codellama-finetune
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: llama2
|
| 3 |
base_model: codellama/CodeLlama-7b-hf
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
- name: lora-fine-tuning-llama2-SQL-lora-codellama
|
|
@@ -14,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# lora-fine-tuning-llama2-SQL-lora-codellama
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -43,6 +47,28 @@ The following hyperparameters were used during training:
|
|
| 43 |
- lr_scheduler_warmup_ratio: 0.03
|
| 44 |
- num_epochs: 1
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.35.2
|
|
|
|
| 2 |
license: llama2
|
| 3 |
base_model: codellama/CodeLlama-7b-hf
|
| 4 |
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: lora-fine-tuning-llama2-SQL-lora-codellama
|
|
|
|
| 16 |
# lora-fine-tuning-llama2-SQL-lora-codellama
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5720
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 47 |
- lr_scheduler_warmup_ratio: 0.03
|
| 48 |
- num_epochs: 1
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 2.7803 | 0.06 | 5 | 2.5059 |
|
| 55 |
+
| 1.2647 | 0.12 | 10 | 1.1731 |
|
| 56 |
+
| 0.8026 | 0.18 | 15 | 0.8834 |
|
| 57 |
+
| 0.6482 | 0.24 | 20 | 0.8281 |
|
| 58 |
+
| 0.8146 | 0.3 | 25 | 0.7858 |
|
| 59 |
+
| 0.7458 | 0.36 | 30 | 0.7275 |
|
| 60 |
+
| 0.5377 | 0.42 | 35 | 0.6520 |
|
| 61 |
+
| 0.5659 | 0.48 | 40 | 0.6560 |
|
| 62 |
+
| 0.6104 | 0.54 | 45 | 0.6101 |
|
| 63 |
+
| 0.6253 | 0.6 | 50 | 0.6024 |
|
| 64 |
+
| 0.4878 | 0.66 | 55 | 0.5891 |
|
| 65 |
+
| 0.4777 | 0.72 | 60 | 0.5830 |
|
| 66 |
+
| 0.634 | 0.78 | 65 | 0.5831 |
|
| 67 |
+
| 0.5562 | 0.84 | 70 | 0.5771 |
|
| 68 |
+
| 0.4696 | 0.9 | 75 | 0.5734 |
|
| 69 |
+
| 0.4193 | 0.96 | 80 | 0.5720 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
### Framework versions
|
| 73 |
|
| 74 |
- Transformers 4.35.2
|