finetuned_glosslm_per_joint – AI Model by Tsedeniya | AlphaNeural AI

You can deploy this model and start earning money today!

Tsedeniya/
finetuned_glosslm_per_joint

like

0

text2text-generation

generated_from_trainer

lecslab/glosslm

text-generation-inference

endpoints_compatible

Views

No views yet

finetuned_glosslm_per_joint

This model is a fine-tuned version of lecslab/glosslm on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.9538
Chrf++: 24.4147
Gen Len: 104.3088

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: 5e-05
train_batch_size: 4
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
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
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf++	Gen Len
5.9387	1.9	38	1.1731	25.28	135.6029
5.9387	3.8	76	1.2601	23.8014	147.8382
2.4680	5.7	114	1.3798	24.3633	130.3162
2.4680	7.6	152	1.5208	25.287	112.0662
2.4680	9.5	190	1.6778	23.7583	119.9706
0.2050	11.4	228	1.8083	24.0216	105.3382
0.2050	13.3	266	1.9538	24.4147	104.3088

Framework versions

Transformers 5.12.1
Pytorch 2.6.0+cu124
Datasets 5.0.0
Tokenizers 0.22.2