You can deploy this model and start earning money today!

Mardiyyah/
CeLLaTe-tapt-biofomer16l-tokenizer-adapted-spanmask

Name: CeLLaTe-tapt-biofomer16l-tokenizer-adapted-spanmask
Availability: InStock

generated_from_trainer

apache-2.0

endpoints_compatible

Views

No views yet

CeLLaTe-tapt-biofomer16l-tokenizer-adapted-spanmask

This model is a fine-tuned version of bioformers/bioformer-16l on the Mardiyyah/TAPT_CeLLaTe2.0 dataset. It achieves the following results on the evaluation set:

Loss: 2.7311
Accuracy: 0.5269
Perplexity: 15.3497

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: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 3407
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.06
num_epochs: 100
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Perplexity
3.6895	1.0	15	3.1710	0.5084	23.8306
3.4231	2.0	30	2.9351	0.5225	18.8227
3.2872	3.0	45	2.9610	0.5221	19.3181
3.2361	4.0	60	2.8894	0.5236	17.9828
3.1479	5.0	75	2.8712	0.5227	17.6579
3.1378	6.0	90	2.8567	0.5248	17.4038
3.0761	7.0	105	2.9116	0.5162	18.3854
3.0169	8.0	120	2.8471	0.5251	17.2385
3.0537	9.0	135	2.7650	0.5363	15.8794
3.0218	10.0	150	2.8013	0.5277	16.4658
3.0206	11.0	165	2.7133	0.5417	15.0789
2.9341	12.0	180	2.7189	0.5407	15.1631
2.918	13.0	195	2.7691	0.5305	15.9438
2.9412	14.0	210	2.7754	0.5324	16.0455
2.932	15.0	225	2.6850	0.5453	14.6577
2.9051	16.0	240	2.6733	0.5392	14.4881
2.8705	17.0	255	2.7261	0.5415	15.2731
2.862	18.0	270	2.7860	0.5339	16.2168
2.8693	19.0	285	2.7000	0.5386	14.8791
2.843	20.0	300	2.6767	0.5439	14.5368
2.8471	21.0	315	2.8352	0.5235	17.0343

Framework versions

Transformers 4.48.2
Pytorch 2.4.1+cu121
Datasets 3.0.2
Tokenizers 0.21.0

Mardiyyah/CeLLaTe-tapt-biofomer16l-tokenizer-adapted-spanmask

CeLLaTe-tapt-biofomer16l-tokenizer-adapted-spanmask

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Mardiyyah/
CeLLaTe-tapt-biofomer16l-tokenizer-adapted-spanmask