Hugging Face's logo

lwit
/
om_de_en

Text2Text Generation
Transformers
TensorBoard
Safetensors
mbart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
lwit commited on
Commit
9fe76c8
•
1 Parent(s): b5951f5

End of training

Browse files
Files changed (4) hide show
  1. README.md +9 -15
  2. generation_config.json +9 -3
  3. model.safetensors +1 -1
  4. runs/Mar05_17-16-24_c657dbb4527e/events.out.tfevents.1709658985.c657dbb4527e.18602.0 +2 -2
README.md CHANGED
@@ -1,10 +1,7 @@
1
  ---
2
- license: apache-2.0
3
- base_model: google-t5/t5-base
4
  tags:
5
  - generated_from_trainer
6
- metrics:
7
- - bleu
8
  model-index:
9
  - name: om_de_en_model
10
  results: []
@@ -15,11 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # om_de_en_model
17
 
18
- This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.9986
21
- - Bleu: 21.386
22
- - Gen Len: 11.0078
23
 
24
  ## Model description
25
 
@@ -39,20 +34,19 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-05
42
- - train_batch_size: 16
43
- - eval_batch_size: 16
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - num_epochs: 2
48
- - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
- |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
54
- | No log | 1.0 | 257 | 1.0632 | 19.91 | 11.0497 |
55
- | 1.4386 | 2.0 | 514 | 0.9986 | 21.386 | 11.0078 |
56
 
57
 
58
  ### Framework versions
 
1
  ---
2
+ base_model: facebook/mbart-large-50-many-to-many-mmt
 
3
  tags:
4
  - generated_from_trainer
 
 
5
  model-index:
6
  - name: om_de_en_model
7
  results: []
 
12
 
13
  # om_de_en_model
14
 
15
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0566
 
 
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
  - num_epochs: 2
 
43
 
44
  ### Training results
45
 
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 0.9754 | 1.0 | 513 | 0.0595 |
49
+ | 0.042 | 2.0 | 1026 | 0.0566 |
50
 
51
 
52
  ### Framework versions
generation_config.json CHANGED
@@ -1,6 +1,12 @@
1
  {
2
- "decoder_start_token_id": 0,
3
- "eos_token_id": 1,
4
- "pad_token_id": 0,
 
 
 
 
 
 
5
  "transformers_version": "4.38.1"
6
  }
 
1
  {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
  "transformers_version": "4.38.1"
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6f34a14dd098afeb71cc42c9e85d3f25a6b9b34378350018c0e5ed550311e85
3
  size 2444578688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0399848fd2dd21f19e1705704060d11d4711fc7475831a8be5ec46dc4070a215
3
  size 2444578688
runs/Mar05_17-16-24_c657dbb4527e/events.out.tfevents.1709658985.c657dbb4527e.18602.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d94738def321093518ffedf9aa0338ff21f51d39ba9c3e7fbc10fb5f0dbaffd2
3
- size 6153
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdbfa67c39331877013bef453b9a08ac55f9434f458fd4828f326ea3b80a8f91
3
+ size 6778