arjuntheprogrammer's picture
llm-workshop-finetune-llama2-7b
cc91d97
---
tags:
- generated_from_trainer
model-index:
- name: LLAMA_2_chkpoint_workshop
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. -->
# LLAMA_2_chkpoint_workshop
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2368
## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.243 | 0.08 | 200 | 1.2715 |
| 1.2144 | 0.16 | 400 | 1.2597 |
| 1.2262 | 0.24 | 600 | 1.2551 |
| 1.2198 | 0.32 | 800 | 1.2511 |
| 1.2053 | 0.41 | 1000 | 1.2482 |
| 1.2206 | 0.49 | 1200 | 1.2466 |
| 1.2078 | 0.57 | 1400 | 1.2427 |
| 1.2077 | 0.65 | 1600 | 1.2415 |
| 1.2359 | 0.73 | 1800 | 1.2403 |
| 1.1679 | 0.81 | 2000 | 1.2389 |
| 1.205 | 0.89 | 2200 | 1.2373 |
| 1.1925 | 0.97 | 2400 | 1.2368 |
### Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3