Hugging Face's logo

sandernotenbaert
/
okai-musiclang-content-t5-small

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
sandernotenbaert commited on
Commit
4392969
·
verified ·
1 Parent(s): 79519df

Model save

Browse files
Files changed (4) hide show
  1. README.md +18 -17
  2. final_model/model.safetensors +1 -1
  3. final_model/training_args.bin +1 -1
  4. model.safetensors +1 -1
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
  library_name: transformers
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
@@ -12,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # okai-musiclang-content-t5-small
14
 
15
- This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 1.3428
18
 
19
  ## Model description
20
 
@@ -33,7 +34,7 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 0.0003
37
  - train_batch_size: 16
38
  - eval_batch_size: 8
39
  - seed: 42
@@ -42,7 +43,7 @@ The following hyperparameters were used during training:
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: cosine_with_restarts
44
  - lr_scheduler_warmup_ratio: 0.1
45
- - lr_scheduler_warmup_steps: 500
46
  - num_epochs: 3
47
  - mixed_precision_training: Native AMP
48
 
@@ -50,19 +51,19 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 3.0082 | 0.2226 | 500 | 2.8350 |
54
- | 2.3549 | 0.4452 | 1000 | 2.2682 |
55
- | 2.1648 | 0.6679 | 1500 | 2.0597 |
56
- | 2.0021 | 0.8905 | 2000 | 1.8762 |
57
- | 1.8782 | 1.1131 | 2500 | 1.7769 |
58
- | 1.7893 | 1.3357 | 3000 | 1.6655 |
59
- | 1.6761 | 1.5583 | 3500 | 1.5614 |
60
- | 1.5877 | 1.7809 | 4000 | 1.4621 |
61
- | 1.5383 | 2.0036 | 4500 | 1.4034 |
62
- | 1.5091 | 2.2262 | 5000 | 1.3646 |
63
- | 1.4742 | 2.4488 | 5500 | 1.3537 |
64
- | 1.482 | 2.6714 | 6000 | 1.3431 |
65
- | 1.4692 | 2.8940 | 6500 | 1.3428 |
66
 
67
 
68
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ base_model: sandernotenbaert/okai-musiclang-content-t5-small
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # okai-musiclang-content-t5-small
15
 
16
+ This model is a fine-tuned version of [sandernotenbaert/okai-musiclang-content-t5-small](https://huggingface.co/sandernotenbaert/okai-musiclang-content-t5-small) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.1968
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 8e-05
38
  - train_batch_size: 16
39
  - eval_batch_size: 8
40
  - seed: 42
 
43
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: cosine_with_restarts
45
  - lr_scheduler_warmup_ratio: 0.1
46
+ - lr_scheduler_warmup_steps: 100
47
  - num_epochs: 3
48
  - mixed_precision_training: Native AMP
49
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.4556 | 0.2226 | 500 | 1.3230 |
55
+ | 1.4166 | 0.4452 | 1000 | 1.3003 |
56
+ | 1.3956 | 0.6679 | 1500 | 1.2741 |
57
+ | 1.3865 | 0.8905 | 2000 | 1.2605 |
58
+ | 1.3589 | 1.1131 | 2500 | 1.2368 |
59
+ | 1.3514 | 1.3357 | 3000 | 1.2370 |
60
+ | 1.3349 | 1.5583 | 3500 | 1.2322 |
61
+ | 1.3163 | 1.7809 | 4000 | 1.2099 |
62
+ | 1.3183 | 2.0036 | 4500 | 1.2062 |
63
+ | 1.3204 | 2.2262 | 5000 | 1.2014 |
64
+ | 1.303 | 2.4488 | 5500 | 1.2008 |
65
+ | 1.3205 | 2.6714 | 6000 | 1.1953 |
66
+ | 1.3108 | 2.8940 | 6500 | 1.1968 |
67
 
68
 
69
  ### Framework versions
final_model/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc2342b29be4075e1e6e3fadbc7b179e137fd59127bac5b04c2f25457e1a1566
3
  size 30214176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61325e89d84579973b38c98781987f8afd3cd053d8337e3f3b91ea75704bc1d7
3
  size 30214176
final_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1827ce703b1ce899be1d32a980c6cc035ffe11339d42b259575cb4b159ea18ba
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0489e26a08d4adb896ba80f560909af07a15d3f4152845a26c5dc0f9d6d795ec
3
  size 5624
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ea50ad64579e31eb535f596e1d441e56fb7e99e7ea5466ce1ff1d62c524397d
3
  size 30214176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61325e89d84579973b38c98781987f8afd3cd053d8337e3f3b91ea75704bc1d7
3
  size 30214176