End of training
Browse files- README.md +7 -5
- all_results.json +14 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1674763356.gera.2822633.17 +3 -0
- train_results.json +8 -0
- trainer_state.json +205 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
@@ -13,7 +15,7 @@ model-index:
|
|
13 |
name: Text Classification
|
14 |
type: text-classification
|
15 |
dataset:
|
16 |
-
name:
|
17 |
type: glue
|
18 |
config: sst2
|
19 |
split: validation
|
@@ -21,7 +23,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
-
value: 0.
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -29,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
# mobilebert_add_GLUE_Experiment_sst2_128
|
31 |
|
32 |
-
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
-
- Accuracy: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
15 |
name: Text Classification
|
16 |
type: text-classification
|
17 |
dataset:
|
18 |
+
name: GLUE SST2
|
19 |
type: glue
|
20 |
config: sst2
|
21 |
split: validation
|
|
|
23 |
metrics:
|
24 |
- name: Accuracy
|
25 |
type: accuracy
|
26 |
+
value: 0.7981651376146789
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
# mobilebert_add_GLUE_Experiment_sst2_128
|
33 |
|
34 |
+
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE SST2 dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.4543
|
37 |
+
- Accuracy: 0.7982
|
38 |
|
39 |
## Model description
|
40 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 12.0,
|
3 |
+
"eval_accuracy": 0.7981651376146789,
|
4 |
+
"eval_loss": 0.4542507827281952,
|
5 |
+
"eval_runtime": 1.5528,
|
6 |
+
"eval_samples": 872,
|
7 |
+
"eval_samples_per_second": 561.568,
|
8 |
+
"eval_steps_per_second": 4.508,
|
9 |
+
"train_loss": 0.3588200110110356,
|
10 |
+
"train_runtime": 4204.4171,
|
11 |
+
"train_samples": 67349,
|
12 |
+
"train_samples_per_second": 800.931,
|
13 |
+
"train_steps_per_second": 6.267
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 12.0,
|
3 |
+
"eval_accuracy": 0.7981651376146789,
|
4 |
+
"eval_loss": 0.4542507827281952,
|
5 |
+
"eval_runtime": 1.5528,
|
6 |
+
"eval_samples": 872,
|
7 |
+
"eval_samples_per_second": 561.568,
|
8 |
+
"eval_steps_per_second": 4.508
|
9 |
+
}
|
logs/events.out.tfevents.1674763356.gera.2822633.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32c9559427833f5c5e6d2925ad3ada38c620f7df53286605212946645b4ff4d2
|
3 |
+
size 363
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 12.0,
|
3 |
+
"train_loss": 0.3588200110110356,
|
4 |
+
"train_runtime": 4204.4171,
|
5 |
+
"train_samples": 67349,
|
6 |
+
"train_samples_per_second": 800.931,
|
7 |
+
"train_steps_per_second": 6.267
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4542507827281952,
|
3 |
+
"best_model_checkpoint": "mobilebert_add_GLUE_Experiment_sst2_128/checkpoint-3689",
|
4 |
+
"epoch": 12.0,
|
5 |
+
"global_step": 6324,
|
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": 0.6677,
|
14 |
+
"step": 527
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.5756880733944955,
|
19 |
+
"eval_loss": 0.677055299282074,
|
20 |
+
"eval_runtime": 1.7061,
|
21 |
+
"eval_samples_per_second": 511.104,
|
22 |
+
"eval_steps_per_second": 4.103,
|
23 |
+
"step": 527
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 4.8e-05,
|
28 |
+
"loss": 0.5966,
|
29 |
+
"step": 1054
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.5424311926605505,
|
34 |
+
"eval_loss": 0.7135030627250671,
|
35 |
+
"eval_runtime": 1.5325,
|
36 |
+
"eval_samples_per_second": 569.001,
|
37 |
+
"eval_steps_per_second": 4.568,
|
38 |
+
"step": 1054
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 4.7e-05,
|
43 |
+
"loss": 0.5714,
|
44 |
+
"step": 1581
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.555045871559633,
|
49 |
+
"eval_loss": 0.7271105647087097,
|
50 |
+
"eval_runtime": 1.5765,
|
51 |
+
"eval_samples_per_second": 553.131,
|
52 |
+
"eval_steps_per_second": 4.44,
|
53 |
+
"step": 1581
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 4.600000000000001e-05,
|
58 |
+
"loss": 0.5573,
|
59 |
+
"step": 2108
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.5619266055045872,
