Mat17892 commited on
Commit
0fb1003
1 Parent(s): 9ae13ed

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 [Mat17892/t5small_enfr_opus](https://huggingface.co/Mat17892/t5small_enfr_opus) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.3217
22
- - Bleu: 7.3648
23
- - Gen Len: 17.5145
24
 
25
  ## Model description
26
 
@@ -45,26 +45,19 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
- - num_epochs: 8
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
54
- |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
55
- | 1.542 | 1.0 | 6355 | 1.3460 | 7.1462 | 17.5281 |
56
- | 1.5196 | 2.0 | 12710 | 1.3419 | 7.2241 | 17.5219 |
57
- | 1.5005 | 3.0 | 19065 | 1.3346 | 7.3005 | 17.5137 |
58
- | 1.5083 | 4.0 | 25420 | 1.3298 | 7.3326 | 17.5174 |
59
- | 1.4999 | 5.0 | 31775 | 1.3269 | 7.3337 | 17.5214 |
60
- | 1.4906 | 6.0 | 38130 | 1.3237 | 7.3359 | 17.5185 |
61
- | 1.4944 | 7.0 | 44485 | 1.3223 | 7.3664 | 17.5161 |
62
- | 1.5018 | 8.0 | 50840 | 1.3217 | 7.3648 | 17.5145 |
63
 
64
 
65
  ### Framework versions
66
 
67
- - Transformers 4.46.2
68
  - Pytorch 2.5.1+cu121
69
  - Datasets 3.1.0
70
  - Tokenizers 0.20.3
 
18
 
19
  This model is a fine-tuned version of [Mat17892/t5small_enfr_opus](https://huggingface.co/Mat17892/t5small_enfr_opus) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7579
22
+ - Bleu: 9.1617
23
+ - Gen Len: 18.2621
24
 
25
  ## Model description
26
 
 
45
  - seed: 42
46
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 1
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
55
+ | 0.8703 | 1.0 | 7500 | 0.7579 | 9.1617 | 18.2621 |
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
59
 
60
+ - Transformers 4.46.3
61
  - Pytorch 2.5.1+cu121
62
  - Datasets 3.1.0
63
  - Tokenizers 0.20.3
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
4
  "pad_token_id": 0,
5
- "transformers_version": "4.46.2"
6
  }
 
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
4
  "pad_token_id": 0,
5
+ "transformers_version": "4.46.3"
6
  }
runs/Dec06_21-46-07_9f8b679bc043/events.out.tfevents.1733521567.9f8b679bc043.170.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f2c3fe4fd57dada5bd7c8dc7ee9208e7e5ce08d896178ef4ecc8e6fb5339027
3
- size 9253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c6dde74523488cddbe7e0a65243ed20b6670a0ced57fcaf5730e395d0964bf4
3
+ size 9977