metadata
library_name: peft
license: apache-2.0
base_model: heegyu/WizardVicuna-open-llama-3b-v2
tags:
- axolotl
- generated_from_trainer
model-index:
- name: b0417515-f9e6-4ef6-bba5-c3542aa0139f
results: []
b0417515-f9e6-4ef6-bba5-c3542aa0139f
This model is a fine-tuned version of heegyu/WizardVicuna-open-llama-3b-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9573
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: 0.000201
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0004 | 1 | 2.9044 |
| 2.1977 | 0.0180 | 50 | 2.3285 |
| 2.1461 | 0.0360 | 100 | 2.2165 |
| 2.068 | 0.0540 | 150 | 2.1610 |
| 2.0445 | 0.0721 | 200 | 2.1003 |
| 1.9553 | 0.0901 | 250 | 2.0650 |
| 1.8413 | 0.1081 | 300 | 2.0259 |
| 1.8631 | 0.1261 | 350 | 1.9985 |
| 1.8504 | 0.1441 | 400 | 1.9718 |
| 1.8513 | 0.1621 | 450 | 1.9626 |
| 1.8913 | 0.1801 | 500 | 1.9573 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1