 5557.9976,
237
+ "train_samples_per_second": 3.374
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c22d16a5647e0e91cba13456d06c26782bde2845bc631f8dc36ee998436bd40
3
+ size 2543
vocab.txt ADDED
The diff for this file is too large to render. See raw diff