update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,83 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: lyrics-generator-v2
|
| 7 |
+
results: []
|
| 8 |
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# lyrics-generator-v2
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.1114
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-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: 10
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 3.4325 | 0.36 | 200 | 2.3267 |
|
| 49 |
+
| 2.4121 | 0.71 | 400 | 2.2693 |
|
| 50 |
+
| 2.3582 | 1.07 | 600 | 2.2401 |
|
| 51 |
+
| 2.2903 | 1.42 | 800 | 2.2182 |
|
| 52 |
+
| 2.2738 | 1.78 | 1000 | 2.2046 |
|
| 53 |
+
| 2.2322 | 2.14 | 1200 | 2.1922 |
|
| 54 |
+
| 2.1933 | 2.49 | 1400 | 2.1832 |
|
| 55 |
+
| 2.1944 | 2.85 | 1600 | 2.1736 |
|
| 56 |
+
| 2.1632 | 3.2 | 1800 | 2.1648 |
|
| 57 |
+
| 2.1366 | 3.56 | 2000 | 2.1554 |
|
| 58 |
+
| 2.1492 | 3.91 | 2200 | 2.1491 |
|
| 59 |
+
| 2.1108 | 4.27 | 2400 | 2.1472 |
|
| 60 |
+
| 2.0882 | 4.63 | 2600 | 2.1422 |
|
| 61 |
+
| 2.0971 | 4.98 | 2800 | 2.1343 |
|
| 62 |
+
| 2.0829 | 5.34 | 3000 | 2.1318 |
|
| 63 |
+
| 2.042 | 5.69 | 3200 | 2.1280 |
|
| 64 |
+
| 2.0375 | 6.05 | 3400 | 2.1261 |
|
| 65 |
+
| 2.0146 | 6.41 | 3600 | 2.1245 |
|
| 66 |
+
| 2.0551 | 6.76 | 3800 | 2.1217 |
|
| 67 |
+
| 1.992 | 7.12 | 4000 | 2.1182 |
|
| 68 |
+
| 1.9994 | 7.47 | 4200 | 2.1170 |
|
| 69 |
+
| 2.0189 | 7.83 | 4400 | 2.1156 |
|
| 70 |
+
| 1.9795 | 8.19 | 4600 | 2.1133 |
|
| 71 |
+
| 2.0101 | 8.54 | 4800 | 2.1143 |
|
| 72 |
+
| 1.9864 | 8.9 | 5000 | 2.1111 |
|
| 73 |
+
| 1.9602 | 9.25 | 5200 | 2.1120 |
|
| 74 |
+
| 1.9899 | 9.61 | 5400 | 2.1117 |
|
| 75 |
+
| 1.9928 | 9.96 | 5600 | 2.1114 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.25.1
|
| 81 |
+
- Pytorch 1.12.1+cu113
|
| 82 |
+
- Datasets 2.7.1
|
| 83 |
+
- Tokenizers 0.13.2
|