zephyr-7b-sft-full

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the scottsuk0306/DepthQA dataset. It achieves the following results on the evaluation set:

• Loss: 0.1468

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: 1e-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: 0.03
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
1.0647	1.0	1	1.0615
1.0647	2.0	2	1.1875
1.0647	3.0	3	0.9856
1.0647	4.0	4	0.6196
0.969	5.0	5	0.4429
0.969	6.0	6	0.3590
0.969	7.0	7	0.2403
0.969	8.0	8	0.1860
0.969	9.0	9	0.1558
0.2782	10.0	10	0.1468

Framework versions

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