metadata
license: llama2
base_model: codellama/CodeLlama-7b-Instruct-hf
tags:
- generated_from_trainer
model-index:
- name: code-llama-instruct-7b-text-to-sparql-axiom-prefix
results: []
code-llama-instruct-7b-text-to-sparql-axiom-prefix
This model is a fine-tuned version of codellama/CodeLlama-7b-Instruct-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0988
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: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.138 | 0.0710 | 20 | 1.0843 |
| 0.6257 | 0.1421 | 40 | 0.3315 |
| 0.1388 | 0.2131 | 60 | 0.1390 |
| 0.1293 | 0.2842 | 80 | 0.1269 |
| 0.1174 | 0.3552 | 100 | 0.1205 |
| 0.1097 | 0.4263 | 120 | 0.1176 |
| 0.1102 | 0.4973 | 140 | 0.1131 |
| 0.1073 | 0.5684 | 160 | 0.1083 |
| 0.1064 | 0.6394 | 180 | 0.1064 |
| 0.1079 | 0.7105 | 200 | 0.1053 |
| 0.1025 | 0.7815 | 220 | 0.1042 |
| 0.1038 | 0.8526 | 240 | 0.1029 |
| 0.0962 | 0.9236 | 260 | 0.1023 |
| 0.1021 | 0.9947 | 280 | 0.1013 |
| 0.098 | 1.0657 | 300 | 0.1008 |
| 0.0964 | 1.1368 | 320 | 0.1003 |
| 0.0961 | 1.2078 | 340 | 0.0997 |
| 0.0948 | 1.2789 | 360 | 0.0994 |
| 0.0955 | 1.3499 | 380 | 0.0989 |
| 0.0988 | 1.4210 | 400 | 0.0988 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.10.1
- Tokenizers 0.19.1