gokuls commited on
Commit
3e544bc
1 Parent(s): 880b7ae

End of training

Browse files
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
  datasets:
@@ -13,7 +15,7 @@ model-index:
13
  name: Text Classification
14
  type: text-classification
15
  dataset:
16
- name: glue
17
  type: glue
18
  config: cola
19
  split: validation
@@ -32,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  # sa_BERT_no_pretrain_cola
34
 
35
- This model is a fine-tuned version of [](https://huggingface.co/) on the glue dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.6310
38
  - Matthews Correlation: 0.0
39
  - Accuracy: 0.6913
40
 
 
1
  ---
2
+ language:
3
+ - en
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
15
  name: Text Classification
16
  type: text-classification
17
  dataset:
18
+ name: GLUE COLA
19
  type: glue
20
  config: cola
21
  split: validation
 
34
 
35
  # sa_BERT_no_pretrain_cola
36
 
37
+ This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE COLA dataset.
38
  It achieves the following results on the evaluation set:
39
+ - Loss: 0.6180
40
  - Matthews Correlation: 0.0
41
  - Accuracy: 0.6913
42
 
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.6912751793861389,
4
+ "eval_loss": 0.6180034875869751,
5
+ "eval_matthews_correlation": 0.0,
6
+ "eval_runtime": 2.0383,
7
+ "eval_samples": 1043,
8
+ "eval_samples_per_second": 511.692,
9
+ "eval_steps_per_second": 4.415,
10
+ "train_loss": 0.6391209616589902,
11
+ "train_runtime": 614.413,
12
+ "train_samples": 8551,
13
+ "train_samples_per_second": 695.867,
14
+ "train_steps_per_second": 5.452
15
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.6912751793861389,
4
+ "eval_loss": 0.6180034875869751,
5
+ "eval_matthews_correlation": 0.0,
6
+ "eval_runtime": 2.0383,
7
+ "eval_samples": 1043,
8
+ "eval_samples_per_second": 511.692,
9
+ "eval_steps_per_second": 4.415
10
+ }
logs/events.out.tfevents.1685335826.serv-3317.2800436.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609bc7b54eb6651a54b65e955fec78ad34dad30c45e266719d48915df6b3329b
3
+ size 427
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 0.6391209616589902,
4
+ "train_runtime": 614.413,
5
+ "train_samples": 8551,
6
+ "train_samples_per_second": 695.867,
7
+ "train_steps_per_second": 5.452
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,185 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6180034875869751,
3
+ "best_model_checkpoint": "sa_BERT_no_pretrain_cola/checkpoint-335",
4
+ "epoch": 10.0,
5
+ "global_step": 670,
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": 0.0004902985074626866,
13
+ "loss": 0.8826,
14
+ "step": 67
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.6912751793861389,
19
+ "eval_loss": 0.662401020526886,
20
+ "eval_matthews_correlation": 0.0,
21
+ "eval_runtime": 2.0483,
22
+ "eval_samples_per_second": 509.196,
23
+ "eval_steps_per_second": 4.394,
24
+ "step": 67
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00048029850746268655,
29
+ "loss": 0.616,
30
+ "step": 134
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.6912751793861389,
35
+ "eval_loss": 0.6358437538146973,
36
+ "eval_matthews_correlation": 0.0,
37
+ "eval_runtime": 2.0437,
38
+ "eval_samples_per_second": 510.344,
39
+ "eval_steps_per_second": 4.404,
40
+ "step": 134
41
+ },
42
+ {
43
+ "epoch": 3.0,
44
+ "learning_rate": 0.0004702985074626866,
45
+ "loss": 0.6134,
46
+ "step": 201
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "eval_accuracy": 0.6912751793861389,
