End of training
Browse files- README.md +10 -8
- all_results.json +16 -0
- eval_results.json +11 -0
- logs/events.out.tfevents.1674772718.garda.473409.11 +3 -0
- train_results.json +8 -0
- trainer_state.json +229 -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: qqp
|
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_add_GLUE_Experiment_qqp
|
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: 0.
|
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 QQP
|
20 |
type: glue
|
21 |
config: qqp
|
22 |
split: validation
|
|
|
24 |
metrics:
|
25 |
- name: Accuracy
|
26 |
type: accuracy
|
27 |
+
value: 0.7599802127133317
|
28 |
- name: F1
|
29 |
type: f1
|
30 |
+
value: 0.6401928068223952
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
# mobilebert_add_GLUE_Experiment_qqp
|
37 |
|
38 |
+
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE QQP dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 0.5008
|
41 |
+
- Accuracy: 0.7600
|
42 |
+
- F1: 0.6402
|
43 |
+
- Combined Score: 0.7001
|
44 |
|
45 |
## Model description
|
46 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 12.0,
|
3 |
+
"eval_accuracy": 0.7599802127133317,
|
4 |
+
"eval_combined_score": 0.7000865097678635,
|
5 |
+
"eval_f1": 0.6401928068223952,
|
6 |
+
"eval_loss": 0.5008143186569214,
|
7 |
+
"eval_runtime": 86.209,
|
8 |
+
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 468.976,
|
10 |
+
"eval_steps_per_second": 3.666,
|
11 |
+
"train_loss": 0.5180756985645023,
|
12 |
+
"train_runtime": 29413.6297,
|
13 |
+
"train_samples": 363846,
|
14 |
+
"train_samples_per_second": 618.499,
|
15 |
+
"train_steps_per_second": 4.833
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 12.0,
|
3 |
+
"eval_accuracy": 0.7599802127133317,
|
4 |
+
"eval_combined_score": 0.7000865097678635,
|
5 |
+
"eval_f1": 0.6401928068223952,
|
6 |
+
"eval_loss": 0.5008143186569214,
|
7 |
+
"eval_runtime": 86.209,
|
8 |
+
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 468.976,
|
10 |
+
"eval_steps_per_second": 3.666
|
11 |
+
}
|
logs/events.out.tfevents.1674772718.garda.473409.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ba777b67d13951b87951c2eb0d2d640b0768326c4ff068c78efe5fc9a3e552a
|
3 |
+
size 475
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 12.0,
|
3 |
+
"train_loss": 0.5180756985645023,
|
4 |
+
"train_runtime": 29413.6297,
|
5 |
+
"train_samples": 363846,
|
6 |
+
"train_samples_per_second": 618.499,
|
7 |
+
"train_steps_per_second": 4.833
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5008143186569214,
|
3 |
+
"best_model_checkpoint": "mobilebert_add_GLUE_Experiment_qqp/checkpoint-19901",
|
4 |
+
"epoch": 12.0,
|
5 |
+
"global_step": 34116,
|
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": 0.6505,
|
14 |
+
"step": 2843
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.6320554044026713,
|
19 |
+
"eval_combined_score": 0.3166319723772454,
|
20 |
+
"eval_f1": 0.0012085403518195246,
|
21 |
+
"eval_loss": 0.6498478651046753,
|
22 |
+
"eval_runtime": 84.4187,
|
23 |
+
"eval_samples_per_second": 478.923,
|
24 |
+
"eval_steps_per_second": 3.743,
|
25 |
+
"step": 2843
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 4.8e-05,
|
30 |
+
"loss": 0.6474,
|
31 |
+
"step": 5686
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.6320554044026713,
|
36 |
+
"eval_combined_score": 0.3166319723772454,
|
37 |
+
"eval_f1": 0.0012085403518195246,
|
38 |
+
"eval_loss": 0.6484191417694092,
|
39 |
+
"eval_runtime": 84.4998,
|
40 |
+
"eval_samples_per_second": 478.463,
|
41 |
+
"eval_steps_per_second": 3.74,
|
42 |
+
"step": 5686
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"learning_rate": 4.7e-05,
|
47 |
+
"loss": 0.646,
|
48 |
+
"step": 8529
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.6322038090526837,
|
53 |
+
"eval_combined_score": 0.3173094719488563,
|
54 |
+
"eval_f1": 0.0024151348450288474,
|
55 |
+
"eval_loss": 0.6478633880615234,
|
56 |
+
"eval_runtime": 84.5145,
|
57 |
+
"eval_samples_per_second": 478.38,
|
58 |
+
"eval_steps_per_second": 3.739,
|
59 |
+
"step": 8529
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"learning_rate": 4.600000000000001e-05,
|
64 |
+
"loss": 0.5481,
|
65 |
+
"step": 11372
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_accuracy": 0.7486272569873856,
|
70 |
+
"eval_combined_score": 0.6866867038546203,
|
71 |
+
"eval_f1": 0.624746150721855,
|
72 |
+
"eval_loss": 0.5139716267585754,
|
73 |
+
"eval_runtime": 85.5613,
|
74 |
+
"eval_samples_per_second": 472.527,
|
75 |
+
"eval_steps_per_second": 3.693,
|
76 |
+
"step": 11372
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.0,
|
80 |
+
"learning_rate": 4.5e-05,
|
81 |
+
"loss": 0.4934,
