|
--- |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: ybelkada/falcon-7b-sharded-bf16 |
|
model-index: |
|
- name: falcon-7b-sharded-bf16-finetuned-html-code-generation |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# falcon-7b-sharded-bf16-finetuned-html-code-generation |
|
|
|
This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2923 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- training_steps: 320 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.0699 | 0.18 | 20 | 1.7214 | |
|
| 1.7563 | 0.36 | 40 | 1.3886 | |
|
| 1.6152 | 0.54 | 60 | 1.3222 | |
|
| 1.7419 | 0.72 | 80 | 1.2957 | |
|
| 1.3596 | 0.9 | 100 | 1.2585 | |
|
| 1.3861 | 1.08 | 120 | 1.2264 | |
|
| 1.322 | 1.26 | 140 | 1.3842 | |
|
| 1.2072 | 1.43 | 160 | 1.2038 | |
|
| 1.1161 | 1.61 | 180 | 1.2392 | |
|
| 1.1715 | 1.79 | 200 | 1.1981 | |
|
| 1.3095 | 1.97 | 220 | 1.2134 | |
|
| 0.9115 | 2.15 | 240 | 1.2422 | |
|
| 0.7851 | 2.33 | 260 | 1.2923 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.2.dev0 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
