Hugging Face's logo

shoubhik
/
electra_abbv_20k_data_multilabel

PyTorch
Model card Files
xet
 Community
shoubhik commited on
Commit
c017cc6
·
1 Parent(s): 7ed7a98

Initial Version

Browse files
Files changed (10) hide show
  1. optimizer.pt +3 -0
  2. pytorch_model.bin +3 -0
  3. rng_state.pth +3 -0
  4. scheduler.pt +3 -0
  5. special_tokens_map.json +1 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +1 -0
  8. trainer_state.json +211 -0
  9. training_args.bin +3 -0
  10. vocab.txt +0 -0
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4e7a77f34049c091d40078f260fc0ac071b61b49edc05d9dec53a2b4f26439
3
+ size 117552277
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0e6703bc9dc7961654842a7e745922e6310bd9ae1f6e1feb868d3f230016f7
3
+ size 58804329
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e672da69abb99c1a5dbbfc1de7e29dbfe4c88d50c3c8ff1140ff5178b27a93c
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98993b8d9e817554ec6ae8c6ccd3c43f20e8fbae01a288523863abf7222da452
3
+ size 623
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, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "name_or_path": "xhlu/electra-medal", "special_tokens_map_file": "/root/.cache/huggingface/transformers/f7e7e0af4b4a5eb6db6cda2accf3a2085612c93bf092c8baf42df197a28947ff.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_class": "ElectraTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6931639313697815,
3
+ "best_model_checkpoint": "checkpoints/electra_26_4_1/checkpoint-13858",
4
+ "epoch": 13.0,
5
+ "global_step": 13858,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 3.904917901570934e-05,
13
+ "loss": 0.7426,
14
+ "step": 1066
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_auc_micro": 0.5212763137512771,
19
+ "eval_loss": 0.6989310383796692,
20
+ "eval_runtime": 23.3554,
21
+ "eval_samples_per_second": 128.835,
22
+ "eval_steps_per_second": 8.092,
23
+ "step": 1066
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 3.5795080764400225e-05,
28
+ "loss": 0.6964,
29
+ "step": 2132
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_auc_micro": 0.5228480764195904,
34
+ "eval_loss": 0.6949135661125183,
35
+ "eval_runtime": 23.3685,
36
+ "eval_samples_per_second": 128.763,
37
+ "eval_steps_per_second": 8.088,
38
+ "step": 2132
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 3.254098251309111e-05,
43
+ "loss": 0.6944,
44
+ "step": 3198
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_auc_micro": 0.5232832697413072,
49
+ "eval_loss": 0.6939617395401001,
50
+ "eval_runtime": 23.1376,
51
+ "eval_samples_per_second": 130.048,
52
+ "eval_steps_per_second": 8.169,
53
+ "step": 3198
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 2.9286884261782e-05,
58
+ "loss": 0.6938,
59
+ "step": 4264
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_auc_micro": 0.5234944214364559,
64
+ "eval_loss": 0.6935874223709106,
65
+ "eval_runtime": 23.1396,
66
+ "eval_samples_per_second": 130.037,
67
+ "eval_steps_per_second": 8.168,
68
+ "step": 4264
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 2.603278601047289e-05,
73
+ "loss": 0.6935,
74
+ "step": 5330
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_auc_micro": 0.5237105566327973,
79
+ "eval_loss": 0.6934056282043457,
80
+ "eval_runtime": 23.0585,
81
+ "eval_samples_per_second": 130.494,
82
+ "eval_steps_per_second": 8.197,
83
