exceptions_exp2_swap_0.3_resemble_to_push_40817

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

• Loss: 3.5614
• Accuracy: 0.3690

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: 40817
• 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
4.8296	0.2915	1000	4.7465	0.2555
4.3456	0.5830	2000	4.2891	0.2986
4.1493	0.8745	3000	4.1066	0.3141
4.011	1.1659	4000	3.9998	0.3237
3.9419	1.4574	5000	3.9227	0.3305
3.8731	1.7488	6000	3.8621	0.3363
3.7499	2.0402	7000	3.8212	0.3404
3.765	2.3317	8000	3.7909	0.3432
3.741	2.6232	9000	3.7586	0.3463
3.735	2.9147	10000	3.7354	0.3485
3.6396	3.2061	11000	3.7206	0.3503
3.6575	3.4976	12000	3.7035	0.3521
3.6516	3.7891	13000	3.6854	0.3537
3.5518	4.0805	14000	3.6787	0.3553
3.5699	4.3719	15000	3.6668	0.3563
3.5867	4.6634	16000	3.6517	0.3576
3.5943	4.9549	17000	3.6388	0.3588
3.5022	5.2463	18000	3.6431	0.3589
3.5185	5.5378	19000	3.6310	0.3602
3.5269	5.8293	20000	3.6213	0.3611
3.458	6.1207	21000	3.6241	0.3614
3.4803	6.4122	22000	3.6171	0.3619
3.4889	6.7037	23000	3.6050	0.3626
3.4893	6.9952	24000	3.5963	0.3634
3.4333	7.2865	25000	3.6056	0.3635
3.4502	7.5780	26000	3.5940	0.3644
3.458	7.8695	27000	3.5880	0.3649
3.3719	8.1609	28000	3.5991	0.3648
3.4147	8.4524	29000	3.5876	0.3654
3.4297	8.7439	30000	3.5794	0.3665
3.3218	9.0353	31000	3.5886	0.3657
3.3882	9.3268	32000	3.5846	0.3662
3.3976	9.6183	33000	3.5781	0.3669
3.4173	9.9098	34000	3.5696	0.3675
3.3436	10.2011	35000	3.5821	0.3668
3.3566	10.4926	36000	3.5754	0.3674
3.3896	10.7841	37000	3.5684	0.3680
3.2871	11.0755	38000	3.5758	0.3679
3.3287	11.3670	39000	3.5723	0.3678
3.3637	11.6585	40000	3.5614	0.3690
3.3625	11.9500	41000	3.5559	0.3694
3.3046	12.2414	42000	3.5715	0.3682
3.335	12.5329	43000	3.5636	0.3692
3.3389	12.8243	44000	3.5563	0.3696
3.2821	13.1157	45000	3.5709	0.3690
3.3064	13.4072	46000	3.5630	0.3696
3.3309	13.6987	47000	3.5554	0.3696
3.3437	13.9902	48000	3.5479	0.3706
3.2782	14.2816	49000	3.5662	0.3697
3.2925	14.5731	50000	3.5596	0.3700
3.333	14.8646	51000	3.5489	0.3709
3.2445	15.1559	52000	3.5659	0.3699
3.2805	15.4474	53000	3.5571	0.3707
3.3048	15.7389	54000	3.5492	0.3710
3.2116	16.0303	55000	3.5625	0.3706
3.2637	16.3218	56000	3.5612	0.3705
3.2769	16.6133	57000	3.5507	0.3710
3.3071	16.9048	58000	3.5413	0.3715
3.2313	17.1962	59000	3.5583	0.3709
3.2458	17.4877	60000	3.5522	0.3712
3.2754	17.7792	61000	3.5459	0.3718
3.1912	18.0705	62000	3.5596	0.3712
3.2436	18.3620	63000	3.5572	0.3713
3.2651	18.6535	64000	3.5496	0.3719
3.2814	18.9450	65000	3.5410	0.3722
3.2169	19.2364	66000	3.5561	0.3713
3.2432	19.5279	67000	3.5538	0.3717
3.256	19.8194	68000	3.5443	0.3725
3.1886	20.1108	69000	3.5608	0.3714
3.2366	20.4023	70000	3.5521	0.3722
3.2463	20.6938	71000	3.5448	0.3727
3.251	20.9853	72000	3.5397	0.3730
3.2125	21.2766	73000	3.5592	0.3718
3.2256	21.5681	74000	3.5496	0.3723
3.2594	21.8596	75000	3.5415	0.3729
3.1772	22.1510	76000	3.5574	0.3723
3.1991	22.4425	77000	3.5516	0.3726
3.224	22.7340	78000	3.5462	0.3728
3.1405	23.0254	79000	3.5574	0.3722
3.1795	23.3169	80000	3.5574	0.3722
3.2152	23.6083	81000	3.5452	0.3730
3.2247	23.8998	82000	3.5396	0.3735
3.1579	24.1912	83000	3.5561	0.3728
3.1864	24.4827	84000	3.5478	0.3730
3.2161	24.7742	85000	3.5425	0.3733
3.13	25.0656	86000	3.5606	0.3725
3.1689	25.3571	87000	3.5543	0.3729
3.1847	25.6486	88000	3.5491	0.3731
3.2083	25.9401	89000	3.5389	0.3735
3.1552	26.2314	90000	3.5569	0.3727
3.1737	26.5229	91000	3.5511	0.3731
3.1893	26.8144	92000	3.5418	0.3736
3.1172	27.1058	93000	3.5610	0.3728
3.1577	27.3973	94000	3.5540	0.3731
3.1827	27.6888	95000	3.5499	0.3735
3.1922	27.9803	96000	3.5420	0.3738
3.1379	28.2717	97000	3.5579	0.3732
3.1689	28.5632	98000	3.5521	0.3732
3.1709	28.8547	99000	3.5444	0.3739
3.1091	29.1460	100000	3.5634	0.3729
3.1371	29.4375	101000	3.5561	0.3732
3.1593	29.7290	102000	3.5492	0.3736
3.0766	30.0204	103000	3.5597	0.3731
3.1104	30.3119	104000	3.5579	0.3736
3.1526	30.6034	105000	3.5508	0.3738
3.1745	30.8949	106000	3.5440	0.3740
3.0947	31.1863	107000	3.5598	0.3734
3.1288	31.4778	108000	3.5515	0.3737
3.152	31.7693	109000	3.5468	0.3744

Framework versions

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