You can deploy this model and start earning money today!

gallyamovi/
distilbert-base-cased-distilled-squad-finetuned-lr3e-06-epochs100

Name: distilbert-base-cased-distilled-squad-finetuned-lr3e-06-epochs100
Availability: InStock

generated_from_trainer

apache-2.0

endpoints_compatible

Views

No views yet

distilbert-base-cased-distilled-squad-finetuned-lr3e-06-epochs100

This model is a fine-tuned version of distilbert-base-cased-distilled-squad on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.3462

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: 3e-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	9	3.0777
No log	2.0	18	3.1319
No log	3.0	27	3.1694
No log	4.0	36	3.0616
No log	5.0	45	3.1448
No log	6.0	54	3.1118
No log	7.0	63	2.9115
No log	8.0	72	2.8013
No log	9.0	81	3.2407
No log	10.0	90	3.2540
No log	11.0	99	3.2567
No log	12.0	108	3.2652
No log	13.0	117	3.2635
No log	14.0	126	3.2646
No log	15.0	135	3.2717
No log	16.0	144	3.2749
No log	17.0	153	3.2778
No log	18.0	162	3.2802
No log	19.0	171	3.2908
No log	20.0	180	3.2998
No log	21.0	189	3.2963
No log	22.0	198	3.2936
No log	23.0	207	3.3001
No log	24.0	216	3.3034
No log	25.0	225	3.3164
No log	26.0	234	3.3119
No log	27.0	243	3.2937
No log	28.0	252	3.2761
No log	29.0	261	3.2692
No log	30.0	270	3.2687
No log	31.0	279	3.3021
No log	32.0	288	3.3296
No log	33.0	297	3.3427
No log	34.0	306	3.3303
No log	35.0	315	3.3177
No log	36.0	324	3.2875
No log	37.0	333	3.2566
No log	38.0	342	3.2476
No log	39.0	351	3.2495
No log	40.0	360	3.2710
No log	41.0	369	3.2782
No log	42.0	378	3.2670
No log	43.0	387	3.2743
No log	44.0	396	3.3123
No log	45.0	405	3.3308
No log	46.0	414	3.3599
No log	47.0	423	3.2345
No log	48.0	432	3.1899
No log	49.0	441	3.2649
No log	50.0	450	3.3745
No log	51.0	459	3.3841
No log	52.0	468	3.3477
No log	53.0	477	3.4445
No log	54.0	486	3.5382
No log	55.0	495	3.5705
0.0001	56.0	504	3.5022
0.0001	57.0	513	3.4424
0.0001	58.0	522	3.4941
0.0001	59.0	531	3.4784
0.0001	60.0	540	3.4759
0.0001	61.0	549	3.4902
0.0001	62.0	558	3.4874
0.0001	63.0	567	3.4836
0.0001	64.0	576	3.4769
0.0001	65.0	585	3.4762
0.0001	66.0	594	3.4609
0.0001	67.0	603	3.4599
0.0001	68.0	612	3.4530
0.0001	69.0	621	3.4525
0.0001	70.0	630	3.4634
0.0001	71.0	639	3.5287
0.0001	72.0	648	3.5306
0.0001	73.0	657	3.5194
0.0001	74.0	666	3.5239
0.0001	75.0	675	3.5213
0.0001	76.0	684	3.4864
0.0001	77.0	693	3.4199
0.0001	78.0	702	3.3633
0.0001	79.0	711	3.3121
0.0001	80.0	720	3.2907
0.0001	81.0	729	3.3259
0.0001	82.0	738	3.3401
0.0001	83.0	747	3.3613
0.0001	84.0	756	3.3617
0.0001	85.0	765	3.3348
0.0001	86.0	774	3.2861
0.0001	87.0	783	3.2698
0.0001	88.0	792	3.3305
0.0001	89.0	801	3.3725
0.0001	90.0	810	3.3847
0.0001	91.0	819	3.3876
0.0001	92.0	828	3.3788
0.0001	93.0	837	3.3743
0.0001	94.0	846	3.3662
0.0001	95.0	855	3.3581
0.0001	96.0	864	3.3527
0.0001	97.0	873	3.3489
0.0001	98.0	882	3.3471
0.0001	99.0	891	3.3463
0.0001	100.0	900	3.3462

Framework versions

Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3

gallyamovi/distilbert-base-cased-distilled-squad-finetuned-lr3e-06-epochs100

distilbert-base-cased-distilled-squad-finetuned-lr3e-06-epochs100

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

gallyamovi/
distilbert-base-cased-distilled-squad-finetuned-lr3e-06-epochs100