+ "step": 5330
84
+ },
85
+ {
86
+ "epoch": 6.0,
87
+ "learning_rate": 2.2778687759163776e-05,
88
+ "loss": 0.6934,
89
+ "step": 6396
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "eval_auc_micro": 0.5238991498421133,
94
+ "eval_loss": 0.6933064460754395,
95
+ "eval_runtime": 23.1864,
96
+ "eval_samples_per_second": 129.775,
97
+ "eval_steps_per_second": 8.151,
98
+ "step": 6396
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "learning_rate": 1.952458950785467e-05,
103
+ "loss": 0.6933,
104
+ "step": 7462
105
+ },
106
+ {
107
+ "epoch": 7.0,
108
+ "eval_auc_micro": 0.5239438807088983,
109
+ "eval_loss": 0.6932488679885864,
110
+ "eval_runtime": 23.1343,
111
+ "eval_samples_per_second": 130.067,
112
+ "eval_steps_per_second": 8.17,
113
+ "step": 7462
114
+ },
115
+ {
116
+ "epoch": 8.0,
117
+ "learning_rate": 1.6270491256545556e-05,
118
+ "loss": 0.6932,
119
+ "step": 8528
120
+ },
121
+ {
122
+ "epoch": 8.0,
123
+ "eval_auc_micro": 0.523929452444219,
124
+ "eval_loss": 0.6932142972946167,
125
+ "eval_runtime": 23.2347,
126
+ "eval_samples_per_second": 129.505,
127
+ "eval_steps_per_second": 8.134,
128
+ "step": 8528
129
+ },
130
+ {
131
+ "epoch": 9.0,
132
+ "learning_rate": 1.3016393005236445e-05,
133
+ "loss": 0.6932,
134
+ "step": 9594
135
+ },
136
+ {
137
+ "epoch": 9.0,
138
+ "eval_auc_micro": 0.5239810749738886,
139
+ "eval_loss": 0.6931925415992737,
140
+ "eval_runtime": 23.1045,
141
+ "eval_samples_per_second": 130.234,
142
+ "eval_steps_per_second": 8.18,
143
+ "step": 9594
144
+ },
145
+ {
146
+ "epoch": 10.0,
147
+ "learning_rate": 9.762294753927335e-06,
148
+ "loss": 0.6932,
149
+ "step": 10660
150
+ },
151
+ {
152
+ "epoch": 10.0,
153
+ "eval_auc_micro": 0.5241205756951521,
154
+ "eval_loss": 0.6931790709495544,
155
+ "eval_runtime": 23.1973,
156
+ "eval_samples_per_second": 129.713,
157
+ "eval_steps_per_second": 8.148,
158
+ "step": 10660
159
+ },
160
+ {
161
+ "epoch": 11.0,
162
+ "learning_rate": 6.508196502618222e-06,
163
+ "loss": 0.6932,
164
+ "step": 11726
165
+ },
166
+ {
167
+ "epoch": 11.0,
168
+ "eval_auc_micro": 0.5241602931373088,
169
+ "eval_loss": 0.6931705474853516,
170
+ "eval_runtime": 23.0891,
171
+ "eval_samples_per_second": 130.321,
172
+ "eval_steps_per_second": 8.186,
173
+ "step": 11726
174
+ },
175
+ {
176
+ "epoch": 12.0,
177
+ "learning_rate": 3.254098251309111e-06,
178
+ "loss": 0.6932,
179
+ "step": 12792
180
+ },
181
+ {
182
+ "epoch": 12.0,
183
+ "eval_auc_micro": 0.5242074068777832,
184
+ "eval_loss": 0.6931658387184143,
185
+ "eval_runtime": 23.1506,
186
+ "eval_samples_per_second": 129.975,
187
+ "eval_steps_per_second": 8.164,
188
+ "step": 12792
189
+ },
190
+ {
191
+ "epoch": 13.0,
192
+ "learning_rate": 0.0,
193
+ "loss": 0.6932,
194
+ "step": 13858
195
+ },
196
+ {
197
+ "epoch": 13.0,
198
+ "eval_auc_micro": 0.5243155309888969,
199
+ "eval_loss": 0.6931639313697815,
200
+ "eval_runtime": 23.1954,
201
+ "eval_samples_per_second": 129.724,
202
+ "eval_steps_per_second": 8.148,
203
+ "step": 13858
204
+ }
205
+ ],
206
+ "max_steps": 13858,
207
+ "num_train_epochs": 13,
208
+ "total_flos": 0.0,
209
+ "trial_name": null,
210
+ "trial_params": null
211
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882a51b56ca6727647fdad1665a574f7840506583f205b6460cdaae1415d0f12
3
+ size 2991
vocab.txt ADDED
The diff for this file is too large to render. See raw diff