metadata
license: other
base_model: baffo32/decapoda-research-llama-7B-hf
tags:
- generated_from_trainer
model-index:
- name: olinaweights
results: []
olinaweights
This model is a fine-tuned version of baffo32/decapoda-research-llama-7B-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0104
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.01 | 100 | 0.1012 |
| No log | 0.03 | 200 | 0.0426 |
| 0.1403 | 0.04 | 300 | 0.0455 |
| 0.1403 | 0.05 | 400 | 0.0258 |
| 0.0307 | 0.07 | 500 | 0.0227 |
| 0.0307 | 0.08 | 600 | 0.0200 |
| 0.0307 | 0.09 | 700 | 0.0164 |
| 0.019 | 0.11 | 800 | 0.0126 |
| 0.019 | 0.12 | 900 | 0.0117 |
| 0.0115 | 0.13 | 1000 | 0.0104 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1