EnabledChat-v2-lora
This model is a fine-tuned version of 0x70DA/EnabledChat on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2828
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3247 | 0.07 | 200 | 1.3711 |
| 1.4053 | 0.14 | 400 | 1.3470 |
| 1.3431 | 0.21 | 600 | 1.3355 |
| 1.4012 | 0.27 | 800 | 1.3278 |
| 1.3189 | 0.34 | 1000 | 1.3235 |
| 1.3581 | 0.41 | 1200 | 1.3181 |
| 1.3417 | 0.48 | 1400 | 1.3138 |
| 1.3111 | 0.55 | 1600 | 1.3110 |
| 1.3547 | 0.62 | 1800 | 1.3068 |
| 1.3725 | 0.68 | 2000 | 1.3058 |
| 1.3574 | 0.75 | 2200 | 1.3028 |
| 1.3773 | 0.82 | 2400 | 1.2999 |
| 1.2944 | 0.89 | 2600 | 1.2979 |
| 1.2433 | 0.96 | 2800 | 1.2962 |
| 1.2349 | 1.03 | 3000 | 1.2952 |
| 1.3126 | 1.1 | 3200 | 1.2934 |
| 1.284 | 1.16 | 3400 | 1.2925 |
| 1.2194 | 1.23 | 3600 | 1.2912 |
| 1.2885 | 1.3 | 3800 | 1.2902 |
| 1.2159 | 1.37 | 4000 | 1.2888 |
| 1.2832 | 1.44 | 4200 | 1.2881 |
| 1.2233 | 1.51 | 4400 | 1.2868 |
| 1.2565 | 1.57 | 4600 | 1.2857 |
| 1.2618 | 1.64 | 4800 | 1.2855 |
| 1.3954 | 1.71 | 5000 | 1.2846 |
| 1.3082 | 1.78 | 5200 | 1.2840 |
| 1.3149 | 1.85 | 5400 | 1.2834 |
| 1.2558 | 1.92 | 5600 | 1.2830 |
| 1.2299 | 1.98 | 5800 | 1.2828 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.3