metadata
license: apache-2.0
base_model: openlm-research/open_llama_3b_v2
tags:
- generated_from_trainer
model-index:
- name: qlora-out
results: []
qlora-out
This model is a fine-tuned version of openlm-research/open_llama_3b_v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9901
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.419 | 0.0 | 1 | 1.6021 |
| 1.1683 | 0.05 | 282 | 1.1232 |
| 1.0823 | 0.1 | 564 | 1.0956 |
| 0.9881 | 0.15 | 846 | 1.0733 |
| 0.5434 | 0.2 | 1128 | 1.0653 |
| 1.0669 | 0.25 | 1410 | 1.0520 |
| 1.2484 | 0.3 | 1692 | 1.0401 |
| 1.3012 | 0.35 | 1974 | 1.0445 |
| 1.2746 | 0.4 | 2256 | 1.0243 |
| 1.2341 | 0.45 | 2538 | 1.0230 |
| 1.0461 | 0.5 | 2820 | 1.0148 |
| 1.0813 | 0.55 | 3102 | 1.0070 |
| 1.1375 | 0.6 | 3384 | 1.0061 |
| 1.0052 | 0.65 | 3666 | 1.0007 |
| 1.171 | 0.7 | 3948 | 0.9966 |
| 1.0764 | 0.75 | 4230 | 0.9948 |
| 1.146 | 0.8 | 4512 | 0.9924 |
| 1.2213 | 0.85 | 4794 | 0.9918 |
| 1.1138 | 0.9 | 5076 | 0.9907 |
| 1.0635 | 0.95 | 5358 | 0.9901 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1