sandernotenbaert commited on
Commit
9030105
·
verified ·
1 Parent(s): 9f102c2

Model save

Browse files
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-stable
14
 
15
- This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.4777
18
 
19
  ## Model description
20
 
@@ -42,22 +43,18 @@ 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: 1000
46
- - num_epochs: 4
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 5.0354 | 0.4637 | 500 | 4.7884 |
54
- | 4.2945 | 0.9274 | 1000 | 4.0578 |
55
- | 3.5799 | 1.3904 | 1500 | 3.3671 |
56
- | 3.1014 | 1.8542 | 2000 | 2.9227 |
57
- | 2.844 | 2.3172 | 2500 | 2.6748 |
58
- | 2.7116 | 2.7809 | 3000 | 2.5518 |
59
- | 2.6486 | 3.2439 | 3500 | 2.4961 |
60
- | 2.6292 | 3.7076 | 4000 | 2.4777 |
61
 
62
 
63
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ base_model: sandernotenbaert/okai-musiclang-content-t5-stable
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # okai-musiclang-content-t5-stable
15
 
16
+ This model is a fine-tuned version of [sandernotenbaert/okai-musiclang-content-t5-stable](https://huggingface.co/sandernotenbaert/okai-musiclang-content-t5-stable) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.1688
19
 
20
  ## Model description
21
 
 
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: 200
47
+ - num_epochs: 8
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 2.4966 | 1.6556 | 500 | 2.3381 |
55
+ | 2.3699 | 3.3113 | 1000 | 2.2373 |
56
+ | 2.3337 | 4.9669 | 1500 | 2.1878 |
57
+ | 2.3111 | 6.6225 | 2000 | 2.1688 |
 
 
 
 
58
 
59
 
60
  ### Framework versions
final_model/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21cbc5b38681c1ce98b36de0b7ba0fe4fb2e8dd97ff6b070c019951c5c2f6026
3
  size 11905784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b4abecdb3a31ece7b075d0e3110a07a564166483699d600c3cb92bd04a4280
3
  size 11905784
final_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27282a459303c45a7ea1398f33e94094a56e6c8251876f324aca9c4ad47de520
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cee358306e4b1f32ec6987fa9dcbd52fec3c59832605d08f3634555ae8ce487
3
  size 5624
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ac780081c300e24c76102e7c06db8ffbdf7d07bf148d4f75b22e23b6ea0f11d
3
  size 11905784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b4abecdb3a31ece7b075d0e3110a07a564166483699d600c3cb92bd04a4280
3
  size 11905784