End of training
Browse files- README.md +9 -7
- all_results.json +15 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1686863361.serv-3317.1921073.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +121 -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: cola
|
20 |
split: validation
|
@@ -22,10 +24,10 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Matthews Correlation
|
24 |
type: matthews_correlation
|
25 |
-
value: 0.
|
26 |
- name: Accuracy
|
27 |
type: accuracy
|
28 |
-
value: 0.
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -33,11 +35,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
33 |
|
34 |
# sa_BERT_24_cola
|
35 |
|
36 |
-
This model is a fine-tuned version of [gokuls/bert_base_24](https://huggingface.co/gokuls/bert_base_24) on the
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
- Loss: 0.
|
39 |
-
- Matthews Correlation: 0.
|
40 |
-
- Accuracy: 0.
|
41 |
|
42 |
## Model description
|
43 |
|
|
|
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 COLA
|
20 |
type: glue
|
21 |
config: cola
|
22 |
split: validation
|
|
|
24 |
metrics:
|
25 |
- name: Matthews Correlation
|
26 |
type: matthews_correlation
|
27 |
+
value: 0.0
|
28 |
- name: Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.6912751793861389
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
# sa_BERT_24_cola
|
37 |
|
38 |
+
This model is a fine-tuned version of [gokuls/bert_base_24](https://huggingface.co/gokuls/bert_base_24) on the GLUE COLA dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 0.6120
|
41 |
+
- Matthews Correlation: 0.0
|
42 |
+
- Accuracy: 0.6913
|
43 |
|
44 |
## Model description
|
45 |
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.6912751793861389,
|
4 |
+
"eval_loss": 0.6119913458824158,
|
5 |
+
"eval_matthews_correlation": 0.0,
|
6 |
+
"eval_runtime": 2.1694,
|
7 |
+
"eval_samples": 1043,
|
8 |
+
"eval_samples_per_second": 480.769,
|
9 |
+
"eval_steps_per_second": 5.07,
|
10 |
+
"train_loss": 0.5213487059981735,
|
11 |
+
"train_runtime": 387.7853,
|
12 |
+
"train_samples": 8551,
|
13 |
+
"train_samples_per_second": 1102.543,
|
14 |
+
"train_steps_per_second": 11.604
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.6912751793861389,
|
4 |
+
"eval_loss": 0.6119913458824158,
|
5 |
+
"eval_matthews_correlation": 0.0,
|
6 |
+
"eval_runtime": 2.1694,
|
7 |
+
"eval_samples": 1043,
|
8 |
+
"eval_samples_per_second": 480.769,
|
9 |
+
"eval_steps_per_second": 5.07
|
10 |
+
}
|
logs/events.out.tfevents.1686863361.serv-3317.1921073.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9f90bc6ad48ee81b1452fd7890936eaa415fe34f39c3363ba9a2f66558b7bc4
|
3 |
+
size 427
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"train_loss": 0.5213487059981735,
|
4 |
+
"train_runtime": 387.7853,
|
5 |
+
"train_samples": 8551,
|
6 |
+
"train_samples_per_second": 1102.543,
|
7 |
+
"train_steps_per_second": 11.604
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6119913458824158,
|
3 |
+
"best_model_checkpoint": "sa_BERT_24_cola/checkpoint-90",
|
4 |
+
"epoch": 6.0,
|
5 |
+
"global_step": 540,
|
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": 3.9200000000000004e-05,
|
13 |
+
"loss": 0.6138,
|
14 |
+
"step": 90
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.6912751793861389,
|
19 |
+
"eval_loss": 0.6119913458824158,
|
20 |
+
"eval_matthews_correlation": 0.0,
|
21 |
+
"eval_runtime": 2.1692,
|
22 |
+
"eval_samples_per_second": 480.825,
|
23 |
+
"eval_steps_per_second": 5.071,
|
24 |
+
"step": 90
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"learning_rate": 3.8400000000000005e-05,
|
29 |
+
"loss": 0.5898,
|
30 |
+
"step": 180
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.693192720413208,
|
35 |
+
"eval_loss": 0.6241820454597473,
|
36 |
+
"eval_matthews_correlation": 0.06558874629318973,
|
37 |
+
"eval_runtime": 2.1753,
|
38 |
+
"eval_samples_per_second": 479.479,
|
39 |
+
"eval_steps_per_second": 5.057,
|
40 |
+
"step": 180
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 3.0,
|
44 |
+
"learning_rate": 3.76e-05,
|
45 |
+
"loss": 0.5491,
|
46 |
+
"step": 270
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 3.0,
|
50 |
+
"eval_accuracy": 0.640460193157196,
|
51 |
+
"eval_loss": 0.679804265499115,
|
52 |
+
"eval_matthews_correlation": 0.07331941707716809,
|
53 |
+
"eval_runtime": 2.1763,
|
54 |
+
"eval_samples_per_second": 479.247,
|
55 |
+
"eval_steps_per_second": 5.054,
|
56 |
+
"step": 270
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"learning_rate": 3.680000000000001e-05,
|
61 |
+
"loss": 0.5027,
|
62 |
+
"step": 360
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.0,
|
66 |
+
"eval_accuracy": 0.6327900290489197,
|
67 |
+
"eval_loss": 0.6873075366020203,
|
68 |
+
"eval_matthews_correlation": 0.0666923742122696,
|
69 |
+
"eval_runtime": 2.1818,
|
70 |
+
"eval_samples_per_second": 478.037,
|
71 |
+
"eval_steps_per_second": 5.042,
|
72 |
+
"step": 360
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 5.0,
|
76 |
+
"learning_rate": 3.6e-05,
|
77 |
+
"loss": 0.4549,
|
78 |
+
"step": 450
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 5.0,
|
82 |
+
"eval_accuracy": 0.6299136877059937,
|
83 |
+
"eval_loss": 0.7840977907180786,
|
84 |
+
"eval_matthews_correlation": 0.10251809083407509,
|
85 |
+
"eval_runtime": 2.1908,
|
86 |
+
"eval_samples_per_second": 476.072,
|
87 |
+
"eval_steps_per_second": 5.021,
|
88 |
+
"step": 450
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 6.0,
|
92 |
+
"learning_rate": 3.52e-05,
|
93 |
+
"loss": 0.4177,
|
94 |
+
"step": 540
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 6.0,
|
98 |
+
"eval_accuracy": 0.5848513841629028,
|
99 |
+
"eval_loss": 0.8220876455307007,
|
100 |
+
"eval_matthews_correlation": 0.08269458252328303,
|
101 |
+
"eval_runtime": 2.1807,
|
102 |
+
"eval_samples_per_second": 478.281,
|
103 |
+
"eval_steps_per_second": 5.044,
|
104 |
+
"step": 540
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.0,
|
108 |
+
"step": 540,
|
109 |
+
"total_flos": 6749587947651072.0,
|
110 |
+
"train_loss": 0.5213487059981735,
|
111 |
+
"train_runtime": 387.7853,
|
112 |
+
"train_samples_per_second": 1102.543,
|
113 |
+
"train_steps_per_second": 11.604
|
114 |
+
}
|
115 |
+
],
|
116 |
+
"max_steps": 4500,
|
117 |
+
"num_train_epochs": 50,
|
118 |
+
"total_flos": 6749587947651072.0,
|
119 |
+
"trial_name": null,
|
120 |
+
"trial_params": null
|
121 |
+
}
|