exceptions_exp2_swap_0.3_resemble_to_hit_3591

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

• Loss: 3.5615
• Accuracy: 0.3687

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: 0.0006
• train_batch_size: 16
• eval_batch_size: 16
• seed: 3591
• gradient_accumulation_steps: 5
• total_train_batch_size: 80
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 50.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.8497	0.2915	1000	4.7690	0.2523
4.3481	0.5830	2000	4.2845	0.2989
4.1345	0.8745	3000	4.0947	0.3157
3.9931	1.1659	4000	3.9913	0.3246
3.9376	1.4574	5000	3.9180	0.3314
3.8784	1.7488	6000	3.8617	0.3364
3.74	2.0402	7000	3.8155	0.3408
3.7518	2.3317	8000	3.7882	0.3439
3.7466	2.6232	9000	3.7559	0.3465
3.7249	2.9147	10000	3.7308	0.3489
3.6205	3.2061	11000	3.7205	0.3506
3.6538	3.4976	12000	3.7014	0.3524
3.6355	3.7891	13000	3.6811	0.3544
3.5377	4.0805	14000	3.6747	0.3554
3.5737	4.3719	15000	3.6649	0.3563
3.5713	4.6634	16000	3.6484	0.3577
3.5795	4.9549	17000	3.6361	0.3589
3.5088	5.2463	18000	3.6402	0.3596
3.5338	5.5378	19000	3.6300	0.3600
3.5118	5.8293	20000	3.6177	0.3613
3.4448	6.1207	21000	3.6232	0.3614
3.4743	6.4122	22000	3.6140	0.3623
3.4996	6.7037	23000	3.6046	0.3630
3.5022	6.9952	24000	3.5945	0.3640
3.4424	7.2865	25000	3.6027	0.3639
3.4529	7.5780	26000	3.5934	0.3645
3.4621	7.8695	27000	3.5851	0.3652
3.4039	8.1609	28000	3.5937	0.3652
3.427	8.4524	29000	3.5883	0.3655
3.4492	8.7439	30000	3.5789	0.3664
3.3342	9.0353	31000	3.5837	0.3663
3.3895	9.3268	32000	3.5864	0.3662
3.4027	9.6183	33000	3.5755	0.3671
3.4055	9.9098	34000	3.5652	0.3678
3.3263	10.2011	35000	3.5791	0.3674
3.3794	10.4926	36000	3.5707	0.3679
3.3766	10.7841	37000	3.5627	0.3683
3.3077	11.0755	38000	3.5715	0.3684
3.3411	11.3670	39000	3.5720	0.3685
3.3651	11.6585	40000	3.5615	0.3687
3.3784	11.9500	41000	3.5542	0.3695
3.2989	12.2414	42000	3.5668	0.3689
3.3437	12.5329	43000	3.5580	0.3695
3.3558	12.8243	44000	3.5476	0.3702
3.2779	13.1157	45000	3.5639	0.3696
3.3267	13.4072	46000	3.5618	0.3698
3.3303	13.6987	47000	3.5512	0.3704
3.3453	13.9902	48000	3.5449	0.3710
3.2886	14.2816	49000	3.5613	0.3701
3.3085	14.5731	50000	3.5537	0.3707
3.3262	14.8646	51000	3.5471	0.3712
3.2482	15.1559	52000	3.5586	0.3705
3.2801	15.4474	53000	3.5554	0.3706
3.3043	15.7389	54000	3.5484	0.3711
3.2112	16.0303	55000	3.5585	0.3708
3.2644	16.3218	56000	3.5540	0.3713
3.2864	16.6133	57000	3.5475	0.3715
3.2981	16.9048	58000	3.5405	0.3718
3.2348	17.1962	59000	3.5569	0.3713
3.2634	17.4877	60000	3.5511	0.3718
3.2771	17.7792	61000	3.5463	0.3718
3.2036	18.0705	62000	3.5546	0.3717
3.2272	18.3620	63000	3.5531	0.3718
3.2629	18.6535	64000	3.5441	0.3723
3.2767	18.9450	65000	3.5348	0.3727
3.2212	19.2364	66000	3.5539	0.3720
3.2418	19.5279	67000	3.5473	0.3724
3.2581	19.8194	68000	3.5400	0.3729
3.1861	20.1108	69000	3.5578	0.3723
3.2295	20.4023	70000	3.5492	0.3724
3.2477	20.6938	71000	3.5440	0.3728
3.259	20.9853	72000	3.5348	0.3733
3.2078	21.2766	73000	3.5519	0.3723
3.2191	21.5681	74000	3.5448	0.3728
3.2383	21.8596	75000	3.5371	0.3734
3.1736	22.1510	76000	3.5571	0.3721
3.2092	22.4425	77000	3.5463	0.3732
3.2159	22.7340	78000	3.5424	0.3732
3.1433	23.0254	79000	3.5522	0.3726
3.1874	23.3169	80000	3.5515	0.3728
3.2162	23.6083	81000	3.5442	0.3732
3.2291	23.8998	82000	3.5392	0.3736
3.1628	24.1912	83000	3.5535	0.3730
3.1968	24.4827	84000	3.5462	0.3734
3.2083	24.7742	85000	3.5446	0.3735
3.1166	25.0656	86000	3.5555	0.3731
3.1774	25.3571	87000	3.5486	0.3737
3.1954	25.6486	88000	3.5421	0.3737
3.2121	25.9401	89000	3.5345	0.3742
3.1498	26.2314	90000	3.5518	0.3733
3.178	26.5229	91000	3.5489	0.3736
3.1829	26.8144	92000	3.5370	0.3743
3.1092	27.1058	93000	3.5601	0.3731
3.1544	27.3973	94000	3.5546	0.3736
3.1813	27.6888	95000	3.5415	0.3741
3.2028	27.9803	96000	3.5332	0.3748
3.1417	28.2717	97000	3.5548	0.3735
3.1731	28.5632	98000	3.5515	0.3737
3.1656	28.8547	99000	3.5427	0.3745
3.1086	29.1460	100000	3.5568	0.3736
3.146	29.4375	101000	3.5504	0.3741
3.1686	29.7290	102000	3.5443	0.3742
3.0957	30.0204	103000	3.5528	0.3739
3.137	30.3119	104000	3.5527	0.3740
3.1535	30.6034	105000	3.5495	0.3741
3.1643	30.8949	106000	3.5389	0.3747
3.1108	31.1863	107000	3.5589	0.3741
3.1346	31.4778	108000	3.5537	0.3741
3.1404	31.7693	109000	3.5436	0.3746
3.0813	32.0606	110000	3.5552	0.3739
3.1034	32.3521	111000	3.5590	0.3738
3.1389	32.6436	112000	3.5501	0.3747
3.1531	32.9351	113000	3.5406	0.3750
3.0861	33.2265	114000	3.5576	0.3744
3.1148	33.5180	115000	3.5527	0.3743
3.1258	33.8095	116000	3.5443	0.3747

Framework versions

• Transformers 4.55.2
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4