metadata
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
model-index:
- name: deepseek-coder-6.7b-instruct-TAVGEN-finetune
results: []
deepseek-coder-6.7b-instruct-TAVGEN-finetune
This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3206
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5933 | 0.21 | 25 | 0.4703 |
| 0.4589 | 0.42 | 50 | 0.4026 |
| 0.4226 | 0.63 | 75 | 0.3733 |
| 0.3968 | 0.84 | 100 | 0.3605 |
| 0.3645 | 1.05 | 125 | 0.3483 |
| 0.355 | 1.26 | 150 | 0.3421 |
| 0.3318 | 1.47 | 175 | 0.3365 |
| 0.3377 | 1.68 | 200 | 0.3318 |
| 0.3111 | 1.89 | 225 | 0.3287 |
| 0.3324 | 2.1 | 250 | 0.3242 |
| 0.2757 | 2.31 | 275 | 0.3254 |
| 0.3061 | 2.52 | 300 | 0.3253 |
| 0.3015 | 2.73 | 325 | 0.3218 |
| 0.2674 | 2.94 | 350 | 0.3209 |
| 0.2579 | 3.15 | 375 | 0.3208 |
| 0.2601 | 3.36 | 400 | 0.3225 |
| 0.2396 | 3.57 | 425 | 0.3222 |
| 0.2504 | 3.78 | 450 | 0.3220 |
| 0.2786 | 3.99 | 475 | 0.3206 |
| 0.2357 | 4.2 | 500 | 0.3206 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.38.0.dev0
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.0