zephyr-7b-sft-full

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.9422

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: 8
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• total_eval_batch_size: 128
• 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
1.0208	0.0923	100	1.0202
1.0303	0.1846	200	1.0460
1.0348	0.2769	300	1.0389
1.0096	0.3692	400	1.0251
1.0154	0.4615	500	1.0106
0.971	0.5538	600	0.9917
0.941	0.6461	700	0.9742
0.9248	0.7383	800	0.9585
0.9359	0.8306	900	0.9474
0.9189	0.9229	1000	0.9422

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+rocm6.2
• Datasets 3.2.0
• Tokenizers 0.20.3