End of training
Browse files- README.md +10 -8
- all_results.json +16 -0
- eval_results.json +11 -0
- logs/events.out.tfevents.1674623718.garda.1292005.5 +3 -0
- train_results.json +8 -0
- trainer_state.json +246 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
@@ -14,7 +16,7 @@ model-index:
|
|
14 |
name: Text Classification
|
15 |
type: text-classification
|
16 |
dataset:
|
17 |
-
name:
|
18 |
type: glue
|
19 |
config: mrpc
|
20 |
split: validation
|
@@ -22,10 +24,10 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
- name: F1
|
27 |
type: f1
|
28 |
-
value: 0.
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -33,12 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
33 |
|
34 |
# mobilebert_sa_GLUE_Experiment_mrpc_256
|
35 |
|
36 |
-
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
- Loss:
|
39 |
-
- Accuracy: 0.
|
40 |
-
- F1: 0.
|
41 |
-
- Combined Score: 0.
|
42 |
|
43 |
## Model description
|
44 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
16 |
name: Text Classification
|
17 |
type: text-classification
|
18 |
dataset:
|
19 |
+
name: GLUE MRPC
|
20 |
type: glue
|
21 |
config: mrpc
|
22 |
split: validation
|
|
|
24 |
metrics:
|
25 |
- name: Accuracy
|
26 |
type: accuracy
|
27 |
+
value: 0.6911764705882353
|
28 |
- name: F1
|
29 |
type: f1
|
30 |
+
value: 0.7947882736156351
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
# mobilebert_sa_GLUE_Experiment_mrpc_256
|
37 |
|
38 |
+
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE MRPC dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 0.6111
|
41 |
+
- Accuracy: 0.6912
|
42 |
+
- F1: 0.7948
|
43 |
+
- Combined Score: 0.7430
|
44 |
|
45 |
## Model description
|
46 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 13.0,
|
3 |
+
"eval_accuracy": 0.6911764705882353,
|
4 |
+
"eval_combined_score": 0.7429823721019352,
|
5 |
+
"eval_f1": 0.7947882736156351,
|
6 |
+
"eval_loss": 0.611058235168457,
|
7 |
+
"eval_runtime": 0.9419,
|
8 |
+
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 433.161,
|
10 |
+
"eval_steps_per_second": 4.247,
|
11 |
+
"train_loss": 0.5084376322495843,
|
12 |
+
"train_runtime": 493.204,
|
13 |
+
"train_samples": 3668,
|
14 |
+
"train_samples_per_second": 371.854,
|
15 |
+
"train_steps_per_second": 2.94
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 13.0,
|
3 |
+
"eval_accuracy": 0.6911764705882353,
|
4 |
+
"eval_combined_score": 0.7429823721019352,
|
5 |
+
"eval_f1": 0.7947882736156351,
|
6 |
+
"eval_loss": 0.611058235168457,
|
7 |
+
"eval_runtime": 0.9419,
|
8 |
+
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 433.161,
|
10 |
+
"eval_steps_per_second": 4.247
|
11 |
+
}
|
logs/events.out.tfevents.1674623718.garda.1292005.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64c8ccb267a25b8e7687fdaaa3cb919ce3808a5cf8538b95aec97990953f33ec
|
3 |
+
size 467
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 13.0,
|
3 |
+
"train_loss": 0.5084376322495843,
|
4 |
+
"train_runtime": 493.204,
|
5 |
+
"train_samples": 3668,
|
6 |
+
"train_samples_per_second": 371.854,
|
7 |
+
"train_steps_per_second": 2.94
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.611058235168457,
|
3 |
+
"best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_mrpc_256/checkpoint-232",
|
4 |
+
"epoch": 13.0,
|
5 |
+
"global_step": 377,
|
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": 0.6431,
|
14 |
+
"step": 29
|
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": 0.626089870929718,
