You can deploy this model and start earning money today!

Wiebke/
trainer_output

Name: trainer_output
Availability: InStock

Views

No views yet

trainer_output

This model is a fine-tuned version of distilbert/distilbert-base-german-cased on the None 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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
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: linear
num_epochs: 2
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Precision	Recall	F1
0.6758	0.2822	500	0.4825	0.0014	0.1876	0.2698	0.2213
0.4239	0.5643	1000	0.4283	0.0014	0.2381	0.4023	0.2991
0.3824	0.8465	1500	0.3869	0.0014	0.3688	0.4018	0.3846
0.3416	1.1287	2000	0.3609	0.0014	0.3915	0.4491	0.4183
0.2896	1.4108	2500	0.3439	0.0014	0.3795	0.4813	0.4244
0.2769	1.6930	3000	0.3366	0.0014	0.4120	0.4922	0.4486
0.2897	1.9752	3500	0.3314	0.0014	0.4109	0.4965	0.4496
0.2897	2.0	3544	0.3315	0.0014	0.4110	0.4941	0.4487