End of training
Browse files- README.md +9 -7
- all_results.json +16 -0
- eval_results.json +11 -0
- logs/events.out.tfevents.1677756168.serv-9223.249682.20 +3 -0
- train_results.json +8 -0
- trainer_state.json +246 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
@@ -12,7 +14,7 @@ model-index:
|
|
12 |
name: Text Classification
|
13 |
type: text-classification
|
14 |
dataset:
|
15 |
-
name:
|
16 |
type: glue
|
17 |
config: stsb
|
18 |
split: validation
|
@@ -20,7 +22,7 @@ model-index:
|
|
20 |
metrics:
|
21 |
- name: Spearmanr
|
22 |
type: spearmanr
|
23 |
-
value: 0.
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -28,12 +30,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
# hBERTv1_stsb
|
30 |
|
31 |
-
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
|
32 |
It achieves the following results on the evaluation set:
|
33 |
-
- Loss: 1.
|
34 |
-
- Pearson: 0.
|
35 |
-
- Spearmanr: 0.
|
36 |
-
- Combined Score: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
14 |
name: Text Classification
|
15 |
type: text-classification
|
16 |
dataset:
|
17 |
+
name: GLUE STSB
|
18 |
type: glue
|
19 |
config: stsb
|
20 |
split: validation
|
|
|
22 |
metrics:
|
23 |
- name: Spearmanr
|
24 |
type: spearmanr
|
25 |
+
value: 0.7155715863961268
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# hBERTv1_stsb
|
32 |
|
33 |
+
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 STSB dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.1154
|
36 |
+
- Pearson: 0.7159
|
37 |
+
- Spearmanr: 0.7156
|
38 |
+
- Combined Score: 0.7157
|
39 |
|
40 |
## Model description
|
41 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 13.0,
|
3 |
+
"eval_combined_score": 0.7157490703420486,
|
4 |
+
"eval_loss": 1.1154277324676514,
|
5 |
+
"eval_pearson": 0.7159265542879704,
|
6 |
+
"eval_runtime": 1.917,
|
7 |
+
"eval_samples": 1500,
|
8 |
+
"eval_samples_per_second": 782.476,
|
9 |
+
"eval_spearmanr": 0.7155715863961268,
|
10 |
+
"eval_steps_per_second": 3.13,
|
11 |
+
"train_loss": 1.0456982304818654,
|
12 |
+
"train_runtime": 396.42,
|
13 |
+
"train_samples": 5749,
|
14 |
+
"train_samples_per_second": 725.115,
|
15 |
+
"train_steps_per_second": 2.901
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 13.0,
|
3 |
+
"eval_combined_score": 0.7157490703420486,
|
4 |
+
"eval_loss": 1.1154277324676514,
|
5 |
+
"eval_pearson": 0.7159265542879704,
|
6 |
+
"eval_runtime": 1.917,
|
7 |
+
"eval_samples": 1500,
|
8 |
+
"eval_samples_per_second": 782.476,
|
9 |
+
"eval_spearmanr": 0.7155715863961268,
|
10 |
+
"eval_steps_per_second": 3.13
|
11 |
+
}
|
logs/events.out.tfevents.1677756168.serv-9223.249682.20
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc888a54b43ca33217531aa62a6610a9aabf41e433d1abf72452883ab4f6bb4d
|
3 |
+
size 473
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 13.0,
|
3 |
+
"train_loss": 1.0456982304818654,
|
4 |
+
"train_runtime": 396.42,
|
5 |
+
"train_samples": 5749,
|
6 |
+
"train_samples_per_second": 725.115,
|
7 |
+
"train_steps_per_second": 2.901
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.1154277324676514,
|
3 |
+
"best_model_checkpoint": "hBERTv1_stsb/checkpoint-184",
|
4 |
+
"epoch": 13.0,
|
5 |
+
"global_step": 299,
|
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": 4.9173913043478265e-05,
|
13 |
+
"loss": 4.0796,
|
14 |
+
"step": 23
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_combined_score": 0.06538801707026302,
|
19 |
+
"eval_loss": 2.301738977432251,
|
20 |
+
"eval_pearson": 0.07610945358839591,
|
21 |
+
"eval_runtime": 1.9306,
