Llama2_7B_chat_LR / README.md
Jukaboo's picture
End of training
e690022
|
raw
history blame
1.59 kB
---
base_model: meta-llama/Llama-2-7b-chat-hf
tags:
- generated_from_trainer
model-index:
- name: Llama2_7B_chat_LR
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. -->
# Llama2_7B_chat_LR
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2693
## 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: 6
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 36
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.5075 | 0.21 | 6 | 2.4168 |
| 2.29 | 0.42 | 12 | 2.3278 |
| 2.2582 | 0.62 | 18 | 2.2871 |
| 2.3052 | 0.83 | 24 | 2.2693 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0