metadata
license: apache-2.0
base_model: teknium/OpenHermes-2.5-Mistral-7B
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: criticon-sft-v0.1
results: []
criticon-sft-v0.1
This model is a fine-tuned version of teknium/OpenHermes-2.5-Mistral-7B on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.4668
WandB logs
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: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6226 | 0.29 | 500 | 0.6215 |
| 0.5616 | 0.57 | 1000 | 0.5684 |
| 0.5384 | 0.86 | 1500 | 0.5288 |
| 0.4248 | 1.14 | 2000 | 0.5098 |
| 0.3969 | 1.43 | 2500 | 0.4809 |
| 0.3933 | 1.72 | 3000 | 0.4668 |
Framework versions
- Transformers 4.38.0
- Pytorch 2.1.1+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2