You can deploy this model and start earning money today!

AFZAL0008/
SmolVLM2-500M-Video-Instruct-video-feedback

Name: SmolVLM2-500M-Video-Instruct-video-feedback
Availability: InStock

Views

No views yet

SmolVLM2-500M-Video-Instruct-video-feedback

This model is a fine-tuned version of HuggingFaceTB/SmolVLM2-500M-Video-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 1

Training Loss	Epoch	Step	Validation Loss
0.0058	0.05	50	0.0106
0.0056	0.1	100	0.0105
0.0052	0.15	150	0.0123
0.0077	0.2	200	0.0108
0.0053	0.25	250	0.0107
0.0062	0.3	300	0.0109
0.0058	0.35	350	0.0104
0.006	0.4	400	0.0119
0.0053	0.45	450	0.0104
0.0066	0.5	500	0.0111
0.0057	0.55	550	0.0104
0.0059	0.6	600	0.0108
0.0053	0.65	650	0.0104
0.0052	0.7	700	0.0103
0.0054	0.75	750	0.0106
0.0064	0.8	800	0.0104
0.0056	0.85	850	0.0104
0.0069	0.9	900	0.0104
0.0052	0.95	950	0.0104
0.0053	1.0	1000	0.0104