|
22 |
+
"eval_samples_per_second": 776.964,
|
23 |
+
"eval_spearmanr": 0.05466658055213014,
|
24 |
+
"eval_steps_per_second": 3.108,
|
25 |
+
"step": 23
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 4.817391304347826e-05,
|
30 |
+
"loss": 2.0746,
|
31 |
+
"step": 46
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_combined_score": 0.08111168068438418,
|
36 |
+
"eval_loss": 2.618116855621338,
|
37 |
+
"eval_pearson": 0.08503304117233579,
|
38 |
+
"eval_runtime": 1.9212,
|
39 |
+
"eval_samples_per_second": 780.765,
|
40 |
+
"eval_spearmanr": 0.07719032019643259,
|
41 |
+
"eval_steps_per_second": 3.123,
|
42 |
+
"step": 46
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"learning_rate": 4.7173913043478264e-05,
|
47 |
+
"loss": 1.9142,
|
48 |
+
"step": 69
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_combined_score": 0.18653024063604068,
|
53 |
+
"eval_loss": 2.29634952545166,
|
54 |
+
"eval_pearson": 0.1878248631380315,
|
55 |
+
"eval_runtime": 1.9303,
|
56 |
+
"eval_samples_per_second": 777.095,
|
57 |
+
"eval_spearmanr": 0.18523561813404985,
|
58 |
+
"eval_steps_per_second": 3.108,
|
59 |
+
"step": 69
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"learning_rate": 4.617391304347826e-05,
|
64 |
+
"loss": 1.6883,
|
65 |
+
"step": 92
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_combined_score": 0.47587247941695476,
|
70 |
+
"eval_loss": 2.18662691116333,
|
71 |
+
"eval_pearson": 0.4740108701640409,
|
72 |
+
"eval_runtime": 1.9255,
|
73 |
+
"eval_samples_per_second": 779.032,
|
74 |
+
"eval_spearmanr": 0.4777340886698686,
|
75 |
+
"eval_steps_per_second": 3.116,
|
76 |
+
"step": 92
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.0,
|
80 |
+
"learning_rate": 4.517391304347826e-05,
|
81 |
+
"loss": 1.1166,
|
82 |
+
"step": 115
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 5.0,
|
86 |
+
"eval_combined_score": 0.6384359218484894,
|
87 |
+
"eval_loss": 1.9366592168807983,
|
88 |
+
"eval_pearson": 0.6318718203898596,
|
89 |
+
"eval_runtime": 1.9201,
|
90 |
+
"eval_samples_per_second": 781.199,
|
91 |
+
"eval_spearmanr": 0.6450000233071193,
|
92 |
+
"eval_steps_per_second": 3.125,
|
93 |
+
"step": 115
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 6.0,
|
97 |
+
"learning_rate": 4.4173913043478265e-05,
|
98 |
+
"loss": 0.7598,
|
99 |
+
"step": 138
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 6.0,
|
103 |
+
"eval_combined_score": 0.684468485485146,
|
104 |
+
"eval_loss": 1.4188166856765747,
|
105 |
+
"eval_pearson": 0.6801003203440246,
|
106 |
+
"eval_runtime": 1.9182,
|
107 |
+
"eval_samples_per_second": 781.975,
|
108 |
+
"eval_spearmanr": 0.6888366506262675,
|
109 |
+
"eval_steps_per_second": 3.128,
|
110 |
+
"step": 138
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"learning_rate": 4.317391304347827e-05,
|
115 |
+
"loss": 0.5453,
|
116 |
+
"step": 161
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 7.0,
|
120 |
+
"eval_combined_score": 0.6994286994310785,
|
121 |
+
"eval_loss": 1.2720448970794678,
|
122 |
+
"eval_pearson": 0.6987976257082615,
|
123 |
+
"eval_runtime": 1.9166,
|
124 |
+
"eval_samples_per_second": 782.626,
|
125 |
+
"eval_spearmanr": 0.7000597731538957,
|
126 |
+
"eval_steps_per_second": 3.131,
|
127 |
+
"step": 161
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 8.0,
|
131 |
+
"learning_rate": 4.2173913043478264e-05,
|
132 |
+
"loss": 0.3705,
|
133 |
+
"step": 184
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 8.0,
|
137 |
+
"eval_combined_score": 0.7157490703420486,
