|
--- |
|
base_model: ybelkada/falcon-7b-sharded-bf16 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: my_thesis |
|
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. --> |
|
|
|
# my_thesis |
|
|
|
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: 1.2940 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.0695 | 0.1794 | 20 | 1.7234 | |
|
| 1.7581 | 0.3587 | 40 | 1.3875 | |
|
| 1.6152 | 0.5381 | 60 | 1.3234 | |
|
| 1.7435 | 0.7175 | 80 | 1.2944 | |
|
| 1.3584 | 0.8969 | 100 | 1.2529 | |
|
| 1.385 | 1.0762 | 120 | 1.2271 | |
|
| 1.3231 | 1.2556 | 140 | 1.3666 | |
|
| 1.2051 | 1.4350 | 160 | 1.2044 | |
|
| 1.1207 | 1.6143 | 180 | 1.2379 | |
|
| 1.1716 | 1.7937 | 200 | 1.1969 | |
|
| 1.31 | 1.9731 | 220 | 1.2153 | |
|
| 0.9115 | 2.1525 | 240 | 1.2411 | |
|
| 0.7857 | 2.3318 | 260 | 1.2940 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.1.dev0 |
|
- Transformers 4.43.3 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
