ar5entum commited on
Commit
4202ea0
·
verified ·
1 Parent(s): 6582be2

End of training

Browse files
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-mul-en](https://huggingface.co/Helsinki-NLP/opus-mt-mul-en) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Bleu: 78.0784
22
- - Gen Len: 74.6804
23
- - Loss: 0.1472
24
 
25
  ## Model description
26
 
 
18
 
19
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-mul-en](https://huggingface.co/Helsinki-NLP/opus-mt-mul-en) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1450
22
+ - Bleu: 77.8649
23
+ - Gen Len: 74.8945
24
 
25
  ## Model description
26
 
all_results.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "eval_bleu": 77.8649,
4
+ "eval_gen_len": 74.8945,
5
+ "eval_loss": 0.14499661326408386,
6
+ "eval_runtime": 55.7236,
7
+ "eval_samples": 1042,
8
+ "eval_samples_per_second": 18.699,
9
+ "eval_steps_per_second": 0.197,
10
+ "predict_bleu": 77.8649,
11
+ "predict_gen_len": 74.8945,
12
+ "predict_loss": 0.14499661326408386,
13
+ "predict_runtime": 52.4823,
14
+ "predict_samples": 1042,
15
+ "predict_samples_per_second": 19.854,
16
+ "predict_steps_per_second": 0.21,
17
+ "total_flos": 1.544729654989947e+17,
18
+ "train_loss": 0.0,
19
+ "train_runtime": 0.2648,
20
+ "train_samples": 111736,
21
+ "train_samples_per_second": 12659125.519,
22
+ "train_steps_per_second": 63331.882
23
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "eval_bleu": 77.8649,
4
+ "eval_gen_len": 74.8945,
5
+ "eval_loss": 0.14499661326408386,
6
+ "eval_runtime": 55.7236,
7
+ "eval_samples": 1042,
8
+ "eval_samples_per_second": 18.699,
9
+ "eval_steps_per_second": 0.197
10
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 77.8649,
3
+ "predict_gen_len": 74.8945,
4
+ "predict_loss": 0.14499661326408386,
5
+ "predict_runtime": 52.4823,
6
+ "predict_samples": 1042,
7
+ "predict_samples_per_second": 19.854,
8
+ "predict_steps_per_second": 0.21
9
+ }
runs/Aug17_09-33-09_e2e-68-229/events.out.tfevents.1723901718.e2e-68-229 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fc76d7809aab04de9c75b1c168011b7a006aedab8dadded79fd7df60b109faa
3
+ size 40
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "total_flos": 1.544729654989947e+17,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.2648,
6
+ "train_samples": 111736,
7
+ "train_samples_per_second": 12659125.519,
8
+ "train_steps_per_second": 63331.882
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff