End of training
Browse files- README.md +7 -5
- all_results.json +14 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1686870314.serv-9225.2647846.7 +3 -0
- train_results.json +8 -0
- trainer_state.json +130 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
@@ -12,7 +14,7 @@ model-index:
|
|
12 |
name: Text Classification
|
13 |
type: text-classification
|
14 |
dataset:
|
15 |
-
name:
|
16 |
type: glue
|
17 |
config: qnli
|
18 |
split: validation
|
@@ -20,7 +22,7 @@ model-index:
|
|
20 |
metrics:
|
21 |
- name: Accuracy
|
22 |
type: accuracy
|
23 |
-
value: 0.
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
# hBERTv2_new_pretrain_48_KD_w_init_qnli
|
30 |
|
31 |
-
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48_KD_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48_KD_wt_init) on the
|
32 |
It achieves the following results on the evaluation set:
|
33 |
-
- Loss: 0.
|
34 |
-
- Accuracy: 0.
|
35 |
|
36 |
## Model description
|
37 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
14 |
name: Text Classification
|
15 |
type: text-classification
|
16 |
dataset:
|
17 |
+
name: GLUE QNLI
|
18 |
type: glue
|
19 |
config: qnli
|
20 |
split: validation
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.6417719201903715
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# hBERTv2_new_pretrain_48_KD_w_init_qnli
|
32 |
|
33 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48_KD_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48_KD_wt_init) on the GLUE QNLI dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6306
|
36 |
+
- Accuracy: 0.6418
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.0,
|
3 |
+
"eval_accuracy": 0.6417719201903715,
|
4 |
+
"eval_loss": 0.6305641531944275,
|
5 |
+
"eval_runtime": 11.4015,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 479.146,
|
8 |
+
"eval_steps_per_second": 3.771,
|
9 |
+
"train_loss": 0.5375828685590823,
|
10 |
+
"train_runtime": 4891.2045,
|
11 |
+
"train_samples": 104743,
|
12 |
+
"train_samples_per_second": 1070.728,
|
13 |
+
"train_steps_per_second": 8.372
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.0,
|
3 |
+
"eval_accuracy": 0.6417719201903715,
|
4 |
+
"eval_loss": 0.6305641531944275,
|
5 |
+
"eval_runtime": 11.4015,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 479.146,
|
8 |
+
"eval_steps_per_second": 3.771
|
9 |
+
}
|
logs/events.out.tfevents.1686870314.serv-9225.2647846.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30c11b0affb8cdf85592196418113b0b8150dc28588ba1ae3796c04531942c36
|
3 |
+
size 363
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.0,
|
3 |
+
"train_loss": 0.5375828685590823,
|
4 |
+
"train_runtime": 4891.2045,
|
5 |
+
"train_samples": 104743,
|
6 |
+
"train_samples_per_second": 1070.728,
|
7 |
+
"train_steps_per_second": 8.372
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6305641531944275,
|
3 |
+
"best_model_checkpoint": "hBERTv2_new_pretrain_48_KD_w_init_qnli/checkpoint-1638",
|
4 |
+
"epoch": 7.0,
|
5 |
+
"global_step": 5733,
|
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": 0.6733,
|
14 |
+
"step": 819
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.5912502288120081,
|
19 |
+
"eval_loss": 0.6642831563949585,
|
20 |
+
"eval_runtime": 11.4659,
|
21 |
+
"eval_samples_per_second": 476.455,
|
22 |
+
"eval_steps_per_second": 3.75,
|
23 |
+
"step": 819
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 3.8400000000000005e-05,
|
28 |
+
"loss": 0.641,
|
29 |
+
"step": 1638
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.6417719201903715,
|
34 |
+
"eval_loss": 0.6305641531944275,
|
35 |
+
"eval_runtime": 11.4569,
|
36 |
+
"eval_samples_per_second": 476.832,
|
37 |
+
"eval_steps_per_second": 3.753,
|
38 |
+
"step": 1638
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 3.76e-05,
|
43 |
+
"loss": 0.5952,
|
44 |
+
"step": 2457
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.6377448288486179,
|
49 |
+
"eval_loss": 0.6487901210784912,
|
50 |
+
"eval_runtime": 11.4643,
|
51 |
+
"eval_samples_per_second": 476.521,
|
52 |
+
"eval_steps_per_second": 3.751,
|
53 |
+
"step": 2457
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 3.680000000000001e-05,
|
58 |
+
"loss": 0.5439,
|
59 |
+
"step": 3276
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.6302397949844408,
|
64 |
+
"eval_loss": 0.6660674810409546,
|
65 |
+
"eval_runtime": 11.4595,
|
66 |
+
"eval_samples_per_second": 476.722,
|
67 |
+
"eval_steps_per_second": 3.752,
|
68 |
+
"step": 3276
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 3.6e-05,
|
73 |
+
"loss": 0.4907,
|
74 |
+
"step": 4095
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_accuracy": 0.6252974556104705,
|
79 |
+
"eval_loss": 0.6936535239219666,
|
80 |
+
"eval_runtime": 11.4579,
|
81 |
+
"eval_samples_per_second": 476.79,
|
82 |
+
"eval_steps_per_second": 3.753,
|
83 |
+
"step": 4095
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 3.52e-05,
|
88 |
+
"loss": 0.4364,
|
89 |
+
"step": 4914
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_accuracy": 0.6296906461651107,
|
94 |
+
"eval_loss": 0.7380545139312744,
|
95 |
+
"eval_runtime": 11.4626,
|
96 |
+
"eval_samples_per_second": 476.593,
|
97 |
+
"eval_steps_per_second": 3.751,
|
98 |
+
"step": 4914
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"learning_rate": 3.44e-05,
|
103 |
+
"loss": 0.3825,
|
104 |
+
"step": 5733
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"eval_accuracy": 0.624016108365367,
|
109 |
+
"eval_loss": 0.8474876880645752,
|
110 |
+
"eval_runtime": 11.4645,
|
111 |
+
"eval_samples_per_second": 476.514,
|
112 |
+
"eval_steps_per_second": 3.751,
|
113 |
+
"step": 5733
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 7.0,
|
117 |
+
"step": 5733,
|
118 |
+
"total_flos": 1.0729602688011469e+17,
|
119 |
+
"train_loss": 0.5375828685590823,
|
120 |
+
"train_runtime": 4891.2045,
|
121 |
+
"train_samples_per_second": 1070.728,
|
122 |
+
"train_steps_per_second": 8.372
|
123 |
+
}
|
124 |
+
],
|
125 |
+
"max_steps": 40950,
|
126 |
+
"num_train_epochs": 50,
|
127 |
+
"total_flos": 1.0729602688011469e+17,
|
128 |
+
"trial_name": null,
|
129 |
+
"trial_params": null
|
130 |
+
}
|