|
22 |
+
"eval_runtime": 0.9456,
|
23 |
+
"eval_samples_per_second": 431.492,
|
24 |
+
"eval_steps_per_second": 4.23,
|
25 |
+
"step": 29
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 4.8e-05,
|
30 |
+
"loss": 0.6296,
|
31 |
+
"step": 58
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.6838235294117647,
|
36 |
+
"eval_combined_score": 0.7480253018237863,
|
37 |
+
"eval_f1": 0.8122270742358079,
|
38 |
+
"eval_loss": 0.6234638094902039,
|
39 |
+
"eval_runtime": 0.9411,
|
40 |
+
"eval_samples_per_second": 433.528,
|
41 |
+
"eval_steps_per_second": 4.25,
|
42 |
+
"step": 58
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"learning_rate": 4.7e-05,
|
47 |
+
"loss": 0.6306,
|
48 |
+
"step": 87
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.6838235294117647,
|
53 |
+
"eval_combined_score": 0.7480253018237863,
|
54 |
+
"eval_f1": 0.8122270742358079,
|
55 |
+
"eval_loss": 0.6237208247184753,
|
56 |
+
"eval_runtime": 0.937,
|
57 |
+
"eval_samples_per_second": 435.41,
|
58 |
+
"eval_steps_per_second": 4.269,
|
59 |
+
"step": 87
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"learning_rate": 4.600000000000001e-05,
|
64 |
+
"loss": 0.6297,
|
65 |
+
"step": 116
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_accuracy": 0.6838235294117647,
|
70 |
+
"eval_combined_score": 0.7480253018237863,
|
71 |
+
"eval_f1": 0.8122270742358079,
|
72 |
+
"eval_loss": 0.6237556338310242,
|
73 |
+
"eval_runtime": 0.9403,
|
74 |
+
"eval_samples_per_second": 433.895,
|
75 |
+
"eval_steps_per_second": 4.254,
|
76 |
+
"step": 116
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.0,
|
80 |
+
"learning_rate": 4.5e-05,
|
81 |
+
"loss": 0.6276,
|
82 |
+
"step": 145
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 5.0,
|
86 |
+
"eval_accuracy": 0.6838235294117647,
|
87 |
+
"eval_combined_score": 0.7480253018237863,
|
88 |
+
"eval_f1": 0.8122270742358079,
|
89 |
+
"eval_loss": 0.6206657290458679,
|
90 |
+
"eval_runtime": 0.9389,
|
91 |
+
"eval_samples_per_second": 434.555,
|
92 |
+
"eval_steps_per_second": 4.26,
|
93 |
+
"step": 145
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 6.0,
|
97 |
+
"learning_rate": 4.4000000000000006e-05,
|
98 |
+
"loss": 0.6197,
|
99 |
+
"step": 174
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 6.0,
|
103 |
+
"eval_accuracy": 0.6838235294117647,
|
104 |
+
"eval_combined_score": 0.7480253018237863,
|
105 |
+
"eval_f1": 0.8122270742358079,
|
106 |
+
"eval_loss": 0.6212654709815979,
|
107 |
+
"eval_runtime": 0.9398,
|
108 |
+
"eval_samples_per_second": 434.126,
|
109 |
+
"eval_steps_per_second": 4.256,
|
110 |
+
"step": 174
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"learning_rate": 4.3e-05,
|
115 |
+
"loss": 0.6065,
|
116 |
+
"step": 203
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 7.0,
|
120 |
+
"eval_accuracy": 0.6911764705882353,
|
121 |
+
"eval_combined_score": 0.7477621483375959,
|
122 |
+
"eval_f1": 0.8043478260869565,
|
123 |
+
"eval_loss": 0.6284083724021912,
|
124 |
+
"eval_runtime": 0.9178,
|
125 |
+
"eval_samples_per_second": 444.537,
|
126 |
+
"eval_steps_per_second": 4.358,
|
127 |
+
"step": 203
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 8.0,
|
131 |
+
"learning_rate": 4.2e-05,
|
132 |
+
"loss": 0.5258,
|
133 |
+
"step": 232
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 8.0,
|
137 |
+
"eval_accuracy": 0.6911764705882353,
|
138 |
+
