End of training
Browse files- README.md +6 -4
- all_results.json +14 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1685344455.serv-9225.2840720.8 +3 -0
- train_results.json +8 -0
- trainer_state.json +265 -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: qnli
|
18 |
split: validation
|
@@ -20,7 +22,7 @@ model-index:
|
|
20 |
metrics:
|
21 |
- name: Accuracy
|
22 |
type: accuracy
|
23 |
-
value: 0.
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
# hBERTv1_no_pretrain_qnli
|
30 |
|
31 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on the
|
32 |
It achieves the following results on the evaluation set:
|
33 |
- Loss: 0.6931
|
34 |
-
- Accuracy: 0.
|
35 |
|
36 |
## Model description
|
37 |
|
|
|
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 QNLI
|
18 |
type: glue
|
19 |
config: qnli
|
20 |
split: validation
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.5053999633900788
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# hBERTv1_no_pretrain_qnli
|
32 |
|
33 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE QNLI dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
- Loss: 0.6931
|
36 |
+
- Accuracy: 0.5054
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 16.0,
|
3 |
+
"eval_accuracy": 0.5053999633900788,
|
4 |
+
"eval_loss": 0.6930651664733887,
|
5 |
+
"eval_runtime": 9.4904,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 575.636,
|
8 |
+
"eval_steps_per_second": 4.531,
|
9 |
+
"train_loss": 0.694585192334521,
|
10 |
+
"train_runtime": 8903.1517,
|
11 |
+
"train_samples": 104743,
|
12 |
+
"train_samples_per_second": 588.236,
|
13 |
+
"train_steps_per_second": 4.599
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 16.0,
|
3 |
+
"eval_accuracy": 0.5053999633900788,
|
4 |
+
"eval_loss": 0.6930651664733887,
|
5 |
+
"eval_runtime": 9.4904,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 575.636,
|
8 |
+
"eval_steps_per_second": 4.531
|
9 |
+
}
|
logs/events.out.tfevents.1685344455.serv-9225.2840720.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e03bc5b2c7dc178267024ff32ed8e94971fcb550ca6b2e6b8359a16027826a9a
|
3 |
+
size 363
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 16.0,
|
3 |
+
"train_loss": 0.694585192334521,
|
4 |
+
"train_runtime": 8903.1517,
|
5 |
+
"train_samples": 104743,
|
6 |
+
"train_samples_per_second": 588.236,
|
7 |
+
"train_steps_per_second": 4.599
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6930651664733887,
|
3 |
+
"best_model_checkpoint": "hBERTv1_no_pretrain_qnli/checkpoint-9009",
|
4 |
+
"epoch": 16.0,
|
5 |
+
"global_step": 13104,
|
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": 0.00049002442002442,
|
13 |
+
"loss": 0.715,
|
14 |
+
"step": 819
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.4946000366099213,
|
19 |
+
"eval_loss": 0.6931389570236206,
|
20 |
+
"eval_runtime": 9.5675,
|
21 |
+
"eval_samples_per_second": 570.995,
|
22 |
+
"eval_steps_per_second": 4.494,
|
23 |
+
"step": 819
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 0.00048002442002442004,
|
28 |
+
"loss": 0.6932,
|
29 |
+
"step": 1638
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.4946000366099213,
|
34 |
+
"eval_loss": 0.6931495070457458,
|
35 |
+
"eval_runtime": 9.5694,
|
36 |
+
"eval_samples_per_second": 570.88,
|
37 |
+
"eval_steps_per_second": 4.493,
|
38 |
+
"step": 1638
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 0.00047002442002442,
|
43 |
+
"loss": 0.6936,
|
44 |
+
"step": 2457
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.5053999633900788,
|
49 |
+
"eval_loss": 0.6931167840957642,
|
50 |
+
"eval_runtime": 9.5644,
|
51 |
+
"eval_samples_per_second": 571.18,
|
52 |
+
"eval_steps_per_second": 4.496,
|
53 |
+
"step": 2457
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 0.00046002442002442004,
|
58 |
+
"loss": 0.6932,
|
59 |
+
"step": 3276
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.4946000366099213,
|
64 |
+
"eval_loss": 0.6931969523429871,
|
65 |
+
"eval_runtime": 9.5713,
|
66 |
+
"eval_samples_per_second": 570.77,
|
67 |
+
"eval_steps_per_second": 4.493,
|
68 |
+
"step": 3276
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 0.00045002442002442,
|
73 |
+
"loss": 0.6932,
|
74 |
+
"step": 4095
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_accuracy": 0.5053999633900788,
|
79 |
+
"eval_loss": 0.6933488249778748,
|
80 |
+
"eval_runtime": 9.573,
|
81 |
+
"eval_samples_per_second": 570.669,
|
82 |
+
"eval_steps_per_second": 4.492,
|
83 |
+
"step": 4095
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 0.00044002442002442004,
|
88 |
+
"loss": 0.6932,
|
89 |
+
"step": 4914
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_accuracy": 0.5053999633900788,
|
94 |
+
"eval_loss": 0.6930915117263794,
|
95 |
+
"eval_runtime": 9.5567,
|
96 |
+
"eval_samples_per_second": 571.639,
|
97 |
+
"eval_steps_per_second": 4.499,
|
98 |
+
"step": 4914
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"learning_rate": 0.00043002442002442007,
