ModelWithMidiTok
Browse files- README.md +85 -0
- generation_config.json +6 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: ModelWithMidiTok
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# ModelWithMidiTok
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 8.2405
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 2e-05
|
| 36 |
+
- train_batch_size: 8
|
| 37 |
+
- eval_batch_size: 8
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 30
|
| 42 |
+
- mixed_precision_training: Native AMP
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| No log | 1.0 | 138 | 9.7069 |
|
| 49 |
+
| No log | 2.0 | 276 | 9.3817 |
|
| 50 |
+
| No log | 3.0 | 414 | 9.2525 |
|
| 51 |
+
| 9.5531 | 4.0 | 552 | 9.2097 |
|
| 52 |
+
| 9.5531 | 5.0 | 690 | 9.1881 |
|
| 53 |
+
| 9.5531 | 6.0 | 828 | 9.1586 |
|
| 54 |
+
| 9.5531 | 7.0 | 966 | 9.1142 |
|
| 55 |
+
| 9.1813 | 8.0 | 1104 | 9.0502 |
|
| 56 |
+
| 9.1813 | 9.0 | 1242 | 8.9741 |
|
| 57 |
+
| 9.1813 | 10.0 | 1380 | 8.8876 |
|
| 58 |
+
| 8.9874 | 11.0 | 1518 | 8.8039 |
|
| 59 |
+
| 8.9874 | 12.0 | 1656 | 8.7257 |
|
| 60 |
+
| 8.9874 | 13.0 | 1794 | 8.6524 |
|
| 61 |
+
| 8.9874 | 14.0 | 1932 | 8.5897 |
|
| 62 |
+
| 8.7156 | 15.0 | 2070 | 8.5348 |
|
| 63 |
+
| 8.7156 | 16.0 | 2208 | 8.4827 |
|
| 64 |
+
| 8.7156 | 17.0 | 2346 | 8.4419 |
|
| 65 |
+
| 8.7156 | 18.0 | 2484 | 8.4083 |
|
| 66 |
+
| 8.509 | 19.0 | 2622 | 8.3763 |
|
| 67 |
+
| 8.509 | 20.0 | 2760 | 8.3504 |
|
| 68 |
+
| 8.509 | 21.0 | 2898 | 8.3271 |
|
| 69 |
+
| 8.3922 | 22.0 | 3036 | 8.3093 |
|
| 70 |
+
| 8.3922 | 23.0 | 3174 | 8.2929 |
|
| 71 |
+
| 8.3922 | 24.0 | 3312 | 8.2786 |
|
| 72 |
+
| 8.3922 | 25.0 | 3450 | 8.2666 |
|
| 73 |
+
| 8.3214 | 26.0 | 3588 | 8.2577 |
|
| 74 |
+
| 8.3214 | 27.0 | 3726 | 8.2494 |
|
| 75 |
+
| 8.3214 | 28.0 | 3864 | 8.2447 |
|
| 76 |
+
| 8.2867 | 29.0 | 4002 | 8.2412 |
|
| 77 |
+
| 8.2867 | 30.0 | 4140 | 8.2405 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.41.2
|
| 83 |
+
- Pytorch 2.3.0+cu121
|
| 84 |
+
- Datasets 2.19.1
|
| 85 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.41.2"
|
| 6 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 95853952
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4813426080769e8fec50eebcdb959f898a32377f8c8e62bedc2cc075b16b0f1
|
| 3 |
size 95853952
|