metadata
base_model: mistralai/Mistral-7B-v0.3
datasets:
- llama-duo/synth_classification_dataset_dedup
library_name: peft
license: apache-2.0
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: mistral-7b_0_3-classification-gpt4o-100k
results: []
mistral-7b_0_3-classification-gpt4o-100k
This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the llama-duo/synth_classification_dataset_dedup dataset. It achieves the following results on the evaluation set:
- Loss: 1.5428
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: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8763 | 1.0 | 134 | 1.4227 |
| 0.7756 | 2.0 | 268 | 1.4397 |
| 0.7387 | 3.0 | 402 | 1.4401 |
| 0.7128 | 4.0 | 536 | 1.4540 |
| 0.6837 | 5.0 | 670 | 1.4658 |
| 0.6691 | 6.0 | 804 | 1.4930 |
| 0.6389 | 7.0 | 938 | 1.5040 |
| 0.6291 | 8.0 | 1072 | 1.5243 |
| 0.6197 | 9.0 | 1206 | 1.5375 |
| 0.6028 | 10.0 | 1340 | 1.5428 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1