You can deploy this model and start earning money today!

jung9602/
koelectra-small-clue-mrc

Name: koelectra-small-clue-mrc
Availability: InStock

generated_from_trainer

monologg/koelectra-small-discriminator

finetune

endpoints_compatible

Views

No views yet

koelectra-small-clue-mrc

This model is a fine-tuned version of monologg/koelectra-small-discriminator on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 6.4471

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: 16
seed: 42
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
No log	1.0	10	5.4000
No log	2.0	20	5.4755
No log	3.0	30	5.5088
No log	4.0	40	5.5022
No log	5.0	50	5.5458
No log	6.0	60	5.5648
No log	7.0	70	5.5821
No log	8.0	80	5.6190
No log	9.0	90	5.6272
No log	10.0	100	5.6139
No log	11.0	110	5.6393
No log	12.0	120	5.7026
No log	13.0	130	5.7220
No log	14.0	140	5.7151
No log	15.0	150	5.7243
No log	16.0	160	5.7942
No log	17.0	170	5.8391
No log	18.0	180	5.8407
No log	19.0	190	5.8244
No log	20.0	200	5.8204
No log	21.0	210	5.8577
No log	22.0	220	5.8792
No log	23.0	230	5.9471
No log	24.0	240	5.9698
No log	25.0	250	5.9783
No log	26.0	260	5.9499
No log	27.0	270	6.0046
No log	28.0	280	6.0131
No log	29.0	290	6.0061
No log	30.0	300	6.0890
No log	31.0	310	6.0014
No log	32.0	320	6.0541
No log	33.0	330	6.0317
No log	34.0	340	6.0379
No log	35.0	350	6.0969
No log	36.0	360	6.0850
No log	37.0	370	6.0971
No log	38.0	380	6.1481
No log	39.0	390	6.1544
No log	40.0	400	6.1529
No log	41.0	410	6.1941
No log	42.0	420	6.1579
No log	43.0	430	6.2084
No log	44.0	440	6.2283
No log	45.0	450	6.1759
No log	46.0	460	6.2187
No log	47.0	470	6.1980
No log	48.0	480	6.1609
No log	49.0	490	6.1892
1.3425	50.0	500	6.2666
1.3425	51.0	510	6.2514
1.3425	52.0	520	6.2610
1.3425	53.0	530	6.2581
1.3425	54.0	540	6.2945
1.3425	55.0	550	6.2769
1.3425	56.0	560	6.2652
1.3425	57.0	570	6.2940
1.3425	58.0	580	6.3239
1.3425	59.0	590	6.3200
1.3425	60.0	600	6.2950
1.3425	61.0	610	6.3296
1.3425	62.0	620	6.3497
1.3425	63.0	630	6.3581
1.3425	64.0	640	6.3305
1.3425	65.0	650	6.3342
1.3425	66.0	660	6.3433
1.3425	67.0	670	6.3553
1.3425	68.0	680	6.3713
1.3425	69.0	690	6.3788
1.3425	70.0	700	6.3526
1.3425	71.0	710	6.3945
1.3425	72.0	720	6.3729
1.3425	73.0	730	6.4061
1.3425	74.0	740	6.3969
1.3425	75.0	750	6.3947
1.3425	76.0	760	6.4078
1.3425	77.0	770	6.3925
1.3425	78.0	780	6.3801
1.3425	79.0	790	6.4134
1.3425	80.0	800	6.4011
1.3425	81.0	810	6.3730
1.3425	82.0	820	6.3980
1.3425	83.0	830	6.4063
1.3425	84.0	840	6.4367
1.3425	85.0	850	6.4418
1.3425	86.0	860	6.4303
1.3425	87.0	870	6.4383
1.3425	88.0	880	6.4430
1.3425	89.0	890	6.4381
1.3425	90.0	900	6.4437
1.3425	91.0	910	6.4452
1.3425	92.0	920	6.4512
1.3425	93.0	930	6.4524
1.3425	94.0	940	6.4505
1.3425	95.0	950	6.4474
1.3425	96.0	960	6.4434
1.3425	97.0	970	6.4472
1.3425	98.0	980	6.4469
1.3425	99.0	990	6.4473
0.6855	100.0	1000	6.4471

Framework versions

Transformers 4.53.2
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2

jung9602/koelectra-small-clue-mrc

koelectra-small-clue-mrc

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jung9602/
koelectra-small-clue-mrc