|
64 |
+
"eval_loss": 0.6891608238220215,
|
65 |
+
"eval_runtime": 1.5223,
|
66 |
+
"eval_samples_per_second": 572.828,
|
67 |
+
"eval_steps_per_second": 4.598,
|
68 |
+
"step": 2108
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 4.5e-05,
|
73 |
+
"loss": 0.501,
|
74 |
+
"step": 2635
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_accuracy": 0.7798165137614679,
|
79 |
+
"eval_loss": 0.45462021231651306,
|
80 |
+
"eval_runtime": 1.5903,
|
81 |
+
"eval_samples_per_second": 548.34,
|
82 |
+
"eval_steps_per_second": 4.402,
|
83 |
+
"step": 2635
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 4.4000000000000006e-05,
|
88 |
+
"loss": 0.2856,
|
89 |
+
"step": 3162
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_accuracy": 0.805045871559633,
|
94 |
+
"eval_loss": 0.46127501130104065,
|
95 |
+
"eval_runtime": 1.5321,
|
96 |
+
"eval_samples_per_second": 569.164,
|
97 |
+
"eval_steps_per_second": 4.569,
|
98 |
+
"step": 3162
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"learning_rate": 4.3e-05,
|
103 |
+
"loss": 0.2288,
|
104 |
+
"step": 3689
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"eval_accuracy": 0.7981651376146789,
|
109 |
+
"eval_loss": 0.4542507827281952,
|
110 |
+
"eval_runtime": 1.5229,
|
111 |
+
"eval_samples_per_second": 572.609,
|
112 |
+
"eval_steps_per_second": 4.597,
|
113 |
+
"step": 3689
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 8.0,
|
117 |
+
"learning_rate": 4.2e-05,
|
118 |
+
"loss": 0.2027,
|
119 |
+
"step": 4216
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 8.0,
|
123 |
+
"eval_accuracy": 0.7993119266055045,
|
124 |
+
"eval_loss": 0.4661611020565033,
|
125 |
+
"eval_runtime": 1.5648,
|
126 |
+
"eval_samples_per_second": 557.264,
|
127 |
+
"eval_steps_per_second": 4.473,
|
128 |
+
"step": 4216
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.0,
|
132 |
+
"learning_rate": 4.1e-05,
|
133 |
+
"loss": 0.1883,
|
134 |
+
"step": 4743
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 9.0,
|
138 |
+
"eval_accuracy": 0.8038990825688074,
|
139 |
+
"eval_loss": 0.516830563545227,
|
140 |
+
"eval_runtime": 1.5219,
|
141 |
+
"eval_samples_per_second": 572.954,
|
142 |
+
"eval_steps_per_second": 4.599,
|
143 |
+
"step": 4743
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 10.0,
|
147 |
+
"learning_rate": 4e-05,
|
148 |
+
"loss": 0.1779,
|
149 |
+
"step": 5270
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 10.0,
|
153 |
+
"eval_accuracy": 0.7855504587155964,
|
154 |
+
"eval_loss": 0.5748016834259033,
|
155 |
+
"eval_runtime": 1.5164,
|
156 |
+
"eval_samples_per_second": 575.045,
|
157 |
+
"eval_steps_per_second": 4.616,
|
158 |
+
"step": 5270
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 11.0,
|
162 |
+
"learning_rate": 3.9000000000000006e-05,
|
163 |
+
"loss": 0.1691,
|
164 |
+
"step": 5797
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 11.0,
|
168 |
+
"eval_accuracy": 0.8027522935779816,
|
169 |
+
"eval_loss": 0.5195825099945068,
|
170 |
+
"eval_runtime": 1.5266,
|
171 |
+
"eval_samples_per_second": 571.211,
|
172 |
+
"eval_steps_per_second": 4.585,
|
173 |
+
"step": 5797
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 12.0,
|
177 |
+
"learning_rate": 3.8e-05,
|
178 |
+
"loss": 0.1596,
|
179 |
+
"step": 6324
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 12.0,
|
183 |
+
"eval_accuracy": 0.7947247706422018,
|
184 |
+
"eval_loss": 0.5943012237548828,
|
185 |
+
"eval_runtime": 1.5592,
|
186 |
+
"eval_samples_per_second": 559.25,
|
187 |
+
"eval_steps_per_second": 4.489,
|
188 |
+
"step": 6324
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 12.0,
|
192 |
+
"step": 6324,
|
193 |
+
"total_flos": 1.9293579893538816e+16,
|
194 |
+
"train_loss": 0.3588200110110356,
|
195 |
+
"train_runtime": 4204.4171,
|
196 |
+
"train_samples_per_second": 800.931,
|
197 |
+
"train_steps_per_second": 6.267
|
198 |
+
}
|
199 |
+
],
|
200 |
+
"max_steps": 26350,
|
201 |
+
"num_train_epochs": 50,
|
202 |
+
"total_flos": 1.9293579893538816e+16,
|
203 |
+
"trial_name": null,
|
204 |
+
"trial_params": null
|
205 |
+
}
|