End of training
Browse files- README.md +7 -5
- all_results.json +14 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1675029964.serv-3334.1016902.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +175 -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: cola
|
19 |
split: validation
|
@@ -21,7 +23,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Matthews Correlation
|
23 |
type: matthews_correlation
|
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_sa_GLUE_Experiment_logit_kd_cola_256
|
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 |
-
- Matthews Correlation: 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 COLA
|
19 |
type: glue
|
20 |
config: cola
|
21 |
split: validation
|
|
|
23 |
metrics:
|
24 |
- name: Matthews Correlation
|
25 |
type: matthews_correlation
|
26 |
+
value: 0.0
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
# mobilebert_sa_GLUE_Experiment_logit_kd_cola_256
|
33 |
|
34 |
+
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE COLA dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.6753
|
37 |
+
- Matthews Correlation: 0.0
|
38 |
|
39 |
## Model description
|
40 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_loss": 0.6752915978431702,
|
4 |
+
"eval_matthews_correlation": 0.0,
|
5 |
+
"eval_runtime": 1.9493,
|
6 |
+
"eval_samples": 1043,
|
7 |
+
"eval_samples_per_second": 535.058,
|
8 |
+
"eval_steps_per_second": 4.617,
|
9 |
+
"train_loss": 0.6987472420308127,
|
10 |
+
"train_runtime": 459.0273,
|
11 |
+
"train_samples": 8551,
|
12 |
+
"train_samples_per_second": 931.426,
|
13 |
+
"train_steps_per_second": 7.298
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_loss": 0.6752915978431702,
|
4 |
+
"eval_matthews_correlation": 0.0,
|
5 |
+
"eval_runtime": 1.9493,
|
6 |
+
"eval_samples": 1043,
|
7 |
+
"eval_samples_per_second": 535.058,
|
8 |
+
"eval_steps_per_second": 4.617
|
9 |
+
}
|
logs/events.out.tfevents.1675029964.serv-3334.1016902.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a816d65f9ddd140191b9a00c327eff41b6dce7d0b530eaecb9ec5453c7872517
|
3 |
+
size 375
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.6987472420308127,
|
4 |
+
"train_runtime": 459.0273,
|
5 |
+
"train_samples": 8551,
|
6 |
+
"train_samples_per_second": 931.426,
|
7 |
+
"train_steps_per_second": 7.298
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6752915978431702,
|
3 |
+
"best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_cola_256/checkpoint-335",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 670,
|
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": 0.8155,
|
14 |
+
"step": 67
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.6866856813430786,
|
19 |
+
"eval_matthews_correlation": 0.0,
|
20 |
+
"eval_runtime": 1.8883,
|
21 |
+
"eval_samples_per_second": 552.344,
|
22 |
+
"eval_steps_per_second": 4.766,
|
23 |
+
"step": 67
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 4.8e-05,
|
28 |
+
"loss": 0.797,
|
29 |
+
"step": 134
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_loss": 0.6862117648124695,
|
34 |
+
"eval_matthews_correlation": 0.0,
|
35 |
+
"eval_runtime": 1.8997,
|
36 |
+
"eval_samples_per_second": 549.042,
|
37 |
+
"eval_steps_per_second": 4.738,
|
38 |
+
"step": 134
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 4.7e-05,
|
43 |
+
"loss": 0.7961,
|
44 |
+
"step": 201
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_loss": 0.6835954189300537,
|
49 |
+
"eval_matthews_correlation": 0.0,
|
50 |
+
"eval_runtime": 1.8895,
|
51 |
+
