gokuls commited on
Commit
f6b49a6
1 Parent(s): 98aa3e4

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: mrpc
19
  split: validation
@@ -21,10 +23,10 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.6838235294117647
25
  - name: F1
26
  type: f1
27
- value: 0.7809847198641766
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  # hBERTv1_mrpc
34
 
35
- This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the glue dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.9708
38
- - Accuracy: 0.6838
39
- - F1: 0.7810
40
- - Combined Score: 0.7324
41
 
42
  ## Model description
43
 
 
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 MRPC
19
  type: glue
20
  config: mrpc
21
  split: validation
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.6862745098039216
27
  - name: F1
28
  type: f1
29
+ value: 0.7999999999999999
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
34
 
35
  # hBERTv1_mrpc
36
 
37
+ This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the GLUE MRPC dataset.
38
  It achieves the following results on the evaluation set:
39
+ - Loss: 0.6051
40
+ - Accuracy: 0.6863
41
+ - F1: 0.8000
42
+ - Combined Score: 0.7431
43
 
44
  ## Model description
45
 
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 12.0,
3
+ "eval_accuracy": 0.6862745098039216,
4
+ "eval_combined_score": 0.7431372549019608,
5
+ "eval_f1": 0.7999999999999999,
6
+ "eval_loss": 0.6050820350646973,
7
+ "eval_runtime": 0.5403,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 755.096,
10
+ "eval_steps_per_second": 3.701,
11
+ "train_loss": 0.4964691546228197,
12
+ "train_runtime": 203.7797,
13
+ "train_samples": 3668,
14
+ "train_samples_per_second": 899.991,
15
+ "train_steps_per_second": 3.68
16
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 12.0,
3
+ "eval_accuracy": 0.6862745098039216,
4
+ "eval_combined_score": 0.7431372549019608,
5
+ "eval_f1": 0.7999999999999999,
6
+ "eval_loss": 0.6050820350646973,
7
+ "eval_runtime": 0.5403,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 755.096,
10
+ "eval_steps_per_second": 3.701
11
+ }
logs/events.out.tfevents.1677681169.serv-9220.1178704.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2d7267f8afbe59b4250732729bd83828a8faad617fbd82aed01440282af639
3
+ size 467
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 12.0,
3
+ "train_loss": 0.4964691546228197,
4
+ "train_runtime": 203.7797,
5
+ "train_samples": 3668,
6
+ "train_samples_per_second": 899.991,
7
+ "train_steps_per_second": 3.68
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,229 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6050820350646973,
3
+ "best_model_checkpoint": "hBERTv1_mrpc/checkpoint-105",
4
+ "epoch": 12.0,
5
+ "global_step": 180,
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": 4.9e-05,
13
+ "loss": 0.6536,
14
+ "step": 15
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.6838235294117647,
19
+ "eval_combined_score": 0.7480253018237863,
20
+ "eval_f1": 0.8122270742358079,
21
+ "eval_loss": 0.6242610216140747,
22
+ "eval_runtime": 0.5132,
23
+ "eval_samples_per_second": 794.982,
24
+ "eval_steps_per_second": 3.897,
25
+ "step": 15
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 4.8e-05,
30
+ "loss": 0.6275,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.7009803921568627,
36
+ "eval_combined_score": 0.7563543936092956,
37
+ "eval_f1": 0.8117283950617284,
38
+ "eval_loss": 0.6174396872520447,
39
+ "eval_runtime": 0.511,
40
+ "eval_samples_per_second": 798.461,
41
+ "eval_steps_per_second": 3.914,
42
+ "step": 30
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 4.7e-05,
47
+ "loss": 0.6129,
48
+ "step": 45
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.696078431372549,
53
+ "eval_combined_score": 0.7571301247771836,
54
+ "eval_f1": 0.8181818181818181,
55
+ "eval_loss": 0.6089469194412231,
56
+ "eval_runtime": 0.5125,
57
+ "eval_samples_per_second": 796.115,
58
+ "eval_steps_per_second": 3.903,
59
+ "step": 45
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "learning_rate": 4.600000000000001e-05,
64
+ "loss": 0.6087,
65
+ "step": 60
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.6887254901960784,
70
