Hugging Face's logo

wajdii
/
results

Text2Text Generation
Transformers
PyTorch
m2m_100
Generated from Trainer
Inference Endpoints
Model card Files Community
wajdii commited on
Commit
97c90be
•
1 Parent(s): caa70ab

second_model

Browse files
Files changed (4) hide show
  1. README.md +16 -16
  2. pytorch_model.bin +1 -1
  3. tokenizer.json +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1972
19
 
20
  ## Model description
21
 
@@ -35,8 +35,8 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
- - train_batch_size: 16
39
- - eval_batch_size: 16
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
@@ -44,23 +44,23 @@ The following hyperparameters were used during training:
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:----:|:---------------:|
49
- | 5.257 | 1.0 | 505 | 1.4156 |
50
- | 0.4709 | 2.0 | 1010 | 0.2085 |
51
- | 0.1929 | 3.0 | 1515 | 0.1996 |
52
- | 0.1762 | 4.0 | 2020 | 0.1973 |
53
- | 0.1649 | 5.0 | 2525 | 0.1966 |
54
- | 0.158 | 6.0 | 3030 | 0.1964 |
55
- | 0.1511 | 7.0 | 3535 | 0.1964 |
56
- | 0.1456 | 8.0 | 4040 | 0.1968 |
57
- | 0.144 | 9.0 | 4545 | 0.1971 |
58
- | 0.1421 | 10.0 | 5050 | 0.1972 |
59
 
60
 
61
  ### Framework versions
62
 
63
  - Transformers 4.33.0
64
  - Pytorch 2.2.1
65
- - Datasets 2.19.1
66
  - Tokenizers 0.13.3
 
15
 
16
  This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.2003
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
 
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 0.4367 | 1.0 | 1009 | 0.2132 |
50
+ | 0.1949 | 2.0 | 2018 | 0.1991 |
51
+ | 0.1744 | 3.0 | 3027 | 0.1956 |
52
+ | 0.1593 | 4.0 | 4036 | 0.1949 |
53
+ | 0.1527 | 5.0 | 5045 | 0.1957 |
54
+ | 0.1419 | 6.0 | 6054 | 0.1962 |
55
+ | 0.1338 | 7.0 | 7063 | 0.1982 |
56
+ | 0.1276 | 8.0 | 8072 | 0.1988 |
57
+ | 0.1239 | 9.0 | 9081 | 0.1996 |
58
+ | 0.1215 | 10.0 | 10090 | 0.2003 |
59
 
60
 
61
  ### Framework versions
62
 
63
  - Transformers 4.33.0
64
  - Pytorch 2.2.1
65
+ - Datasets 2.19.2
66
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f9a6f06f616805e1f2b1a19642542d1dcbbe55d6b3c73034ddeb903991273fa
3
  size 2460469182
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da0108c07e8d27da4a915f5eb671c132b138706d83ade7c14377c44aed209e7
3
  size 2460469182
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ac789ad7dabea44d41537822d48c516ba358374c51813e2cba78c006e150c94
3
- size 17331224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5acc0bc2a48b6c16ee9854bd75bdb10bf95cadf1ededf6dce3af0a340b33a34
3
+ size 17331489
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3662193fa00dbc6aa189b2f93558da4ab4c2ba363a6122bae5d620f089e67252
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118b6f76cd6ec212cb1be95c35eabfaa8009ff76d3a77dff02401643e55bb83e
3
  size 4536