|
103 |
+
"loss": 0.6932,
|
104 |
+
"step": 5733
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"eval_accuracy": 0.5053999633900788,
|
109 |
+
"eval_loss": 0.6931073069572449,
|
110 |
+
"eval_runtime": 9.5808,
|
111 |
+
"eval_samples_per_second": 570.202,
|
112 |
+
"eval_steps_per_second": 4.488,
|
113 |
+
"step": 5733
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 8.0,
|
117 |
+
"learning_rate": 0.00042002442002442005,
|
118 |
+
"loss": 0.6932,
|
119 |
+
"step": 6552
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 8.0,
|
123 |
+
"eval_accuracy": 0.5053999633900788,
|
124 |
+
"eval_loss": 0.6930862069129944,
|
125 |
+
"eval_runtime": 9.5904,
|
126 |
+
"eval_samples_per_second": 569.63,
|
127 |
+
"eval_steps_per_second": 4.484,
|
128 |
+
"step": 6552
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.0,
|
132 |
+
"learning_rate": 0.00041003663003663003,
|
133 |
+
"loss": 0.6935,
|
134 |
+
"step": 7371
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 9.0,
|
138 |
+
"eval_accuracy": 0.5053999633900788,
|
139 |
+
"eval_loss": 0.693478524684906,
|
140 |
+
"eval_runtime": 9.5344,
|
141 |
+
"eval_samples_per_second": 572.981,
|
142 |
+
"eval_steps_per_second": 4.51,
|
143 |
+
"step": 7371
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 10.0,
|
147 |
+
"learning_rate": 0.00040003663003663006,
|
148 |
+
"loss": 0.6932,
|
149 |
+
"step": 8190
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 10.0,
|
153 |
+
"eval_accuracy": 0.5053999633900788,
|
154 |
+
"eval_loss": 0.6930915117263794,
|
155 |
+
"eval_runtime": 9.5321,
|
156 |
+
"eval_samples_per_second": 573.116,
|
157 |
+
"eval_steps_per_second": 4.511,
|
158 |
+
"step": 8190
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 11.0,
|
162 |
+
"learning_rate": 0.00039003663003663004,
|
163 |
+
"loss": 0.6932,
|
164 |
+
"step": 9009
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 11.0,
|
168 |
+
"eval_accuracy": 0.5053999633900788,
|
169 |
+
"eval_loss": 0.6930651664733887,
|
170 |
+
"eval_runtime": 9.5448,
|
171 |
+
"eval_samples_per_second": 572.352,
|
172 |
+
"eval_steps_per_second": 4.505,
|
173 |
+
"step": 9009
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 12.0,
|
177 |
+
"learning_rate": 0.00038004884004884,
|
178 |
+
"loss": 0.6932,
|
179 |
+
"step": 9828
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 12.0,
|
183 |
+
"eval_accuracy": 0.5053999633900788,
|
184 |
+
"eval_loss": 0.6931073069572449,
|
185 |
+
"eval_runtime": 9.5697,
|
186 |
+
"eval_samples_per_second": 570.866,
|
187 |
+
"eval_steps_per_second": 4.493,
|
188 |
+
"step": 9828
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 13.0,
|
192 |
+
"learning_rate": 0.00037004884004884005,
|
193 |
+
"loss": 0.6932,
|
194 |
+
"step": 10647
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 13.0,
|
198 |
+
"eval_accuracy": 0.5053999633900788,
|
199 |
+
"eval_loss": 0.6931073069572449,
|
200 |
+
"eval_runtime": 9.5909,
|
201 |
+
"eval_samples_per_second": 569.603,
|
202 |
+
"eval_steps_per_second": 4.483,
|
203 |
+
"step": 10647
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 14.0,
|
207 |
+
"learning_rate": 0.00036004884004884,
|
208 |
+
"loss": 0.6932,
|
209 |
+
"step": 11466
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 14.0,
|
213 |
+
"eval_accuracy": 0.4946000366099213,
|
214 |
+
"eval_loss": 0.6931231617927551,
|
215 |
+
"eval_runtime": 9.5446,
|
216 |
+
"eval_samples_per_second": 572.363,
|
217 |
+
"eval_steps_per_second": 4.505,
|
218 |
+
"step": 11466
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 15.0,
|
222 |
+
"learning_rate": 0.00035004884004884005,
|
223 |
+
"loss": 0.6932,
|
224 |
+
"step": 12285
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 15.0,
|
228 |
+
"eval_accuracy": 0.4946000366099213,
|
229 |
+
"eval_loss": 0.693396270275116,
|
230 |
+
"eval_runtime": 9.5573,
|
231 |
+
"eval_samples_per_second": 571.603,
|
232 |
+
"eval_steps_per_second": 4.499,
|
233 |
+
"step": 12285
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 16.0,
|
237 |
+
"learning_rate": 0.0003400488400488401,
|
238 |
+
"loss": 0.6932,
|
239 |
+
"step": 13104
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 16.0,
|
243 |
+
"eval_accuracy": 0.4946000366099213,
|
244 |
+
"eval_loss": 0.6931284070014954,
|
245 |
+
"eval_runtime": 9.5555,
|
246 |
+
"eval_samples_per_second": 571.71,
|
247 |
+
"eval_steps_per_second": 4.5,
|
248 |
+
"step": 13104
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 16.0,
|
252 |
+
"step": 13104,
|
253 |
+
"total_flos": 2.481936015514665e+17,
|
254 |
+
"train_loss": 0.694585192334521,
|
255 |
+
"train_runtime": 8903.1517,
|
256 |
+
"train_samples_per_second": 588.236,
|
257 |
+
"train_steps_per_second": 4.599
|
258 |
+
}
|
259 |
+
],
|
260 |
+
"max_steps": 40950,
|
261 |
+
"num_train_epochs": 50,
|
262 |
+
"total_flos": 2.481936015514665e+17,
|
263 |
+
"trial_name": null,
|
264 |
+
"trial_params": null
|
265 |
+
}
|