Hugging Face's logo

sophiebui
/
test-translation

Text2Text Generation
Transformers
TensorBoard
Safetensors
m2m_100
Generated from Trainer
Model card Files Metrics Community
sophiebui commited on
Commit
50f4874
·
verified ·
1 Parent(s): 4299170

Model save

Browse files
Files changed (4) hide show
  1. README.md +8 -8
  2. model/model.safetensors +1 -1
  3. model/tokenizer_config.json +2 -2
  4. model/training_args.bin +1 -1
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 [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6133
22
- - Bleu: 54.1156
23
- - Gen Len: 11.4547
24
 
25
  ## Model description
26
 
@@ -40,8 +40,8 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 2e-05
43
- - train_batch_size: 8
44
- - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
@@ -51,9 +51,9 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
54
- | No log | 1.0 | 438 | 0.6264 | 52.6786 | 11.4113 |
55
- | 0.7391 | 2.0 | 876 | 0.6079 | 53.6395 | 11.3927 |
56
- | 0.4148 | 3.0 | 1314 | 0.6133 | 54.1156 | 11.4547 |
57
 
58
 
59
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.3657
22
+ - Bleu: 32.2114
23
+ - Gen Len: 13.3333
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 2e-05
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 16
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
54
+ | No log | 1.0 | 1 | 1.4545 | 23.3073 | 14.0 |
55
+ | No log | 2.0 | 2 | 1.3870 | 32.2114 | 13.3333 |
56
+ | No log | 3.0 | 3 | 1.3657 | 32.2114 | 13.3333 |
57
 
58
 
59
  ### Framework versions
model/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:399ea74805448dc71ba1352f01343683355e01c595f227e773919b71087301a9
3
  size 1935681888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d4bb8181169a7e23a9cc16262cb8275036dcdc02a8b01af9f1b7253e73b31c
3
  size 1935681888
model/tokenizer_config.json CHANGED
@@ -944,8 +944,8 @@
944
  "pad_token": "<pad>",
945
  "sep_token": "</s>",
946
  "sp_model_kwargs": {},
947
- "src_lang": "ru",
948
- "tgt_lang": "en",
949
  "tokenizer_class": "M2M100Tokenizer",
950
  "unk_token": "<unk>"
951
  }
 
944
  "pad_token": "<pad>",
945
  "sep_token": "</s>",
946
  "sp_model_kwargs": {},
947
+ "src_lang": "en",
948
+ "tgt_lang": "ru",
949
  "tokenizer_class": "M2M100Tokenizer",
950
  "unk_token": "<unk>"
951
  }
model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c084f29fb0585345bbc61d3dce59c747d0e6493407d0cb3dc17acedac28b54
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16826306dd663b8dc849b383fafc63272b3a0e5a9cbf92b9f1e55653c01493a4
3
  size 5304