You can deploy this model and start earning money today!

CodeIsAbstract/
HybridTimeScaleModel_conti4

Name: HybridTimeScaleModel_conti4
Rating: 2.5 (12 reviews)

Views

No views yet

HybridTimeScaleModel_conti3

This model is a fine-tuned version of CodeIsAbstract/HybridTimeScaleModel_conti2 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: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 10
training_steps: 1000

Training Loss	Epoch	Step	Validation Loss
3.1777	0.05	50	3.4269
3.1601	0.1	100	3.3961
3.1383	0.15	150	3.3838
3.0848	0.2	200	3.3661
3.0850	0.25	250	3.3512
3.0674	0.3	300	3.3399
3.0248	0.35	350	3.3282
3.0237	0.4	400	3.3229
3.0460	0.45	450	3.3178
3.0554	0.5	500	3.3105
3.0215	0.55	550	3.3045
3.0404	0.6	600	3.2980
3.0302	0.65	650	3.2929
3.0227	0.7	700	3.2861
2.9928	0.75	750	3.2805
3.0219	0.8	800	3.2757
2.9899	0.85	850	3.2712
2.9925	0.9	900	3.2690
2.9400	0.95	950	3.2654
2.9780	1.0	1000	3.2616