Hugging Face's logo

sandernotenbaert
/
okai-musiclang-content-t5

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
sandernotenbaert commited on
Commit
fd14110
·
verified ·
1 Parent(s): 05372a9

Model save

Browse files
Files changed (3) hide show
  1. README.md +6 -9
  2. final_model/model.safetensors +1 -1
  3. final_model/training_args.bin +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
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: 1.5639
18
 
19
  ## Model description
20
 
@@ -40,8 +41,8 @@ The following hyperparameters were used during training:
40
  - gradient_accumulation_steps: 4
41
  - total_train_batch_size: 96
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
44
- - lr_scheduler_warmup_steps: 1000
45
  - num_epochs: 4
46
  - mixed_precision_training: Native AMP
47
 
@@ -49,11 +50,7 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:------:|:----:|:---------------:|
52
- | 2.7352 | 0.6954 | 500 | 2.6036 |
53
- | 2.2123 | 1.3908 | 1000 | 2.0960 |
54
- | 1.8487 | 2.0862 | 1500 | 1.7925 |
55
- | 1.713 | 2.7816 | 2000 | 1.6366 |
56
- | 1.6597 | 3.4771 | 2500 | 1.5639 |
57
 
58
 
59
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ base_model: sandernotenbaert/okai-musiclang-content-t5
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # okai-musiclang-content-t5
15
 
16
+ This model is a fine-tuned version of [sandernotenbaert/okai-musiclang-content-t5](https://huggingface.co/sandernotenbaert/okai-musiclang-content-t5) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.5040
19
 
20
  ## Model description
21
 
 
41
  - gradient_accumulation_steps: 4
42
  - total_train_batch_size: 96
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: constant_with_warmup
45
+ - lr_scheduler_warmup_steps: 200
46
  - num_epochs: 4
47
  - mixed_precision_training: Native AMP
48
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 1.5731 | 2.4764 | 500 | 1.5040 |
 
 
 
 
54
 
55
 
56
  ### Framework versions
final_model/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68c31c91b324264716d6a08bbe92198046f468c06980655b5f3da0003e65601c
3
  size 362303176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fea8921cf12d4a5d9e2fddeda14297240eb814e6b2f5cb6284bdf0760cf8536
3
  size 362303176
final_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4072d75f3bcfbefc199402079a3fa943a2dce1fccc31ce7f3a881b0731caf594
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:258e93bb7afb81bdb858196bb5d9459c58151567faf53e997e6292b1461756ae
3
  size 5624