mistral_o1_5_full

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5849

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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.7053	0.0824	100	0.7166
0.7157	0.1648	200	0.7360
0.7015	0.2472	300	0.7378
0.6937	0.3296	400	0.7115
0.6718	0.4120	500	0.6946
0.6401	0.4944	600	0.6726
0.6232	0.5768	700	0.6494
0.6021	0.6593	800	0.6263
0.5771	0.7417	900	0.6054
0.5587	0.8241	1000	0.5935
0.5512	0.9065	1100	0.5863
0.5406	0.9889	1200	0.5847

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1