End of training
Browse files- README.md +19 -2
- all_results.json +15 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1700431280.serv-3330.2739418.2 +3 -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: model_v1_complete_training_wt_init_48_tiny_freeze_new
|
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 |
# model_v1_complete_training_wt_init_48_tiny_freeze_new
|
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: model_v1_complete_training_wt_init_48_tiny_freeze_new
|
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: 0.3687288371394257
|
21 |
---
|
22 |
|
23 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
25 |
|
26 |
# model_v1_complete_training_wt_init_48_tiny_freeze_new
|
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: 3.8361
|
31 |
+
- Accuracy: 0.3687
|
32 |
|
33 |
## Model description
|
34 |
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.56,
|
3 |
+
"eval_accuracy": 0.3687288371394257,
|
4 |
+
"eval_loss": 3.8361308574676514,
|
5 |
+
"eval_runtime": 373.4057,
|
6 |
+
"eval_samples": 308356,
|
7 |
+
"eval_samples_per_second": 825.793,
|
8 |
+
"eval_steps_per_second": 4.59,
|
9 |
+
"perplexity": 46.3458085484046,
|
10 |
+
"train_loss": 4.279609714360915,
|
11 |
+
"train_runtime": 179999.8831,
|
12 |
+
"train_samples": 5858758,
|
13 |
+
"train_samples_per_second": 3254.868,
|
14 |
+
"train_steps_per_second": 18.083
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.56,
|
3 |
+
"eval_accuracy": 0.3687288371394257,
|
4 |
+
"eval_loss": 3.8361308574676514,
|
5 |
+
"eval_runtime": 373.4057,
|
6 |
+
"eval_samples": 308356,
|
7 |
+
"eval_samples_per_second": 825.793,
|
8 |
+
"eval_steps_per_second": 4.59,
|
9 |
+
"perplexity": 46.3458085484046
|
10 |
+
}
|
logs/events.out.tfevents.1700431280.serv-3330.2739418.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0798475990e9dfcf05d35e7a5351c26bb1c908cab59cce5fff64cb174a75bb21
|
3 |
+
size 369
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.56,
|
3 |
+
"train_loss": 4.279609714360915,
|
4 |
+
"train_runtime": 179999.8831,
|
5 |
+
"train_samples": 5858758,
|
6 |
+
"train_samples_per_second": 3254.868,
|
7 |
+
"train_steps_per_second": 18.083
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|