metadata
base_model: RWKV/rwkv-raven-1b5
tags:
- generated_from_trainer
model-index:
- name: RWKV-1b5-finetuned-overfit
results: []
library_name: peft
RWKV-1b5-finetuned-overfit
This model is a fine-tuned version of RWKV/rwkv-raven-1b5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 67.8669
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6836 | 1.0 | 1 | 1.4181 |
| 1.5358 | 2.0 | 2 | 1.4378 |
| 0.7673 | 3.0 | 3 | 7.2988 |
| 0.3153 | 4.0 | 4 | 28.9362 |
| 0.0964 | 5.0 | 5 | 60.8725 |
| 0.0242 | 6.0 | 6 | 68.6885 |
| 0.0119 | 7.0 | 7 | 67.8234 |
| 0.0088 | 8.0 | 8 | 67.8669 |
Framework versions
- PEFT 0.4.0
- PEFT 0.4.0
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3