metadata
license: llama2
base_model: codellama/CodeLlama-7b-Instruct-hf
tags:
- generated_from_trainer
datasets:
- tmnam20/InstructNSText2SQL
model-index:
- name: codellama_instruct_pt_text2sql
results: []
codellama_instruct_pt_text2sql
This model is a fine-tuned version of codellama/CodeLlama-7b-Instruct-hf on the tmnam20/InstructNSText2SQL dataset. It achieves the following results on the evaluation set:
- Loss: 0.0150
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0693 | 0.22 | 2000 | 0.0589 |
| 0.047 | 0.45 | 4000 | 0.0396 |
| 0.0364 | 0.67 | 6000 | 0.0307 |
| 0.0311 | 0.89 | 8000 | 0.0278 |
| 0.0251 | 1.11 | 10000 | 0.0241 |
| 0.0243 | 1.34 | 12000 | 0.0228 |
| 0.0227 | 1.56 | 14000 | 0.0223 |
| 0.0212 | 1.78 | 16000 | 0.0201 |
| 0.0202 | 2.01 | 18000 | 0.0182 |
| 0.016 | 2.23 | 20000 | 0.0184 |
| 0.0156 | 2.45 | 22000 | 0.0179 |
| 0.015 | 2.67 | 24000 | 0.0173 |
| 0.0147 | 2.9 | 26000 | 0.0165 |
| 0.0112 | 3.12 | 28000 | 0.0165 |
| 0.0109 | 3.34 | 30000 | 0.0161 |
| 0.0109 | 3.56 | 32000 | 0.0155 |
| 0.0105 | 3.79 | 34000 | 0.0152 |
| 0.0104 | 4.01 | 36000 | 0.0150 |
| 0.0077 | 4.23 | 38000 | 0.0158 |
| 0.0078 | 4.46 | 40000 | 0.0151 |
| 0.0076 | 4.68 | 42000 | 0.0150 |
| 0.0077 | 4.9 | 44000 | 0.0150 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3