Hugging Face's logo

ShengdingHu
/
cola

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
ShengdingHu commited on
Commit
f8f9564
•
1 Parent(s): 96b5fb1

Training in progress, epoch 1

Browse files
Files changed (12) hide show
  1. all_results.json +18 -0
  2. eval_results.json +8 -0
  3. pytorch_model.bin +1 -1
  4. runs/Jan31_19-06-42_node1/events.out.tfevents.1643627262.node1 +2 -2
  5. runs/Jan31_19-06-42_node1/events.out.tfevents.1643627698.node1 +3 -0
  6. runs/Jan31_19-19-11_node1/1643628019.4905183/events.out.tfevents.1643628019.node1 +3 -0
  7. runs/Jan31_19-19-11_node1/events.out.tfevents.1643628019.node1 +3 -0
  8. test_results.json +8 -0
  9. tokenizer.json +0 -0
  10. train_results.json +8 -0
  11. trainer_state.json +223 -0
  12. training_args.bin +1 -1
all_results.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "eval_average_metrics": 0.0,
4
+ "eval_loss": 0.27982431650161743,
5
+ "eval_matthews_correlation": 0.0,
6
+ "eval_runtime": 0.7644,
7
+ "eval_samples_per_second": 681.568,
8
+ "test_average_metrics": 0.0,
9
+ "test_loss": 0.27551037073135376,
10
+ "test_matthews_correlation": 0.0,
11
+ "test_runtime": 0.6746,
12
+ "test_samples_per_second": 773.807,
13
+ "train_loss": 0.2779904210290243,
14
+ "train_runtime": 435.9382,
15
+ "train_samples": 8551,
16
+ "train_samples_per_second": 392.303,
17
+ "train_steps_per_second": 3.946
18
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "eval_average_metrics": 0.0,
4
+ "eval_loss": 0.27982431650161743,
5
+ "eval_matthews_correlation": 0.0,
6
+ "eval_runtime": 0.7644,
7
+ "eval_samples_per_second": 681.568
8
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ce2672e171da4277ab5270927f0e17379f17e85f4a52d3525e0f54e0a911f62
3
  size 1084131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b72dfdda00c56b0ecbcd3fb22c325e0ed38a625296a8037d0726af1260a59444
3
  size 1084131
runs/Jan31_19-06-42_node1/events.out.tfevents.1643627262.node1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aed08c22f7001e9946783e5b262324ca693294bf10f1bf8324499e99cb50f69
3
- size 11113
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7edefeeb9c17a41cda42e5d2fc0bf476e7aee260bbddff9ae6a11cdb8d3b8d9f
3
+ size 11801
runs/Jan31_19-06-42_node1/events.out.tfevents.1643627698.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1fc6f2e19f253276c6d9b75e5e3c3a194330dc79e0e00ad6ad76a88623135f
3
+ size 708
runs/Jan31_19-19-11_node1/1643628019.4905183/events.out.tfevents.1643628019.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e21f6c960d173a3469c48a23cf95daff65fff95151d436cfc90b82cd0fcfd66
3
+ size 5008
runs/Jan31_19-19-11_node1/events.out.tfevents.1643628019.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c17c73771eb73d973240704425b287e25d6d9c14c1f66c176d26252288daafc
3
+ size 4302
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "test_average_metrics": 0.0,
4
+ "test_loss": 0.27551037073135376,
5
+ "test_matthews_correlation": 0.0,
6
+ "test_runtime": 0.6746,
7
+ "test_samples_per_second": 773.807
8
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "train_loss": 0.2779904210290243,