"eval_combined_score": 0.7429823721019352,
|
139 |
+
"eval_f1": 0.7947882736156351,
|
140 |
+
"eval_loss": 0.611058235168457,
|
141 |
+
"eval_runtime": 0.9172,
|
142 |
+
"eval_samples_per_second": 444.815,
|
143 |
+
"eval_steps_per_second": 4.361,
|
144 |
+
"step": 232
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 9.0,
|
148 |
+
"learning_rate": 4.1e-05,
|
149 |
+
"loss": 0.4596,
|
150 |
+
"step": 261
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 9.0,
|
154 |
+
"eval_accuracy": 0.7034313725490197,
|
155 |
+
"eval_combined_score": 0.7542921758075211,
|
156 |
+
"eval_f1": 0.8051529790660225,
|
157 |
+
"eval_loss": 0.6506468057632446,
|
158 |
+
"eval_runtime": 0.9479,
|
159 |
+
"eval_samples_per_second": 430.438,
|
160 |
+
"eval_steps_per_second": 4.22,
|
161 |
+
"step": 261
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 10.0,
|
165 |
+
"learning_rate": 4e-05,
|
166 |
+
"loss": 0.3953,
|
167 |
+
"step": 290
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 10.0,
|
171 |
+
"eval_accuracy": 0.7034313725490197,
|
172 |
+
"eval_combined_score": 0.7482968828557064,
|
173 |
+
"eval_f1": 0.7931623931623932,
|
174 |
+
"eval_loss": 0.7271472811698914,
|
175 |
+
"eval_runtime": 0.9357,
|
176 |
+
"eval_samples_per_second": 436.055,
|
177 |
+
"eval_steps_per_second": 4.275,
|
178 |
+
"step": 290
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 11.0,
|
182 |
+
"learning_rate": 3.9000000000000006e-05,
|
183 |
+
"loss": 0.3426,
|
184 |
+
"step": 319
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 11.0,
|
188 |
+
"eval_accuracy": 0.6740196078431373,
|
189 |
+
"eval_combined_score": 0.7140892863614947,
|
190 |
+
"eval_f1": 0.7541589648798522,
|
191 |
+
"eval_loss": 0.9509055018424988,
|
192 |
+
"eval_runtime": 0.944,
|
193 |
+
"eval_samples_per_second": 432.196,
|
194 |
+
"eval_steps_per_second": 4.237,
|
195 |
+
"step": 319
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 12.0,
|
199 |
+
"learning_rate": 3.8e-05,
|
200 |
+
"loss": 0.2821,
|
201 |
+
"step": 348
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 12.0,
|
205 |
+
"eval_accuracy": 0.6862745098039216,
|
206 |
+
"eval_combined_score": 0.7335482138060704,
|
207 |
+
"eval_f1": 0.7808219178082192,
|
208 |
+
"eval_loss": 1.0021162033081055,
|
209 |
+
"eval_runtime": 0.9425,
|
210 |
+
"eval_samples_per_second": 432.902,
|
211 |
+
"eval_steps_per_second": 4.244,
|
212 |
+
"step": 348
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 13.0,
|
216 |
+
"learning_rate": 3.7e-05,
|
217 |
+
"loss": 0.2177,
|
218 |
+
"step": 377
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 13.0,
|
222 |
+
"eval_accuracy": 0.6691176470588235,
|
223 |
+
"eval_combined_score": 0.7183798218082413,
|
224 |
+
"eval_f1": 0.7676419965576592,
|
225 |
+
"eval_loss": 1.0359125137329102,
|
226 |
+
"eval_runtime": 0.9408,
|
227 |
+
"eval_samples_per_second": 433.683,
|
228 |
+
"eval_steps_per_second": 4.252,
|
229 |
+
"step": 377
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 13.0,
|
233 |
+
"step": 377,
|
234 |
+
"total_flos": 1256051433275392.0,
|
235 |
+
"train_loss": 0.5084376322495843,
|
236 |
+
"train_runtime": 493.204,
|
237 |
+
"train_samples_per_second": 371.854,
|
238 |
+
"train_steps_per_second": 2.94
|
239 |
+
}
|
240 |
+
],
|
241 |
+
"max_steps": 1450,
|
242 |
+
"num_train_epochs": 50,
|
243 |
+
"total_flos": 1256051433275392.0,
|
244 |
+
"trial_name": null,
|
245 |
+
"trial_params": null
|
246 |
+
}
|