|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
library_name: peft |
|
tags: |
|
- llama-factory |
|
- lora |
|
- generated_from_trainer |
|
base_model: bigscience/bloom-7b1 |
|
model-index: |
|
- name: BLOOM_AAID_structured_train_final_last |
|
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. --> |
|
|
|
# BLOOM_AAID_structured_train_final_last |
|
|
|
This model is a fine-tuned version of [bigscience/bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on the AAID_structured dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8413 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.817 | 0.2188 | 200 | 0.8413 | |
|
| 0.381 | 0.4375 | 400 | 0.8806 | |
|
| 0.3025 | 0.6563 | 600 | 1.0179 | |
|
| 0.1879 | 0.8750 | 800 | 1.1555 | |
|
| 0.0744 | 1.0938 | 1000 | 1.2785 | |
|
| 0.0231 | 1.3126 | 1200 | 1.3369 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
