End of training
Browse files- README.md +4 -2
- all_results.json +14 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1685547527.serv-3318.2597307.17 +3 -0
- train_results.json +8 -0
- trainer_state.json +115 -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: rte
|
18 |
split: validation
|
@@ -28,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
# hBERTv1_new_pretrain_rte
|
30 |
|
31 |
-
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new) on the
|
32 |
It achieves the following results on the evaluation set:
|
33 |
- Loss: 28.2681
|
34 |
- Accuracy: 0.4729
|
|
|
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 RTE
|
18 |
type: glue
|
19 |
config: rte
|
20 |
split: validation
|
|
|
30 |
|
31 |
# hBERTv1_new_pretrain_rte
|
32 |
|
33 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new) on the GLUE RTE dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
- Loss: 28.2681
|
36 |
- Accuracy: 0.4729
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.4729241877256318,
|
4 |
+
"eval_loss": 28.268051147460938,
|
5 |
+
"eval_runtime": 0.5114,
|
6 |
+
"eval_samples": 277,
|
7 |
+
"eval_samples_per_second": 541.669,
|
8 |
+
"eval_steps_per_second": 5.866,
|
9 |
+
"train_loss": 29.028575642903647,
|
10 |
+
"train_runtime": 102.0364,
|
11 |
+
"train_samples": 2490,
|
12 |
+
"train_samples_per_second": 1220.153,
|
13 |
+
"train_steps_per_second": 9.8
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.4729241877256318,
|
4 |
+
"eval_loss": 28.268051147460938,
|
5 |
+
"eval_runtime": 0.5114,
|
6 |
+
"eval_samples": 277,
|
7 |
+
"eval_samples_per_second": 541.669,
|
8 |
+
"eval_steps_per_second": 5.866
|
9 |
+
}
|
logs/events.out.tfevents.1685547527.serv-3318.2597307.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cf02ac44f3aa6d7ff81a7e86fe6843799a11293c03fcce22a91ae69337a6ea0
|
3 |
+
size 357
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"train_loss": 29.028575642903647,
|
4 |
+
"train_runtime": 102.0364,
|
5 |
+
"train_samples": 2490,
|
6 |
+
"train_samples_per_second": 1220.153,
|
7 |
+
"train_steps_per_second": 9.8
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 28.268051147460938,
|
3 |
+
"best_model_checkpoint": "hBERTv1_new_pretrain_rte/checkpoint-20",
|
4 |
+
"epoch": 6.0,
|
5 |
+
"global_step": 120,
|
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": 0.00049,
|
13 |
+
"loss": 28.8034,
|
14 |
+
"step": 20
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.4729241877256318,
|
19 |
+
"eval_loss": 28.268051147460938,
|
20 |
+
"eval_runtime": 0.5081,
|
21 |
+
"eval_samples_per_second": 545.128,
|
22 |
+
"eval_steps_per_second": 5.904,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 0.00048,
|
28 |
+
"loss": 28.8444,
|
29 |
+
"step": 40
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.4729241877256318,
|
34 |
+
"eval_loss": 28.268051147460938,
|
35 |
+
"eval_runtime": 0.5097,
|
36 |
+
"eval_samples_per_second": 543.476,
|
37 |
+
"eval_steps_per_second": 5.886,
|
38 |
+
"step": 40
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 0.00047,
|
43 |
+
"loss": 28.6738,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.4729241877256318,
|
49 |
+
"eval_loss": 28.268051147460938,
|
50 |
+
"eval_runtime": 0.5098,
|
51 |
+
"eval_samples_per_second": 543.347,
|
52 |
+
"eval_steps_per_second": 5.885,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 0.00046,
|
58 |
+
"loss": 29.3662,
|
59 |
+
"step": 80
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.4729241877256318,
|
64 |
+
"eval_loss": 28.268051147460938,
|
65 |
+
"eval_runtime": 0.5103,
|
66 |
+
"eval_samples_per_second": 542.814,
|
67 |
+
"eval_steps_per_second": 5.879,
|
68 |
+
"step": 80
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 0.00045000000000000004,
|
73 |
+
"loss": 30.0413,
|
74 |
+
"step": 100
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_accuracy": 0.4729241877256318,
|
79 |
+
"eval_loss": 28.268051147460938,
|
80 |
+
"eval_runtime": 0.5111,
|
81 |
+
"eval_samples_per_second": 541.935,
|
82 |
+
"eval_steps_per_second": 5.869,
|
83 |
+
"step": 100
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 0.00044,
|
88 |
+
"loss": 28.4423,
|
89 |
+
"step": 120
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_accuracy": 0.4729241877256318,
|
94 |
+
"eval_loss": 28.268051147460938,
|
95 |
+
"eval_runtime": 0.5109,
|
96 |
+
"eval_samples_per_second": 542.142,
|
97 |
+
"eval_steps_per_second": 5.872,
|
98 |
+
"step": 120
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 6.0,
|
102 |
+
"step": 120,
|
103 |
+
"total_flos": 2212565757198336.0,
|
104 |
+
"train_loss": 29.028575642903647,
|
105 |
+
"train_runtime": 102.0364,
|
106 |
+
"train_samples_per_second": 1220.153,
|
107 |
+
"train_steps_per_second": 9.8
|
108 |
+
}
|
109 |
+
],
|
110 |
+
"max_steps": 1000,
|
111 |
+
"num_train_epochs": 50,
|
112 |
+
"total_flos": 2212565757198336.0,
|
113 |
+
"trial_name": null,
|
114 |
+
"trial_params": null
|
115 |
+
}
|