End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: wvangils/DistilGPT2-Beatles-Lyrics-finetuned
|
| 7 |
+
model-index:
|
| 8 |
+
- name: DistilGPT2-Beatles-Spotify-FinalVersion
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# DistilGPT2-Beatles-Spotify-FinalVersion
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [wvangils/DistilGPT2-Beatles-Lyrics-finetuned](https://huggingface.co/wvangils/DistilGPT2-Beatles-Lyrics-finetuned) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.8839
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 1
|
| 47 |
+
- training_steps: 500
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 2.1125 | 0.0 | 25 | 1.9245 |
|
| 54 |
+
| 2.1035 | 0.0 | 50 | 1.9315 |
|
| 55 |
+
| 2.1064 | 0.0 | 75 | 1.9184 |
|
| 56 |
+
| 2.0874 | 0.0 | 100 | 1.9101 |
|
| 57 |
+
| 2.0948 | 0.0 | 125 | 1.9143 |
|
| 58 |
+
| 2.1088 | 0.0 | 150 | 1.8953 |
|
| 59 |
+
| 2.0612 | 0.01 | 175 | 1.9130 |
|
| 60 |
+
| 2.0828 | 0.01 | 200 | 1.9046 |
|
| 61 |
+
| 2.0676 | 0.01 | 225 | 1.8950 |
|
| 62 |
+
| 2.072 | 0.01 | 250 | 1.9092 |
|
| 63 |
+
| 2.0748 | 0.01 | 275 | 1.8814 |
|
| 64 |
+
| 2.0769 | 0.01 | 300 | 1.8948 |
|
| 65 |
+
| 2.068 | 0.01 | 325 | 1.8921 |
|
| 66 |
+
| 2.0513 | 0.01 | 350 | 1.8904 |
|
| 67 |
+
| 2.0686 | 0.01 | 375 | 1.8794 |
|
| 68 |
+
| 2.0702 | 0.01 | 400 | 1.8800 |
|
| 69 |
+
| 2.059 | 0.01 | 425 | 1.8780 |
|
| 70 |
+
| 2.0562 | 0.01 | 450 | 1.8841 |
|
| 71 |
+
| 2.0705 | 0.01 | 475 | 1.8824 |
|
| 72 |
+
| 2.0675 | 0.02 | 500 | 1.8839 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- PEFT 0.8.2
|
| 78 |
+
- Transformers 4.38.1
|
| 79 |
+
- Pytorch 1.13.1
|
| 80 |
+
- Datasets 2.17.0
|
| 81 |
+
- Tokenizers 0.15.2
|