judy93536/distilroberta-rbm213k-ep40

distilroberta-base-rbm213k-ep40

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

• Loss: 1.2136

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: 7.3e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.19
• num_epochs: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.7375	1.0	13587	1.5878
1.6433	2.0	27174	1.5049
1.5936	3.0	40761	1.4690
1.5591	4.0	54348	1.4469
1.5452	5.0	67935	1.4324
1.5378	6.0	81522	1.4267
1.5333	7.0	95109	1.4279
1.5248	8.0	108696	1.4250
1.5095	9.0	122283	1.4120
1.4906	10.0	135870	1.3937
1.4746	11.0	149457	1.3860
1.4565	12.0	163044	1.3730
1.4377	13.0	176631	1.3672
1.4222	14.0	190218	1.3581
1.415	15.0	203805	1.3501
1.4148	16.0	217392	1.3422
1.404	17.0	230979	1.3356
1.3925	18.0	244566	1.3296
1.3782	19.0	258153	1.3207
1.3655	20.0	271740	1.3185
1.3628	21.0	285327	1.3109
1.355	22.0	298914	1.3046
1.3455	23.0	312501	1.2985
1.3365	24.0	326088	1.2900
1.3279	25.0	339675	1.2858
1.321	26.0	353262	1.2811
1.3198	27.0	366849	1.2746
1.3042	28.0	380436	1.2682
1.3057	29.0	394023	1.2641
1.2885	30.0	407610	1.2584
1.2841	31.0	421197	1.2507
1.2776	32.0	434784	1.2443
1.2688	33.0	448371	1.2415
1.2658	34.0	461958	1.2344
1.2606	35.0	475545	1.2315
1.2445	36.0	489132	1.2258
1.2409	37.0	502719	1.2211
1.2478	38.0	516306	1.2187
1.236	39.0	529893	1.2138
1.2277	40.0	543480	1.2124

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0