craa commited on
Commit
2ac87f2
·
verified ·
1 Parent(s): a6dd4e3

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -2
  2. all_results.json +16 -0
  3. eval_results.json +10 -0
  4. train_results.json +9 -0
  5. trainer_state.json +0 -0
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 3.5417
21
- - Accuracy: 0.3750
22
 
23
  ## Model description
24
 
 
17
 
18
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.5548
21
+ - Accuracy: 0.3700
22
 
23
  ## Model description
24
 
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 28.813053097345133,
3
+ "eval_accuracy": 0.37002520138009964,
4
+ "eval_loss": 3.5547902584075928,
5
+ "eval_runtime": 53.5464,
6
+ "eval_samples": 16651,
7
+ "eval_samples_per_second": 310.964,
8
+ "eval_steps_per_second": 19.441,
9
+ "perplexity": 34.98048233614886,
10
+ "total_flos": 2.068919715889152e+18,
11
+ "train_loss": 1.2580723141756924,
12
+ "train_runtime": 17335.8607,
13
+ "train_samples": 274807,
14
+ "train_samples_per_second": 792.597,
15
+ "train_steps_per_second": 9.91
16
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 28.813053097345133,
3
+ "eval_accuracy": 0.37002520138009964,
4
+ "eval_loss": 3.5547902584075928,
5
+ "eval_runtime": 53.5464,
6
+ "eval_samples": 16651,
7
+ "eval_samples_per_second": 310.964,
8
+ "eval_steps_per_second": 19.441,
9
+ "perplexity": 34.98048233614886
10
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 28.813053097345133,
3
+ "total_flos": 2.068919715889152e+18,
4
+ "train_loss": 1.2580723141756924,
5
+ "train_runtime": 17335.8607,
6
+ "train_samples": 274807,
7
+ "train_samples_per_second": 792.597,
8
+ "train_steps_per_second": 9.91
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff