metadata
library_name: peft
license: apache-2.0
base_model: unsloth/mistral-7b-v0.2
tags:
- axolotl
- generated_from_trainer
model-index:
- name: b5af5b63-2744-4a7a-a494-5577cfe61051
results: []
b5af5b63-2744-4a7a-a494-5577cfe61051
This model is a fine-tuned version of unsloth/mistral-7b-v0.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2066
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: 0.000208
- 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 | 0.0002 | 1 | 3.8023 |
| 7.0134 | 0.0077 | 50 | 3.4676 |
| 7.03 | 0.0154 | 100 | 3.3677 |
| 6.2444 | 0.0231 | 150 | 3.1878 |
| 5.9664 | 0.0307 | 200 | 3.0007 |
| 5.6566 | 0.0384 | 250 | 2.7571 |
| 5.3847 | 0.0461 | 300 | 2.5729 |
| 5.0546 | 0.0538 | 350 | 2.4003 |
| 4.9947 | 0.0615 | 400 | 2.4386 |
| 5.0258 | 0.0692 | 450 | 2.2233 |
| 5.0228 | 0.0768 | 500 | 2.2066 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1