handbook-sft-test / README.md
lewtun's picture
lewtun HF staff
End of training
1a633b1
---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- alignment-handbook
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrachat_200k
model-index:
- name: handbook-sft-test
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. -->
# handbook-sft-test
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7116
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6972 | 0.0 | 1 | 1.7116 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0