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: 0.4085

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
1.1097	1.0	1	1.1095
1.1097	2.0	2	1.2839
1.1097	3.0	3	1.0813
1.1097	4.0	4	0.8745
1.0879	5.0	5	0.7450
1.0879	6.0	6	0.6025
1.0879	7.0	7	0.5167
1.0879	8.0	8	0.4539
1.0879	9.0	9	0.4191
0.547	10.0	10	0.4085

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1

interview-eval/zephyr-7b-stem-test

zephyr-7b-stem-test

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

interview-eval/
zephyr-7b-stem-test