gokuls commited on
Commit
956a19c
1 Parent(s): 8029521

End of training

Browse files
Files changed (5) hide show
  1. README.md +15 -3
  2. all_results.json +15 -0
  3. eval_results.json +10 -0
  4. train_results.json +8 -0
  5. trainer_state.json +0 -0
README.md CHANGED
@@ -1,11 +1,23 @@
1
  ---
2
  tags:
3
  - generated_from_trainer
 
 
4
  metrics:
5
  - accuracy
6
  model-index:
7
  - name: HBERTv1_emb_compress_48_L10_H256_A4
8
- results: []
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,9 +25,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # HBERTv1_emb_compress_48_L10_H256_A4
15
 
16
- This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 6.0493
19
  - Accuracy: 0.1509
20
 
21
  ## Model description
 
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_emb_compress_48_L10_H256_A4
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: 0.15093352306316574
21
  ---
22
 
23
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
25
 
26
  # HBERTv1_emb_compress_48_L10_H256_A4
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: 6.0495
31
  - Accuracy: 0.1509
32
 
33
  ## Model description
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.15093352306316574,
4
+ "eval_loss": 6.049524307250977,
5
+ "eval_runtime": 766.2857,
6
+ "eval_samples": 308356,
7
+ "eval_samples_per_second": 402.403,
8
+ "eval_steps_per_second": 6.289,
9
+ "perplexity": 423.9113305289076,
10
+ "train_loss": 6.211948149485322,
11
+ "train_runtime": 192213.636,
12
+ "train_samples": 5858758,
13
+ "train_samples_per_second": 152.402,
14
+ "train_steps_per_second": 2.381
15
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.15093352306316574,
4
+ "eval_loss": 6.049524307250977,
5
+ "eval_runtime": 766.2857,
6
+ "eval_samples": 308356,
7
+ "eval_samples_per_second": 402.403,
8
+ "eval_steps_per_second": 6.289,
9
+ "perplexity": 423.9113305289076
10
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 6.211948149485322,
4
+ "train_runtime": 192213.636,
5
+ "train_samples": 5858758,
6
+ "train_samples_per_second": 152.402,
7
+ "train_steps_per_second": 2.381
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff