End of training
Browse files- README.md +19 -2
- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
README.md
CHANGED
@@ -1,9 +1,23 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
4 |
model-index:
|
5 |
- name: HBERTv1_48_L2_H128_A2_ffn_1
|
6 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
---
|
8 |
|
9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -11,7 +25,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
11 |
|
12 |
# HBERTv1_48_L2_H128_A2_ffn_1
|
13 |
|
14 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on
|
|
|
|
|
|
|
15 |
|
16 |
## Model description
|
17 |
|
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- gokuls/wiki_book_corpus_complete_processed_bert_dataset
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
model-index:
|
9 |
- name: HBERTv1_48_L2_H128_A2_ffn_1
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Masked Language Modeling
|
13 |
+
type: fill-mask
|
14 |
+
dataset:
|
15 |
+
name: gokuls/wiki_book_corpus_complete_processed_bert_dataset
|
16 |
+
type: gokuls/wiki_book_corpus_complete_processed_bert_dataset
|
17 |
+
metrics:
|
18 |
+
- name: Accuracy
|
19 |
+
type: accuracy
|
20 |
+
value: 0.1496531706247267
|
21 |
---
|
22 |
|
23 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
25 |
|
26 |
# HBERTv1_48_L2_H128_A2_ffn_1
|
27 |
|
28 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the gokuls/wiki_book_corpus_complete_processed_bert_dataset dataset.
|
29 |
+
It achieves the following results on the evaluation set:
|
30 |
+
- Loss: 6.0273
|
31 |
+
- Accuracy: 0.1497
|
32 |
|
33 |
## Model description
|
34 |
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 14.21,
|
3 |
+
"eval_accuracy": 0.1496531706247267,
|
4 |
+
"eval_loss": 6.027312278747559,
|
5 |
+
"eval_runtime": 496.2332,
|
6 |
+
"eval_samples": 308356,
|
7 |
+
"eval_samples_per_second": 621.393,
|
8 |
+
"eval_steps_per_second": 3.454,
|
9 |
+
"perplexity": 414.5992034488068,
|
10 |
+
"train_loss": 6.210341006701539,
|
11 |
+
"train_runtime": 197999.3651,
|
12 |
+
"train_samples": 5858758,
|
13 |
+
"train_samples_per_second": 2958.978,
|
14 |
+
"train_steps_per_second": 16.439
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 14.21,
|
3 |
+
"eval_accuracy": 0.1496531706247267,
|
4 |
+
"eval_loss": 6.027312278747559,
|
5 |
+
"eval_runtime": 496.2332,
|
6 |
+
"eval_samples": 308356,
|
7 |
+
"eval_samples_per_second": 621.393,
|
8 |
+
"eval_steps_per_second": 3.454,
|
9 |
+
"perplexity": 414.5992034488068
|
10 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 14.21,
|
3 |
+
"train_loss": 6.210341006701539,
|
4 |
+
"train_runtime": 197999.3651,
|
5 |
+
"train_samples": 5858758,
|
6 |
+
"train_samples_per_second": 2958.978,
|
7 |
+
"train_steps_per_second": 16.439
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|