|
82 |
+
"step": 14215
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 5.0,
|
86 |
+
"eval_accuracy": 0.7529062577294089,
|
87 |
+
"eval_combined_score": 0.7038665764495293,
|
88 |
+
"eval_f1": 0.6548268951696496,
|
89 |
+
"eval_loss": 0.508634090423584,
|
90 |
+
"eval_runtime": 85.77,
|
91 |
+
"eval_samples_per_second": 471.377,
|
92 |
+
"eval_steps_per_second": 3.684,
|
93 |
+
"step": 14215
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 6.0,
|
97 |
+
"learning_rate": 4.4000000000000006e-05,
|
98 |
+
"loss": 0.4794,
|
99 |
+
"step": 17058
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 6.0,
|
103 |
+
"eval_accuracy": 0.7575315359881276,
|
104 |
+
"eval_combined_score": 0.7051322705269201,
|
105 |
+
"eval_f1": 0.6527330050657125,
|
106 |
+
"eval_loss": 0.5043991208076477,
|
107 |
+
"eval_runtime": 85.6759,
|
108 |
+
"eval_samples_per_second": 471.895,
|
109 |
+
"eval_steps_per_second": 3.688,
|
110 |
+
"step": 17058
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"learning_rate": 4.3e-05,
|
115 |
+
"loss": 0.4708,
|
116 |
+
"step": 19901
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 7.0,
|
120 |
+
"eval_accuracy": 0.7599802127133317,
|
121 |
+
"eval_combined_score": 0.7000865097678635,
|
122 |
+
"eval_f1": 0.6401928068223952,
|
123 |
+
"eval_loss": 0.5008143186569214,
|
124 |
+
"eval_runtime": 85.4807,
|
125 |
+
"eval_samples_per_second": 472.972,
|
126 |
+
"eval_steps_per_second": 3.697,
|
127 |
+
"step": 19901
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 8.0,
|
131 |
+
"learning_rate": 4.2e-05,
|
132 |
+
"loss": 0.4652,
|
133 |
+
"step": 22744
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 8.0,
|
137 |
+
"eval_accuracy": 0.7618600049468217,
|
138 |
+
"eval_combined_score": 0.7001156995887954,
|
139 |
+
"eval_f1": 0.6383713942307692,
|
140 |
+
"eval_loss": 0.5009844303131104,
|
141 |
+
"eval_runtime": 85.8727,
|
142 |
+
"eval_samples_per_second": 470.813,
|
143 |
+
"eval_steps_per_second": 3.68,
|
144 |
+
"step": 22744
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 9.0,
|
148 |
+
"learning_rate": 4.1e-05,
|
149 |
+
"loss": 0.4604,
|
150 |
+
"step": 25587
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 9.0,
|
154 |
+
"eval_accuracy": 0.7614147909967846,
|
155 |
+
"eval_combined_score": 0.7051723831239565,
|
156 |
+
"eval_f1": 0.6489299752511283,
|
157 |
+
"eval_loss": 0.5014066100120544,
|
158 |
+
"eval_runtime": 86.3999,
|
159 |
+
"eval_samples_per_second": 467.94,
|
160 |
+
"eval_steps_per_second": 3.657,
|
161 |
+
"step": 25587
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 10.0,
|
165 |
+
"learning_rate": 4e-05,
|
166 |
+
"loss": 0.4562,
|
167 |
+
"step": 28430
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 10.0,
|
171 |
+
"eval_accuracy": 0.7599802127133317,
|
172 |
+
"eval_combined_score": 0.7108365712848488,
|
173 |
+
"eval_f1": 0.661692929856366,
|
174 |
+
"eval_loss": 0.5057373642921448,
|
175 |
+
"eval_runtime": 86.4384,
|
176 |
+
"eval_samples_per_second": 467.732,
|
177 |
+
"eval_steps_per_second": 3.656,
|
178 |
+
"step": 28430
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 11.0,
|
182 |
+
"learning_rate": 3.9000000000000006e-05,
|
183 |
+
"loss": 0.452,
|
184 |
+
"step": 31273
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 11.0,
|
188 |
+
"eval_accuracy": 0.7619836754884987,
|
189 |
+
"eval_combined_score": 0.6991856786662217,
|
190 |
+
"eval_f1": 0.6363876818439448,
|
191 |
+
"eval_loss": 0.5101634860038757,
|
192 |
+
"eval_runtime": 86.4692,
|
193 |
+
"eval_samples_per_second": 467.565,
|
194 |
+
"eval_steps_per_second": 3.654,
|
195 |
+
"step": 31273
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 12.0,
|
199 |
+
"learning_rate": 3.8e-05,
|
200 |
+
"loss": 0.4476,
|
201 |
+
"step": 34116
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 12.0,
|
205 |
+
"eval_accuracy": 0.7621815483551818,
|
206 |
+
"eval_combined_score": 0.712056633324597,
|
207 |
+
"eval_f1": 0.6619317182940121,
|
208 |
+
"eval_loss": 0.5301799774169922,
|
209 |
+
"eval_runtime": 86.4861,
|
210 |
+
"eval_samples_per_second": 467.474,
|
211 |
+
"eval_steps_per_second": 3.654,
|
212 |
+
"step": 34116
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 12.0,
|
216 |
+
"step": 34116,
|
217 |
+
"total_flos": 1.2915236812514918e+17,
|
218 |
+
"train_loss": 0.5180756985645023,
|
219 |
+
"train_runtime": 29413.6297,
|
220 |
+
"train_samples_per_second": 618.499,
|
221 |
+
"train_steps_per_second": 4.833
|
222 |
+
}
|
223 |
+
],
|
224 |
+
"max_steps": 142150,
|
225 |
+
"num_train_epochs": 50,
|
226 |
+
"total_flos": 1.2915236812514918e+17,
|
227 |
+
"trial_name": null,
|
228 |
+
"trial_params": null
|
229 |
+
}
|