my_awesome_qa_model

This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3052

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-07
• train_batch_size: 32
• eval_batch_size: 32
• 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
4.6796	1.0	2190	4.4264
3.9385	2.0	4380	3.7109
3.3803	3.0	6570	3.2006
3.0145	4.0	8760	2.7950
2.7776	5.0	10950	2.5765
2.595	6.0	13140	2.4387
2.4978	7.0	15330	2.3404
2.3957	8.0	17520	2.2612
2.3229	9.0	19710	2.1812
2.2338	10.0	21900	2.0971
2.1596	11.0	24090	2.0173
2.0972	12.0	26280	1.9428
2.0085	13.0	28470	1.8775
1.9591	14.0	30660	1.8191
1.9021	15.0	32850	1.7753
1.8743	16.0	35040	1.7351
1.8223	17.0	37230	1.7036
1.8064	18.0	39420	1.6734
1.7535	19.0	41610	1.6507
1.7349	20.0	43800	1.6266
1.7017	21.0	45990	1.6077
1.6698	22.0	48180	1.5890
1.6592	23.0	50370	1.5778
1.6407	24.0	52560	1.5616
1.6127	25.0	54750	1.5478
1.6082	26.0	56940	1.5328
1.5979	27.0	59130	1.5232
1.5655	28.0	61320	1.5127
1.5408	29.0	63510	1.5034
1.5523	30.0	65700	1.4931
1.5291	31.0	67890	1.4841
1.527	32.0	70080	1.4731
1.5099	33.0	72270	1.4676
1.4846	34.0	74460	1.4564
1.4928	35.0	76650	1.4504
1.4743	36.0	78840	1.4432
1.4605	37.0	81030	1.4395
1.452	38.0	83220	1.4314
1.4617	39.0	85410	1.4257
1.4633	40.0	87600	1.4198
1.4551	41.0	89790	1.4143
1.4227	42.0	91980	1.4074
1.4208	43.0	94170	1.4050
1.4008	44.0	96360	1.3999
1.4075	45.0	98550	1.3966
1.4032	46.0	100740	1.3916
1.368	47.0	102930	1.3884
1.3802	48.0	105120	1.3843
1.3914	49.0	107310	1.3807
1.3692	50.0	109500	1.3765
1.3698	51.0	111690	1.3722
1.3597	52.0	113880	1.3684
1.3551	53.0	116070	1.3663
1.3498	54.0	118260	1.3628
1.3428	55.0	120450	1.3608
1.3367	56.0	122640	1.3573
1.3202	57.0	124830	1.3549
1.346	58.0	127020	1.3499
1.3268	59.0	129210	1.3488
1.3253	60.0	131400	1.3468
1.3132	61.0	133590	1.3438
1.3247	62.0	135780	1.3425
1.3222	63.0	137970	1.3397
1.3045	64.0	140160	1.3381
1.3096	65.0	142350	1.3345
1.3131	66.0	144540	1.3334
1.284	67.0	146730	1.3331
1.2991	68.0	148920	1.3294
1.2794	69.0	151110	1.3280
1.2992	70.0	153300	1.3278
1.2884	71.0	155490	1.3259
1.2934	72.0	157680	1.3235
1.2778	73.0	159870	1.3222
1.2771	74.0	162060	1.3205
1.2846	75.0	164250	1.3190
1.2666	76.0	166440	1.3193
1.2828	77.0	168630	1.3170
1.2804	78.0	170820	1.3164
1.283	79.0	173010	1.3149
1.2621	80.0	175200	1.3139
1.2779	81.0	177390	1.3136
1.2633	82.0	179580	1.3125
1.2596	83.0	181770	1.3116
1.2653	84.0	183960	1.3103
1.2715	85.0	186150	1.3088
1.2553	86.0	188340	1.3095
1.2688	87.0	190530	1.3093
1.2496	88.0	192720	1.3086
1.2683	89.0	194910	1.3080
1.242	90.0	197100	1.3078
1.2619	91.0	199290	1.3065
1.2662	92.0	201480	1.3063
1.2557	93.0	203670	1.3059
1.2623	94.0	205860	1.3057
1.2402	95.0	208050	1.3056
1.2389	96.0	210240	1.3054
1.2653	97.0	212430	1.3053
1.2365	98.0	214620	1.3052
1.2637	99.0	216810	1.3052
1.2375	100.0	219000	1.3052

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2