"eval_samples_per_second": 552.012,
|
52 |
+
"eval_steps_per_second": 4.763,
|
53 |
+
"step": 201
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 4.600000000000001e-05,
|
58 |
+
"loss": 0.7944,
|
59 |
+
"step": 268
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_loss": 0.6820743083953857,
|
64 |
+
"eval_matthews_correlation": 0.0,
|
65 |
+
"eval_runtime": 1.89,
|
66 |
+
"eval_samples_per_second": 551.842,
|
67 |
+
"eval_steps_per_second": 4.762,
|
68 |
+
"step": 268
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 4.5e-05,
|
73 |
+
"loss": 0.7863,
|
74 |
+
"step": 335
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_loss": 0.6752915978431702,
|
79 |
+
"eval_matthews_correlation": 0.0,
|
80 |
+
"eval_runtime": 1.8919,
|
81 |
+
"eval_samples_per_second": 551.283,
|
82 |
+
"eval_steps_per_second": 4.757,
|
83 |
+
"step": 335
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 4.4000000000000006e-05,
|
88 |
+
"loss": 0.7138,
|
89 |
+
"step": 402
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_loss": 0.6790478229522705,
|
94 |
+
"eval_matthews_correlation": 0.10850458893694606,
|
95 |
+
"eval_runtime": 1.8885,
|
96 |
+
"eval_samples_per_second": 552.291,
|
97 |
+
"eval_steps_per_second": 4.766,
|
98 |
+
"step": 402
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"learning_rate": 4.3e-05,
|
103 |
+
"loss": 0.6262,
|
104 |
+
"step": 469
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"eval_loss": 0.7237713932991028,
|
109 |
+
"eval_matthews_correlation": 0.12306256417772918,
|
110 |
+
"eval_runtime": 1.8926,
|
111 |
+
"eval_samples_per_second": 551.092,
|
112 |
+
"eval_steps_per_second": 4.755,
|
113 |
+
"step": 469
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 8.0,
|
117 |
+
"learning_rate": 4.2e-05,
|
118 |
+
"loss": 0.5782,
|
119 |
+
"step": 536
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 8.0,
|
123 |
+
"eval_loss": 0.728486180305481,
|
124 |
+
"eval_matthews_correlation": 0.1280618805073397,
|
125 |
+
"eval_runtime": 1.8913,
|
126 |
+
"eval_samples_per_second": 551.473,
|
127 |
+
"eval_steps_per_second": 4.759,
|
128 |
+
"step": 536
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.0,
|
132 |
+
"learning_rate": 4.1e-05,
|
133 |
+
"loss": 0.5482,
|
134 |
+
"step": 603
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 9.0,
|
138 |
+
"eval_loss": 0.7484392523765564,
|
139 |
+
"eval_matthews_correlation": 0.1280618805073397,
|
140 |
+
"eval_runtime": 1.8977,
|
141 |
+
"eval_samples_per_second": 549.598,
|
142 |
+
"eval_steps_per_second": 4.742,
|
143 |
+
"step": 603
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 10.0,
|
147 |
+
"learning_rate": 4e-05,
|
148 |
+
"loss": 0.5318,
|
149 |
+
"step": 670
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 10.0,
|
153 |
+
"eval_loss": 0.7918062210083008,
|
154 |
+
"eval_matthews_correlation": 0.11818409443621868,
|
155 |
+
"eval_runtime": 1.949,
|
156 |
+
"eval_samples_per_second": 535.158,
|
157 |
+
"eval_steps_per_second": 4.618,
|
158 |
+
"step": 670
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 10.0,
|
162 |
+
"step": 670,
|
163 |
+
"total_flos": 2252431677194240.0,
|
164 |
+
"train_loss": 0.6987472420308127,
|
165 |
+
"train_runtime": 459.0273,
|
166 |
+
"train_samples_per_second": 931.426,
|
167 |
+
"train_steps_per_second": 7.298
|
168 |
+
}
|
169 |
+
],
|
170 |
+
"max_steps": 3350,
|
171 |
+
"num_train_epochs": 50,
|
172 |
+
"total_flos": 2252431677194240.0,
|
173 |
+
"trial_name": null,
|
174 |
+
"trial_params": null
|
175 |
+
}
|