Hugging Face's logo

za17
/
helsinki-biomedical-finetuned

Translation
Transformers
Safetensors
marian
text2text-generation
Generated from Trainer
Inference Endpoints
Model card Files Community
za17 commited on
Commit
49711c8
•
1 Parent(s): 2167636

Revert to FT All model

Browse files
Files changed (3) hide show
  1. README.md +33 -11
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # helsinki-biomedical-finetuned
18
 
19
- This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-es](https://huggingface.co/Helsinki-NLP/opus-mt-en-es) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0875
22
- - Bleu: 43.9070
23
 
24
  ## Model description
25
 
@@ -38,24 +38,46 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 8e-07
42
  - train_batch_size: 8
43
  - eval_batch_size: 16
44
  - seed: 42
45
  - gradient_accumulation_steps: 4
46
  - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
- - lr_scheduler_type: cosine
49
- - num_epochs: 3
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Bleu |
55
- |:-------------:|:------:|:----:|:---------------:|:-------:|
56
- | No log | 0.9987 | 187 | 0.0890 | 43.7030 |
57
- | No log | 1.9973 | 374 | 0.0880 | 43.7818 |
58
- | 0.0947 | 2.9960 | 561 | 0.0875 | 43.9070 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
16
 
17
  # helsinki-biomedical-finetuned
18
 
19
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-es](https://huggingface.co/Helsinki-NLP/opus-mt-en-es) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0247
22
+ - Bleu: 55.6929
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 1.5e-05
42
  - train_batch_size: 8
43
  - eval_batch_size: 16
44
  - seed: 42
45
  - gradient_accumulation_steps: 4
46
  - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: reduce_lr_on_plateau
49
+ - num_epochs: 25
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Bleu |
55
+ |:-------------:|:-------:|:-----:|:---------------:|:-------:|
56
+ | 0.0289 | 0.9998 | 3293 | 0.0253 | 52.7060 |
57
+ | 0.0255 | 1.9998 | 6587 | 0.0238 | 53.6061 |
58
+ | 0.0228 | 2.9999 | 9881 | 0.0231 | 54.1920 |
59
+ | 0.0206 | 4.0 | 13175 | 0.0226 | 54.4549 |
60
+ | 0.0192 | 4.9998 | 16468 | 0.0224 | 54.5222 |
61
+ | 0.0176 | 5.9998 | 19762 | 0.0222 | 54.6624 |
62
+ | 0.0167 | 6.9999 | 23056 | 0.0221 | 55.0200 |
63
+ | 0.0154 | 8.0 | 26350 | 0.0223 | 53.3307 |
64
+ | 0.0147 | 8.9998 | 29643 | 0.0223 | 55.2185 |
65
+ | 0.0138 | 9.9998 | 32937 | 0.0224 | 54.9215 |
66
+ | 0.0133 | 10.9999 | 36231 | 0.0225 | 55.3672 |
67
+ | 0.0122 | 12.0 | 39525 | 0.0229 | 55.2831 |
68
+ | 0.0115 | 12.9998 | 42818 | 0.0231 | 55.2310 |
69
+ | 0.0108 | 13.9998 | 46112 | 0.0233 | 55.3215 |
70
+ | 0.0103 | 14.9999 | 49406 | 0.0234 | 55.3170 |
71
+ | 0.0096 | 16.0 | 52700 | 0.0237 | 55.3158 |
72
+ | 0.0089 | 16.9998 | 55993 | 0.0242 | 55.0178 |
73
+ | 0.0084 | 17.9998 | 59287 | 0.0243 | 55.1974 |
74
+ | 0.0072 | 18.9999 | 62581 | 0.0244 | 55.6011 |
75
+ | 0.007 | 20.0 | 65875 | 0.0245 | 55.5510 |
76
+ | 0.0069 | 20.9998 | 69168 | 0.0246 | 55.6178 |
77
+ | 0.0068 | 21.9998 | 72462 | 0.0246 | 55.7191 |
78
+ | 0.0068 | 22.9999 | 75756 | 0.0247 | 55.6917 |
79
+ | 0.0066 | 24.0 | 79050 | 0.0247 | 55.6962 |
80
+ | 0.0067 | 24.9943 | 82325 | 0.0247 | 55.6929 |
81
 
82
 
83
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8270085986f0253d764e56a4ca7d1dc839d0c9345d7e50b6957bfd72cbce7388
3
  size 309965092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6335ad8280fc181bac5297c034176c06781616753b847f6fa7feebc70ef5d7d5
3
  size 309965092
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e747c183dae3cb169560061858f8d235fcb25e6555f2915d4b7763b65e64965
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c23a95b52128c133143d8847bfa4f4a2dfd234abefea64204da3abdee5f725
3
  size 5176