You can deploy this model and start earning money today!

Kyungjin-Kim/
embc25_finetuned_30000_fr_es_it

Name: embc25_finetuned_30000_fr_es_it
Availability: InStock

Views

No views yet

embc25_finetuned_30000_fr_es_it

This model is a fine-tuned version of Kyungjin-Kim/mmc_roberta_500000_fr_es_it 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: 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 Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.6339	0.3950	500	0.6241	0.6462	0.7554	0.4324	0.5500
0.5484	0.7900	1000	0.5399	0.7162	0.7170	0.7144	0.7157
0.4822	1.1849	1500	0.5293	0.735	0.7445	0.7156	0.7297
0.4734	1.5799	2000	0.5126	0.7394	0.7554	0.7082	0.7310
0.4639	1.9749	2500	0.5002	0.752	0.7581	0.7402	0.7490
0.4019	2.3697	3000	0.5191	0.7534	0.7531	0.7542	0.7536
0.4026	2.7648	3500	0.5080	0.7627	0.7792	0.7331	0.7554
0.3723	3.1596	4000	0.5277	0.763	0.7731	0.7444	0.7585
0.3407	3.5546	4500	0.5493	0.7626	0.7826	0.7271	0.7538
0.3611	3.9496	5000	0.5424	0.761	0.7522	0.7784	0.7651
0.3009	4.3445	5500	0.5994	0.7606	0.7788	0.7278	0.7524
0.3026	4.7395	6000	0.5735	0.7589	0.7799	0.7213	0.7495
0.2603	5.1343	6500	0.6343	0.759	0.7852	0.7131	0.7474
0.2633	5.5293	7000	0.6436	0.7598	0.7470	0.7856	0.7658
0.2634	5.9244	7500	0.6263	0.7532	0.7534	0.7529	0.7531
0.2315	6.3192	8000	0.6605	0.7571	0.7572	0.7569	0.7571
0.2272	6.7142	8500	0.6937	0.7603	0.7743	0.7349	0.7541
0.1889	7.1090	9000	0.7585	0.7546	0.7392	0.7867	0.7622
0.2019	7.5040	9500	0.7345	0.7536	0.7452	0.7707	0.7577
0.1989	7.8991	10000	0.7465	0.7564	0.7549	0.7596	0.7572
0.1796	8.2939	10500	0.8035	0.7549	0.7524	0.7598	0.7561
0.1588	8.6889	11000	0.8073	0.7542	0.7525	0.7576	0.7550
0.1516	9.0837	11500	0.8369	0.7534	0.7562	0.748	0.7521
0.1501	9.4788	12000	0.8472	0.7541	0.7569	0.7487	0.7528
0.152	9.8738	12500	0.8458	0.7536	0.7570	0.7469	0.7519