4
+ "train_runtime": 435.9382,
5
+ "train_samples": 8551,
6
+ "train_samples_per_second": 392.303,
7
+ "train_steps_per_second": 3.946
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "outputs/bitfit/t5-base/cola/checkpoint-86",
4
+ "epoch": 20.0,
5
+ "global_step": 1720,
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
+ "eval_average_metrics": 0.0,
13
+ "eval_loss": 0.27982431650161743,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8066,
16
+ "eval_samples_per_second": 645.909,
17
+ "step": 86
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_average_metrics": 0.0,
22
+ "eval_loss": 0.27295124530792236,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.8088,
25
+ "eval_samples_per_second": 644.148,
26
+ "step": 172
27
+ },
28
+ {
29
+ "epoch": 3.0,
30
+ "eval_average_metrics": 0.0,
31
+ "eval_loss": 0.27825212478637695,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.7356,
34
+ "eval_samples_per_second": 708.276,
35
+ "step": 258
36
+ },
37
+ {
38
+ "epoch": 4.0,
39
+ "eval_average_metrics": 0.0,
40
+ "eval_loss": 0.2720172107219696,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 0.7952,
43
+ "eval_samples_per_second": 655.185,
44
+ "step": 344
45
+ },
46
+ {
47
+ "epoch": 5.0,
48
+ "eval_average_metrics": 0.0,
49
+ "eval_loss": 0.2690984904766083,
50
+ "eval_matthews_correlation": 0.0,
51
+ "eval_runtime": 0.7358,
52
+ "eval_samples_per_second": 708.105,
53
+ "step": 430
54
+ },
55
+ {
56
+ "epoch": 5.81,
57
+ "learning_rate": 0.002127906976744186,
58
+ "loss": 0.3,
59
+ "step": 500
60
+ },
61
+ {
62
+ "epoch": 6.0,
63
+ "eval_average_metrics": 0.0,
64
+ "eval_loss": 0.2694063186645508,
65
+ "eval_matthews_correlation": 0.0,
66
+ "eval_runtime": 0.7511,
67
+ "eval_samples_per_second": 693.659,
68
+ "step": 516
69
+ },
70
+ {
71
+ "epoch": 7.0,
72
+ "eval_average_metrics": 0.0,
73
+ "eval_loss": 0.28033140301704407,
74
+ "eval_matthews_correlation": 0.0,
75
+ "eval_runtime": 0.7448,
76
+ "eval_samples_per_second": 699.547,
77
+ "step": 602
78
+ },
79
+ {
80
+ "epoch": 8.0,
81
+ "eval_average_metrics": 0.0,
82
+ "eval_loss": 0.2737719714641571,
83
+ "eval_matthews_correlation": 0.0,
84
+ "eval_runtime": 0.7024,
85
+ "eval_samples_per_second": 741.703,
86
+ "step": 688
87
+ },
88
+ {
89
+ "epoch": 9.0,
90
+ "eval_average_metrics": 0.0,
91
+ "eval_loss": 0.26990658044815063,
92
+ "eval_matthews_correlation": 0.0,
93
+ "eval_runtime": 0.7557,
94
+ "eval_samples_per_second": 689.411,
95
+ "step": 774
96
+ },
97
+ {
98
+ "epoch": 10.0,
99
+ "eval_average_metrics": 0.0,
100
+ "eval_loss": 0.269914448261261,
101
+ "eval_matthews_correlation": 0.0,
102
+ "eval_runtime": 0.7515,
103
+ "eval_samples_per_second": 693.272,
104
+ "step": 860
105
+ },
106
+ {
107
+ "epoch": 11.0,
108
+ "eval_average_metrics": 0.0,
109
+ "eval_loss": 0.2703316807746887,
110
+ "eval_matthews_correlation": 0.0,
111
+ "eval_runtime": 0.7544,
112
+ "eval_samples_per_second": 690.634,
113
+ "step": 946
114
+ },
115
+ {
116
+ "epoch": 11.63,
117
+ "learning_rate": 0.0012558139534883722,