51
+ "eval_loss": 0.6195451021194458,
52
+ "eval_matthews_correlation": 0.0,
53
+ "eval_runtime": 2.0501,
54
+ "eval_samples_per_second": 508.758,
55
+ "eval_steps_per_second": 4.39,
56
+ "step": 201
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.0004602985074626866,
61
+ "loss": 0.6139,
62
+ "step": 268
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_accuracy": 0.6912751793861389,
67
+ "eval_loss": 0.6284816265106201,
68
+ "eval_matthews_correlation": 0.0,
69
+ "eval_runtime": 2.0535,
70
+ "eval_samples_per_second": 507.913,
71
+ "eval_steps_per_second": 4.383,
72
+ "step": 268
73
+ },
74
+ {
75
+ "epoch": 5.0,
76
+ "learning_rate": 0.0004502985074626866,
77
+ "loss": 0.6117,
78
+ "step": 335
79
+ },
80
+ {
81
+ "epoch": 5.0,
82
+ "eval_accuracy": 0.6912751793861389,
83
+ "eval_loss": 0.6180034875869751,
84
+ "eval_matthews_correlation": 0.0,
85
+ "eval_runtime": 2.044,
86
+ "eval_samples_per_second": 510.27,
87
+ "eval_steps_per_second": 4.403,
88
+ "step": 335
89
+ },
90
+ {
91
+ "epoch": 6.0,
92
+ "learning_rate": 0.00044029850746268656,
93
+ "loss": 0.6099,
94
+ "step": 402
95
+ },
96
+ {
97
+ "epoch": 6.0,
98
+ "eval_accuracy": 0.6912751793861389,
99
+ "eval_loss": 0.618323028087616,
100
+ "eval_matthews_correlation": 0.0,
101
+ "eval_runtime": 2.045,
102
+ "eval_samples_per_second": 510.017,
103
+ "eval_steps_per_second": 4.401,
104
+ "step": 402
105
+ },
106
+ {
107
+ "epoch": 7.0,
108
+ "learning_rate": 0.0004302985074626866,
109
+ "loss": 0.6113,
110
+ "step": 469
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_accuracy": 0.6912751793861389,
115
+ "eval_loss": 0.6232409477233887,
116
+ "eval_matthews_correlation": 0.0,
117
+ "eval_runtime": 2.0445,
118
+ "eval_samples_per_second": 510.158,
119
+ "eval_steps_per_second": 4.402,
120
+ "step": 469
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "learning_rate": 0.00042029850746268656,
125
+ "loss": 0.6135,
126
+ "step": 536
127
+ },
128
+ {
129
+ "epoch": 8.0,
130
+ "eval_accuracy": 0.6912751793861389,
131
+ "eval_loss": 0.6182034015655518,
132
+ "eval_matthews_correlation": 0.0,
133
+ "eval_runtime": 2.0437,
134
+ "eval_samples_per_second": 510.344,
135
+ "eval_steps_per_second": 4.404,
136
+ "step": 536
137
+ },
138
+ {
139
+ "epoch": 9.0,
140
+ "learning_rate": 0.0004102985074626866,
141
+ "loss": 0.6094,
142
+ "step": 603
143
+ },
144
+ {
145
+ "epoch": 9.0,
146
+ "eval_accuracy": 0.6912751793861389,
147
+ "eval_loss": 0.6220687031745911,
148
+ "eval_matthews_correlation": 0.0,
149
+ "eval_runtime": 2.0453,
150
+ "eval_samples_per_second": 509.941,
151
+ "eval_steps_per_second": 4.4,
152
+ "step": 603
153
+ },
154
+ {
155
+ "epoch": 10.0,
156
+ "learning_rate": 0.0004002985074626866,
157
+ "loss": 0.6096,
158
+ "step": 670
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_accuracy": 0.6912751793861389,
163
+ "eval_loss": 0.6310281157493591,
164
+ "eval_matthews_correlation": 0.0,
165
+ "eval_runtime": 2.0508,
166
+ "eval_samples_per_second": 508.571,
167
+ "eval_steps_per_second": 4.388,
168
+ "step": 670
169
+ },
170
+ {
171
+ "epoch": 10.0,
172
+ "step": 670,
173
+ "total_flos": 1.311463297777664e+16,
174
+ "train_loss": 0.6391209616589902,
175
+ "train_runtime": 614.413,
176
+ "train_samples_per_second": 695.867,
177
+ "train_steps_per_second": 5.452
178
+ }
179
+ ],
180
+ "max_steps": 3350,
181
+ "num_train_epochs": 50,
182
+ "total_flos": 1.311463297777664e+16,
183
+ "trial_name": null,
184
+ "trial_params": null
185
+ }