+ "eval_combined_score": 0.7508428629183632,
71
+ "eval_f1": 0.8129602356406479,
72
+ "eval_loss": 0.606163740158081,
73
+ "eval_runtime": 0.5136,
74
+ "eval_samples_per_second": 794.368,
75
+ "eval_steps_per_second": 3.894,
76
+ "step": 60
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "learning_rate": 4.5e-05,
81
+ "loss": 0.5939,
82
+ "step": 75
83
+ },
84
+ {
85
+ "epoch": 5.0,
86
+ "eval_accuracy": 0.6862745098039216,
87
+ "eval_combined_score": 0.739911448450348,
88
+ "eval_f1": 0.7935483870967743,
89
+ "eval_loss": 0.6104128956794739,
90
+ "eval_runtime": 0.5141,
91
+ "eval_samples_per_second": 793.575,
92
+ "eval_steps_per_second": 3.89,
93
+ "step": 75
94
+ },
95
+ {
96
+ "epoch": 6.0,
97
+ "learning_rate": 4.4000000000000006e-05,
98
+ "loss": 0.5707,
99
+ "step": 90
100
+ },
101
+ {
102
+ "epoch": 6.0,
103
+ "eval_accuracy": 0.7083333333333334,
104
+ "eval_combined_score": 0.7633269720101782,
105
+ "eval_f1": 0.818320610687023,
106
+ "eval_loss": 0.6184039115905762,
107
+ "eval_runtime": 0.5141,
108
+ "eval_samples_per_second": 793.682,
109
+ "eval_steps_per_second": 3.891,
110
+ "step": 90
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "learning_rate": 4.3e-05,
115
+ "loss": 0.5426,
116
+ "step": 105
117
+ },
118
+ {
119
+ "epoch": 7.0,
120
+ "eval_accuracy": 0.6862745098039216,
121
+ "eval_combined_score": 0.7431372549019608,
122
+ "eval_f1": 0.7999999999999999,
123
+ "eval_loss": 0.6050820350646973,
124
+ "eval_runtime": 0.5141,
125
+ "eval_samples_per_second": 793.592,
126
+ "eval_steps_per_second": 3.89,
127
+ "step": 105
128
+ },
129
+ {
130
+ "epoch": 8.0,
131
+ "learning_rate": 4.2e-05,
132
+ "loss": 0.4819,
133
+ "step": 120
134
+ },
135
+ {
136
+ "epoch": 8.0,
137
+ "eval_accuracy": 0.6936274509803921,
138
+ "eval_combined_score": 0.7477645971225257,
139
+ "eval_f1": 0.8019017432646594,
140
+ "eval_loss": 0.6560007929801941,
141
+ "eval_runtime": 0.515,
142
+ "eval_samples_per_second": 792.192,
143
+ "eval_steps_per_second": 3.883,
144
+ "step": 120
145
+ },
146
+ {
147
+ "epoch": 9.0,
148
+ "learning_rate": 4.1e-05,
149
+ "loss": 0.4279,
150
+ "step": 135
151
+ },
152
+ {
153
+ "epoch": 9.0,
154
+ "eval_accuracy": 0.6887254901960784,
155
+ "eval_combined_score": 0.7282749937269242,
156
+ "eval_f1": 0.7678244972577698,
157
+ "eval_loss": 0.6672889590263367,
158
+ "eval_runtime": 0.5142,
159
+ "eval_samples_per_second": 793.515,
160
+ "eval_steps_per_second": 3.89,
161
+ "step": 135
162
+ },
163
+ {
164
+ "epoch": 10.0,
165
+ "learning_rate": 4e-05,
166
+ "loss": 0.3374,
167
+ "step": 150
168
+ },
169
+ {
170
+ "epoch": 10.0,
171
+ "eval_accuracy": 0.6862745098039216,
172
+ "eval_combined_score": 0.7382192221150756,
173
+ "eval_f1": 0.7901639344262296,
174
+ "eval_loss": 0.8091686367988586,
175
+ "eval_runtime": 0.5155,
176
+ "eval_samples_per_second": 791.402,
177
+ "eval_steps_per_second": 3.879,
178
+ "step": 150
179
+ },
180
+ {
181
+ "epoch": 11.0,
182
+ "learning_rate": 3.9000000000000006e-05,
183
+ "loss": 0.2789,
184
+ "step": 165
185
+ },
186
+ {
187
+ "epoch": 11.0,
188
+ "eval_accuracy": 0.6887254901960784,
189
+ "eval_combined_score": 0.741110712577714,
190
+ "eval_f1": 0.7934959349593496,
191
+ "eval_loss": 0.9342193603515625,
192
+ "eval_runtime": 0.5139,
193
+ "eval_samples_per_second": 793.922,
194
+ "eval_steps_per_second": 3.892,
195
+ "step": 165
196
+ },
197
+ {
198
+ "epoch": 12.0,
199
+ "learning_rate": 3.8e-05,
200
+ "loss": 0.2216,
201
+ "step": 180
202
+ },
203
+ {
204
+ "epoch": 12.0,
205
+ "eval_accuracy": 0.6838235294117647,
206
+ "eval_combined_score": 0.7324041246379707,
207
+ "eval_f1": 0.7809847198641766,
208
+ "eval_loss": 0.9707943201065063,
209
+ "eval_runtime": 0.5142,
210
+ "eval_samples_per_second": 793.529,
211
+ "eval_steps_per_second": 3.89,
212
+ "step": 180
213
+ },
214
+ {
215
+ "epoch": 12.0,
216
+ "step": 180,
217
+ "total_flos": 5559706315653120.0,
218
+ "train_loss": 0.4964691546228197,
219
+ "train_runtime": 203.7797,
220
+ "train_samples_per_second": 899.991,
221
+ "train_steps_per_second": 3.68
222
+ }
223
+ ],
224
+ "max_steps": 750,
225
+ "num_train_epochs": 50,
226
+ "total_flos": 5559706315653120.0,
227
+ "trial_name": null,
228
+ "trial_params": null
229
+ }