End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: NousResearch/CodeLlama-13b-hf-flash
|
| 4 |
+
tags:
|
| 5 |
+
- axolotl
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: ef1d817c-d307-4432-be40-8d62c1ccceed
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 16 |
+
<br>
|
| 17 |
+
|
| 18 |
+
# ef1d817c-d307-4432-be40-8d62c1ccceed
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [NousResearch/CodeLlama-13b-hf-flash](https://huggingface.co/NousResearch/CodeLlama-13b-hf-flash) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.2801
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.000212
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 120
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_steps: 50
|
| 50 |
+
- training_steps: 500
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| No log | 0.0000 | 1 | 2.2917 |
|
| 57 |
+
| 3.2582 | 0.0024 | 50 | 1.5773 |
|
| 58 |
+
| 3.0859 | 0.0047 | 100 | 1.4720 |
|
| 59 |
+
| 3.1501 | 0.0071 | 150 | 1.5418 |
|
| 60 |
+
| 3.0678 | 0.0094 | 200 | 1.5444 |
|
| 61 |
+
| 2.8509 | 0.0118 | 250 | 1.4362 |
|
| 62 |
+
| 2.949 | 0.0141 | 300 | 1.3197 |
|
| 63 |
+
| 2.7131 | 0.0165 | 350 | 1.2930 |
|
| 64 |
+
| 2.8697 | 0.0188 | 400 | 1.2848 |
|
| 65 |
+
| 2.7921 | 0.0212 | 450 | 1.2807 |
|
| 66 |
+
| 2.788 | 0.0235 | 500 | 1.2801 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- PEFT 0.13.2
|
| 72 |
+
- Transformers 4.46.0
|
| 73 |
+
- Pytorch 2.5.0+cu124
|
| 74 |
+
- Datasets 3.0.1
|
| 75 |
+
- Tokenizers 0.20.1
|