You can deploy this model and start earning money today!

mrovejaxd/
FNST_trad_2i

Name: FNST_trad_2i
Availability: InStock

tensorboard

safetensors

bert

generated_from_trainer

dccuchile/bert-base-spanish-wwm-cased

finetune

Views

No views yet

FNST_trad_2i

This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.2303
Accuracy: 0.4261
F1: 0.2542

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: 1e-07
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 16
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.3933	0.32	500	1.3964	0.2558	0.1034
1.3919	0.64	1000	1.3958	0.2556	0.1033
1.3926	0.96	1500	1.3945	0.2556	0.1033
1.3924	1.28	2000	1.3922	0.2556	0.1033
1.3893	1.6	2500	1.3892	0.2554	0.1036
1.3838	1.92	3000	1.3853	0.2558	0.1045
1.3801	2.24	3500	1.3808	0.2554	0.1050
1.3775	2.56	4000	1.3757	0.2558	0.1060
1.3739	2.88	4500	1.3702	0.2558	0.1073
1.3666	3.2	5000	1.3643	0.2549	0.1084
1.359	3.52	5500	1.3579	0.2556	0.1116
1.356	3.84	6000	1.3513	0.2580	0.1176
1.3502	4.16	6500	1.3445	0.2601	0.1248
1.3423	4.48	7000	1.3378	0.2688	0.1429
1.3344	4.8	7500	1.3309	0.2769	0.1629
1.3308	5.12	8000	1.3245	0.2896	0.1892
1.3249	5.44	8500	1.3183	0.3035	0.2153
1.3188	5.76	9000	1.3124	0.3177	0.2375
1.3112	6.08	9500	1.3068	0.3314	0.2516
1.3111	6.4	10000	1.3017	0.3428	0.2576
1.2993	6.72	10500	1.2968	0.3537	0.2560
1.2998	7.04	11000	1.2925	0.3640	0.2501
1.296	7.36	11500	1.2888	0.3620	0.2349
1.2954	7.68	12000	1.2854	0.3676	0.2236
1.2882	8.0	12500	1.2824	0.3707	0.2156
1.2898	8.32	13000	1.2798	0.3726	0.2074
1.2848	8.64	13500	1.2776	0.3717	0.2007
1.2825	8.96	14000	1.2755	0.3739	0.1966
1.2838	9.28	14500	1.2738	0.3746	0.1955
1.2756	9.6	15000	1.2718	0.3766	0.1888
1.2784	9.92	15500	1.2700	0.3755	0.1821
1.2803	10.24	16000	1.2684	0.3784	0.1814
1.2765	10.56	16500	1.2668	0.3782	0.1799
1.2716	10.88	17000	1.2653	0.3798	0.1806
1.271	11.2	17500	1.2636	0.3807	0.1802
1.2702	11.52	18000	1.2620	0.3813	0.1809
1.2666	11.84	18500	1.2603	0.3825	0.1810
1.2666	12.16	19000	1.2585	0.3842	0.1834
1.2656	12.48	19500	1.2567	0.3865	0.1863
1.2676	12.8	20000	1.2546	0.3883	0.1887
1.26	13.12	20500	1.2526	0.3928	0.1976
1.2595	13.44	21000	1.2505	0.3969	0.2044
1.2574	13.76	21500	1.2482	0.4	0.2093
1.2541	14.08	22000	1.2456	0.4018	0.2112
1.2505	14.4	22500	1.2429	0.4063	0.2186
1.2516	14.72	23000	1.2401	0.4106	0.2263
1.2502	15.04	23500	1.2370	0.4180	0.2396
1.2408	15.36	24000	1.2336	0.4200	0.2423
1.2437	15.68	24500	1.2303	0.4261	0.2542

Framework versions

Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1

mrovejaxd/FNST_trad_2i

FNST_trad_2i

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mrovejaxd/
FNST_trad_2i