exceptions_exp2_resemble_to_drop_frequency_1032

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

• Loss: 3.5608
• Accuracy: 0.3697

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: 1032
• 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
4.8179	0.2912	1000	4.7388	0.2568
4.3391	0.5824	2000	4.2838	0.2992
4.1469	0.8737	3000	4.0994	0.3146
3.9916	1.1648	4000	3.9897	0.3247
3.9303	1.4561	5000	3.9140	0.3321
3.8779	1.7473	6000	3.8589	0.3370
3.7486	2.0384	7000	3.8123	0.3417
3.7408	2.3297	8000	3.7838	0.3445
3.7353	2.6209	9000	3.7540	0.3475
3.7216	2.9121	10000	3.7265	0.3500
3.627	3.2033	11000	3.7146	0.3516
3.6338	3.4945	12000	3.6967	0.3533
3.6322	3.7857	13000	3.6785	0.3548
3.5546	4.0769	14000	3.6719	0.3559
3.5751	4.3681	15000	3.6628	0.3569
3.5864	4.6593	16000	3.6476	0.3583
3.5727	4.9506	17000	3.6343	0.3598
3.5001	5.2417	18000	3.6371	0.3599
3.5292	5.5329	19000	3.6272	0.3609
3.5401	5.8242	20000	3.6149	0.3623
3.4454	6.1153	21000	3.6226	0.3623
3.4806	6.4065	22000	3.6113	0.3629
3.4971	6.6978	23000	3.6041	0.3635
3.4885	6.9890	24000	3.5931	0.3645
3.4323	7.2802	25000	3.6029	0.3644
3.4491	7.5714	26000	3.5926	0.3649
3.4585	7.8626	27000	3.5874	0.3659
3.3888	8.1538	28000	3.5957	0.3654
3.431	8.4450	29000	3.5858	0.3663
3.4303	8.7362	30000	3.5769	0.3668
3.3287	9.0274	31000	3.5821	0.3670
3.3702	9.3186	32000	3.5814	0.3673
3.3958	9.6098	33000	3.5711	0.3675
3.4182	9.9010	34000	3.5638	0.3683
3.3301	10.1922	35000	3.5756	0.3681
3.3746	10.4834	36000	3.5671	0.3685
3.3964	10.7747	37000	3.5621	0.3688
3.2846	11.0658	38000	3.5708	0.3690
3.3397	11.3570	39000	3.5662	0.3690
3.3675	11.6483	40000	3.5608	0.3697
3.3618	11.9395	41000	3.5535	0.3700
3.2947	12.2306	42000	3.5662	0.3694
3.3348	12.5219	43000	3.5599	0.3700
3.3386	12.8131	44000	3.5525	0.3705
3.2812	13.1043	45000	3.5638	0.3701
3.3061	13.3955	46000	3.5608	0.3699
3.3265	13.6867	47000	3.5513	0.3709
3.3405	13.9779	48000	3.5451	0.3712
3.2761	14.2691	49000	3.5578	0.3708
3.3001	14.5603	50000	3.5523	0.3713
3.3161	14.8515	51000	3.5440	0.3718
3.2441	15.1427	52000	3.5590	0.3707
3.2836	15.4339	53000	3.5512	0.3716
3.3039	15.7251	54000	3.5427	0.3721
3.1908	16.0163	55000	3.5534	0.3716
3.2603	16.3075	56000	3.5535	0.3717
3.2797	16.5988	57000	3.5465	0.3722
3.3015	16.8900	58000	3.5399	0.3728
3.214	17.1811	59000	3.5574	0.3718
3.2536	17.4724	60000	3.5466	0.3723
3.2649	17.7636	61000	3.5422	0.3726
3.1855	18.0547	62000	3.5523	0.3722
3.234	18.3460	63000	3.5505	0.3724
3.2567	18.6372	64000	3.5431	0.3728
3.2589	18.9284	65000	3.5341	0.3735
3.2112	19.2196	66000	3.5503	0.3726
3.2412	19.5108	67000	3.5466	0.3730
3.248	19.8020	68000	3.5371	0.3736
3.1563	20.0932	69000	3.5551	0.3727
3.217	20.3844	70000	3.5472	0.3732
3.2238	20.6756	71000	3.5425	0.3733
3.2515	20.9669	72000	3.5328	0.3739
3.195	21.2580	73000	3.5512	0.3728
3.2048	21.5492	74000	3.5449	0.3733
3.2347	21.8405	75000	3.5347	0.3742
3.1672	22.1316	76000	3.5518	0.3730
3.1982	22.4229	77000	3.5476	0.3735
3.2172	22.7141	78000	3.5398	0.3737
3.1973	23.0052	79000	3.5512	0.3734
3.167	23.2965	80000	3.5488	0.3736
3.2075	23.5877	81000	3.5396	0.3741
3.2149	23.8789	82000	3.5350	0.3744
3.1563	24.1701	83000	3.5525	0.3734
3.1832	24.4613	84000	3.5431	0.3740
3.1941	24.7525	85000	3.5368	0.3745
3.1068	25.0437	86000	3.5506	0.3738
3.1546	25.3349	87000	3.5476	0.3741
3.1857	25.6261	88000	3.5417	0.3743
3.21	25.9174	89000	3.5322	0.3751
3.1305	26.2085	90000	3.5505	0.3742
3.1673	26.4997	91000	3.5474	0.3740
3.1799	26.7910	92000	3.5412	0.3745
3.1123	27.0821	93000	3.5531	0.3741
3.1516	27.3733	94000	3.5482	0.3744
3.1699	27.6646	95000	3.5420	0.3744
3.193	27.9558	96000	3.5334	0.3751
3.1241	28.2470	97000	3.5512	0.3743
3.1584	28.5382	98000	3.5444	0.3747
3.1838	28.8294	99000	3.5358	0.3755
3.1031	29.1206	100000	3.5505	0.3745
3.1339	29.4118	101000	3.5469	0.3748
3.1536	29.7030	102000	3.5419	0.3749
3.1805	29.9942	103000	3.5314	0.3755
3.1183	30.2854	104000	3.5509	0.3745
3.129	30.5766	105000	3.5427	0.3751
3.146	30.8678	106000	3.5382	0.3752
3.1008	31.1590	107000	3.5534	0.3746
3.1194	31.4502	108000	3.5460	0.3749
3.1194	31.7415	109000	3.5423	0.3752
3.0636	32.0326	110000	3.5524	0.3747
3.1026	32.3238	111000	3.5523	0.3749
3.1189	32.6151	112000	3.5448	0.3755
3.1413	32.9063	113000	3.5360	0.3757
3.0919	33.1974	114000	3.5544	0.3749
3.0985	33.4887	115000	3.5457	0.3752
3.1181	33.7799	116000	3.5391	0.3757
3.0525	34.0711	117000	3.5525	0.3750
3.0902	34.3623	118000	3.5551	0.3749
3.1092	34.6535	119000	3.5476	0.3755
3.1216	34.9447	120000	3.5423	0.3756
3.0606	35.2359	121000	3.5529	0.3751
3.0835	35.5271	122000	3.5473	0.3756
3.1028	35.8183	123000	3.5453	0.3757

Framework versions

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