You can deploy this model and start earning money today!

Kyungjin-Kim/
embc25_finetuned_it

Name: embc25_finetuned_it
Availability: InStock

generated_from_trainer

Kyungjin-Kim/mmc_roberta_500000_it

finetune

autotrain_compatible

endpoints_compatible

Views

No views yet

embc25_finetuned_it

This model is a fine-tuned version of Kyungjin-Kim/mmc_roberta_500000_it on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.0118
Accuracy: 0.6326
Precision: 0.6723
Recall: 0.7953
F1: 0.7286

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: 2e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use 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: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.6322	0.64	500	1.0333	0.6180	0.6202	0.9909	0.7629
0.5622	1.2790	1000	0.6836	0.5831	0.7080	0.5580	0.6241
0.5048	1.9190	1500	0.8695	0.6169	0.6861	0.7047	0.6953
0.4943	2.5581	2000	0.8653	0.5944	0.6876	0.6341	0.6598
0.3837	3.1971	2500	1.0086	0.6056	0.6929	0.6540	0.6729
0.3642	3.8371	3000	1.0619	0.6079	0.7026	0.6377	0.6686
0.2798	4.4762	3500	1.5552	0.6247	0.6817	0.7409	0.7101
0.2695	5.1152	4000	1.7214	0.6225	0.6682	0.7772	0.7186
0.2279	5.7552	4500	1.9768	0.6292	0.6808	0.7572	0.7170
0.1942	6.3942	5000	1.7897	0.6180	0.6873	0.7047	0.6959
0.1529	7.0333	5500	2.3379	0.6281	0.6713	0.7844	0.7235
0.1507	7.6733	6000	2.2585	0.6090	0.6771	0.7065	0.6915
0.1196	8.3123	6500	2.5288	0.6202	0.6737	0.7518	0.7106
0.1246	8.9523	7000	3.0118	0.6326	0.6723	0.7953	0.7286
0.1102	9.5914	7500	3.1808	0.6326	0.6718	0.7971	0.7291

Framework versions

Transformers 4.48.1
Pytorch 2.3.1
Datasets 3.2.0
Tokenizers 0.21.0

Kyungjin-Kim/embc25_finetuned_it

embc25_finetuned_it

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Kyungjin-Kim/
embc25_finetuned_it