118
+ "loss": 0.2698,
119
+ "step": 1000
120
+ },
121
+ {
122
+ "epoch": 12.0,
123
+ "eval_average_metrics": 0.0,
124
+ "eval_loss": 0.2690633535385132,
125
+ "eval_matthews_correlation": 0.0,
126
+ "eval_runtime": 0.8328,
127
+ "eval_samples_per_second": 625.617,
128
+ "step": 1032
129
+ },
130
+ {
131
+ "epoch": 13.0,
132
+ "eval_average_metrics": 0.0,
133
+ "eval_loss": 0.2688796818256378,
134
+ "eval_matthews_correlation": 0.0,
135
+ "eval_runtime": 0.7677,
136
+ "eval_samples_per_second": 678.682,
137
+ "step": 1118
138
+ },
139
+ {
140
+ "epoch": 14.0,
141
+ "eval_average_metrics": 0.0,
142
+ "eval_loss": 0.26915279030799866,
143
+ "eval_matthews_correlation": 0.0,
144
+ "eval_runtime": 0.7677,
145
+ "eval_samples_per_second": 678.671,
146
+ "step": 1204
147
+ },
148
+ {
149
+ "epoch": 15.0,
150
+ "eval_average_metrics": 0.0,
151
+ "eval_loss": 0.27187806367874146,
152
+ "eval_matthews_correlation": 0.0,
153
+ "eval_runtime": 0.7511,
154
+ "eval_samples_per_second": 693.632,
155
+ "step": 1290
156
+ },
157
+ {
158
+ "epoch": 16.0,
159
+ "eval_average_metrics": 0.0,
160
+ "eval_loss": 0.27496567368507385,
161
+ "eval_matthews_correlation": 0.0,
162
+ "eval_runtime": 0.7145,
163
+ "eval_samples_per_second": 729.175,
164
+ "step": 1376
165
+ },
166
+ {
167
+ "epoch": 17.0,
168
+ "eval_average_metrics": 0.0,
169
+ "eval_loss": 0.26937127113342285,
170
+ "eval_matthews_correlation": 0.0,
171
+ "eval_runtime": 0.7488,
172
+ "eval_samples_per_second": 695.759,
173
+ "step": 1462
174
+ },
175
+ {
176
+ "epoch": 17.44,
177
+ "learning_rate": 0.0003837209302325582,
178
+ "loss": 0.2686,
179
+ "step": 1500
180
+ },
181
+ {
182
+ "epoch": 18.0,
183
+ "eval_average_metrics": 0.0,
184
+ "eval_loss": 0.26900675892829895,
185
+ "eval_matthews_correlation": 0.0,
186
+ "eval_runtime": 0.7556,
187
+ "eval_samples_per_second": 689.484,
188
+ "step": 1548
189
+ },
190
+ {
191
+ "epoch": 19.0,
192
+ "eval_average_metrics": 0.0,
193
+ "eval_loss": 0.2690284252166748,
194
+ "eval_matthews_correlation": 0.0,
195
+ "eval_runtime": 0.7419,
196
+ "eval_samples_per_second": 702.253,
197
+ "step": 1634
198
+ },
199
+ {
200
+ "epoch": 20.0,
201
+ "eval_average_metrics": 0.0,
202
+ "eval_loss": 0.26897749304771423,
203
+ "eval_matthews_correlation": 0.0,
204
+ "eval_runtime": 0.7455,
205
+ "eval_samples_per_second": 698.863,
206
+ "step": 1720
207
+ },
208
+ {
209
+ "epoch": 20.0,
210
+ "step": 1720,
211
+ "total_flos": 6646762904679216.0,
212
+ "train_loss": 0.2779904210290243,
213
+ "train_runtime": 435.9382,
214
+ "train_samples_per_second": 392.303,
215
+ "train_steps_per_second": 3.946
216
+ }
217
+ ],
218
+ "max_steps": 1720,
219
+ "num_train_epochs": 20,
220
+ "total_flos": 6646762904679216.0,
221
+ "trial_name": null,
222
+ "trial_params": null
223
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5e98333eb27622d6bd9effc3988e125d40d0f8e4c4f1b2462c6e9541a23d253
3
  size 3183
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5671f63c7b06e7b055be2e554d1b04117f631e20ceccceb2c6bdc0d98e02557
3
  size 3183