|
138 |
+
"eval_loss": 1.1154277324676514,
|
139 |
+
"eval_pearson": 0.7159265542879704,
|
140 |
+
"eval_runtime": 1.9188,
|
141 |
+
"eval_samples_per_second": 781.732,
|
142 |
+
"eval_spearmanr": 0.7155715863961268,
|
143 |
+
"eval_steps_per_second": 3.127,
|
144 |
+
"step": 184
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 9.0,
|
148 |
+
"learning_rate": 4.117391304347826e-05,
|
149 |
+
"loss": 0.2976,
|
150 |
+
"step": 207
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 9.0,
|
154 |
+
"eval_combined_score": 0.6780274177666261,
|
155 |
+
"eval_loss": 1.6889050006866455,
|
156 |
+
"eval_pearson": 0.6753593078005974,
|
157 |
+
"eval_runtime": 1.9186,
|
158 |
+
"eval_samples_per_second": 781.809,
|
159 |
+
"eval_spearmanr": 0.680695527732655,
|
160 |
+
"eval_steps_per_second": 3.127,
|
161 |
+
"step": 207
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 10.0,
|
165 |
+
"learning_rate": 4.017391304347826e-05,
|
166 |
+
"loss": 0.2272,
|
167 |
+
"step": 230
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 10.0,
|
171 |
+
"eval_combined_score": 0.691436341571948,
|
172 |
+
"eval_loss": 1.3627489805221558,
|
173 |
+
"eval_pearson": 0.692937129271751,
|
174 |
+
"eval_runtime": 1.9208,
|
175 |
+
"eval_samples_per_second": 780.912,
|
176 |
+
"eval_spearmanr": 0.6899355538721449,
|
177 |
+
"eval_steps_per_second": 3.124,
|
178 |
+
"step": 230
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 11.0,
|
182 |
+
"learning_rate": 3.917391304347826e-05,
|
183 |
+
"loss": 0.1966,
|
184 |
+
"step": 253
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 11.0,
|
188 |
+
"eval_combined_score": 0.7181059118945743,
|
189 |
+
"eval_loss": 1.127779245376587,
|
190 |
+
"eval_pearson": 0.7195047805569822,
|
191 |
+
"eval_runtime": 1.9246,
|
192 |
+
"eval_samples_per_second": 779.363,
|
193 |
+
"eval_spearmanr": 0.7167070432321663,
|
194 |
+
"eval_steps_per_second": 3.117,
|
195 |
+
"step": 253
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 12.0,
|
199 |
+
"learning_rate": 3.817391304347827e-05,
|
200 |
+
"loss": 0.1708,
|
201 |
+
"step": 276
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 12.0,
|
205 |
+
"eval_combined_score": 0.7167948198834158,
|
206 |
+
"eval_loss": 1.3475854396820068,
|
207 |
+
"eval_pearson": 0.717074708327728,
|
208 |
+
"eval_runtime": 1.9199,
|
209 |
+
"eval_samples_per_second": 781.302,
|
210 |
+
"eval_spearmanr": 0.7165149314391035,
|
211 |
+
"eval_steps_per_second": 3.125,
|
212 |
+
"step": 276
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 13.0,
|
216 |
+
"learning_rate": 3.7173913043478264e-05,
|
217 |
+
"loss": 0.1529,
|
218 |
+
"step": 299
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 13.0,
|
222 |
+
"eval_combined_score": 0.6961706036044664,
|
223 |
+
"eval_loss": 1.26143217086792,
|
224 |
+
"eval_pearson": 0.6981627569979957,
|
225 |
+
"eval_runtime": 1.9277,
|
226 |
+
"eval_samples_per_second": 778.118,
|
227 |
+
"eval_spearmanr": 0.6941784502109372,
|
228 |
+
"eval_steps_per_second": 3.112,
|
229 |
+
"step": 299
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 13.0,
|
233 |
+
"step": 299,
|
234 |
+
"total_flos": 9440019617939456.0,
|
235 |
+
"train_loss": 1.0456982304818654,
|
236 |
+
"train_runtime": 396.42,
|
237 |
+
"train_samples_per_second": 725.115,
|
238 |
+
"train_steps_per_second": 2.901
|
239 |
+
}
|
240 |
+
],
|
241 |
+
"max_steps": 1150,
|
242 |
+
"num_train_epochs": 50,
|
243 |
+
"total_flos": 9440019617939456.0,
|
244 |
+
"trial_name": null,
|
245 |
+
"trial_params": null
|
246 |
+
}
|