|
--- |
|
library_name: peft |
|
tags: |
|
- llama-factory |
|
- lora |
|
- generated_from_trainer |
|
base_model: google/gemma-7b |
|
model-index: |
|
- name: Gemma_ei_oc_unstructured_train_2e-4 |
|
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. --> |
|
|
|
# Gemma_ei_oc_unstructured_train_2e-4 |
|
|
|
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the emollms_ei_oc_unstructured dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1376 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 8 |
|
- 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 |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 3.0971 | 0.3604 | 10 | 0.1433 | |
|
| 0.1428 | 0.7207 | 20 | 0.1388 | |
|
| 0.1363 | 1.0811 | 30 | 0.1394 | |
|
| 0.136 | 1.4414 | 40 | 0.1378 | |
|
| 0.1359 | 1.8018 | 50 | 0.1413 | |
|
| 0.1364 | 2.1622 | 60 | 0.1376 | |
|
| 0.1336 | 2.5225 | 70 | 0.1382 | |
|
| 0.1322 | 2.8829 | 80 | 0.1386 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
