metadata
library_name: peft
license: apache-2.0
base_model: NousResearch/Genstruct-7B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 5d2e0439-654c-4778-8338-e27d168845e3
results: []
5d2e0439-654c-4778-8338-e27d168845e3
This model is a fine-tuned version of NousResearch/Genstruct-7B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2475
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: 0.000206
- 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 | 0.0014 | 1 | 3.1059 |
| 4.6831 | 0.0690 | 50 | 2.2452 |
| 5.8523 | 0.1380 | 100 | 2.1304 |
| 3.5201 | 0.2070 | 150 | 2.0188 |
| 3.1193 | 0.2761 | 200 | 2.0781 |
| 3.3962 | 0.3451 | 250 | 1.7017 |
| 3.1208 | 0.4141 | 300 | 1.5399 |
| 2.7352 | 0.4831 | 350 | 1.4595 |
| 2.6196 | 0.5521 | 400 | 1.2977 |
| 2.4864 | 0.6211 | 450 | 1.2511 |
| 2.5017 | 0.6901 | 500 | 1.2475 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1