exceptions_exp2_swap_require_to_push_5039

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

• Loss: 3.5557
• Accuracy: 0.3699

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: 5039
• 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	Accuracy	Validation Loss
4.8239	0.2911	1000	0.2558	4.7466
4.3346	0.5822	2000	0.2990	4.2863
4.1431	0.8733	3000	0.3154	4.0945
3.9889	1.1642	4000	0.3249	3.9909
3.9256	1.4553	5000	0.3323	3.9127
3.8679	1.7464	6000	0.3373	3.8544
3.7456	2.0373	7000	0.3416	3.8116
3.7495	2.3284	8000	0.3446	3.7812
3.7333	2.6195	9000	0.3476	3.7508
3.7235	2.9106	10000	0.3500	3.7253
3.6348	3.2014	11000	0.3522	3.7121
3.6474	3.4925	12000	0.3536	3.6934
3.6408	3.7837	13000	0.3552	3.6762
3.5411	4.0745	14000	0.3562	3.6695
3.5657	4.3656	15000	0.3575	3.6554
3.5775	4.6567	16000	0.3589	3.6422
3.5844	4.9478	17000	0.3601	3.6308
3.5074	5.2387	18000	0.3605	3.6327
3.5232	5.5298	19000	0.3613	3.6238
3.5269	5.8209	20000	0.3623	3.6123
3.45	6.1118	21000	0.3623	3.6170
3.4654	6.4029	22000	0.3633	3.6082
3.4808	6.6940	23000	0.3642	3.5998
3.494	6.9851	24000	0.3648	3.5889
3.4155	7.2760	25000	0.3649	3.5996
3.4493	7.5671	26000	0.3653	3.5899
3.463	7.8582	27000	0.3662	3.5802
3.3767	8.1490	28000	0.3661	3.5874
3.4147	8.4401	29000	0.3670	3.5803
3.4224	8.7313	30000	0.3672	3.5707
3.3221	9.0221	31000	0.3673	3.5753
3.3657	9.3132	32000	0.3678	3.5763
3.4001	9.6043	33000	0.3685	3.5693
3.4211	9.8954	34000	0.3686	3.5597
3.322	10.1863	35000	0.3684	3.5719
3.3627	10.4774	36000	0.3691	3.5639
3.3818	10.7685	37000	0.3694	3.5583
3.2802	11.0594	38000	0.3692	3.5664
3.3399	11.3505	39000	0.3694	3.5642
3.3617	11.6416	40000	0.3699	3.5557
3.3705	11.9327	41000	0.3707	3.5489
3.3017	12.2236	42000	0.3699	3.5640
3.3312	12.5147	43000	0.3705	3.5569
3.3499	12.8058	44000	0.3707	3.5486
3.2567	13.0966	45000	0.3704	3.5622
3.2984	13.3878	46000	0.3709	3.5586
3.3315	13.6789	47000	0.3713	3.5500
3.3493	13.9700	48000	0.3720	3.5378
3.2806	14.2608	49000	0.3709	3.5578
3.3178	14.5519	50000	0.3717	3.5472
3.3285	14.8430	51000	0.3721	3.5417
3.2349	15.1339	52000	0.3716	3.5551
3.2865	15.4250	53000	0.3719	3.5477
3.2972	15.7161	54000	0.3723	3.5454
3.2481	16.0070	55000	0.3720	3.5482
3.2594	16.2981	56000	0.3720	3.5524
3.2754	16.5892	57000	0.3726	3.5434
3.2861	16.8803	58000	0.3731	3.5368
3.2287	17.1712	59000	0.3723	3.5501
3.2512	17.4623	60000	0.3728	3.5421
3.2781	17.7534	61000	0.3728	3.5358
3.1885	18.0442	62000	0.3726	3.5486
3.2445	18.3354	63000	0.3725	3.5455
3.2465	18.6265	64000	0.3732	3.5405
3.2764	18.9176	65000	0.3736	3.5328
3.219	19.2084	66000	0.3730	3.5486
3.2462	19.4995	67000	0.3734	3.5420
3.2577	19.7906	68000	0.3738	3.5331
3.167	20.0815	69000	0.3731	3.5499
3.222	20.3726	70000	0.3734	3.5452
3.2491	20.6637	71000	0.3735	3.5381
3.2553	20.9548	72000	0.3741	3.5309
3.1908	21.2457	73000	0.3733	3.5486
3.2235	21.5368	74000	0.3741	3.5418
3.2307	21.8279	75000	0.3741	3.5354
3.1703	22.1188	76000	0.3736	3.5511
3.1936	22.4099	77000	0.3740	3.5436
3.2232	22.7010	78000	0.3741	3.5401
3.2529	22.9921	79000	0.3744	3.5317
3.1891	23.2830	80000	0.3738	3.5474
3.1885	23.5741	81000	3.5490	0.3737
3.1981	23.8652	82000	3.5399	0.3743
3.1553	24.1563	83000	3.5522	0.3737
3.1871	24.4474	84000	3.5480	0.3742
3.2118	24.7385	85000	3.5372	0.3746
3.1186	25.0294	86000	3.5472	0.3743
3.1519	25.3205	87000	3.5476	0.3739
3.1872	25.6116	88000	3.5368	0.3747
3.1996	25.9027	89000	3.5331	0.3752
3.1469	26.1936	90000	3.5512	0.3741
3.1706	26.4847	91000	3.5404	0.3746
3.1898	26.7758	92000	3.5351	0.3751
3.0979	27.0667	93000	3.5498	0.3745
3.1498	27.3578	94000	3.5463	0.3745
3.1628	27.6489	95000	3.5412	0.3747
3.1913	27.9400	96000	3.5291	0.3755
3.1256	28.2308	97000	3.5540	0.3747
3.1429	28.5219	98000	3.5409	0.3749
3.153	28.8131	99000	3.5362	0.3753
3.096	29.1039	100000	3.5486	0.3745
3.1396	29.3950	101000	3.5484	0.3748
3.1598	29.6861	102000	3.5395	0.3753
3.1707	29.9772	103000	3.5295	0.3756
3.121	30.2681	104000	3.5518	0.3745
3.1484	30.5592	105000	3.5386	0.3756
3.1598	30.8503	106000	3.5361	0.3757
3.0879	31.1412	107000	3.5529	0.3749
3.1218	31.4323	108000	3.5470	0.3748
3.1351	31.7234	109000	3.5377	0.3758
3.069	32.0143	110000	3.5497	0.3752
3.0951	32.3054	111000	3.5464	0.3753
3.1199	32.5965	112000	3.5463	0.3752
3.1481	32.8876	113000	3.5357	0.3759
3.0671	33.1784	114000	3.5544	0.3751
3.1046	33.4696	115000	3.5469	0.3754
3.124	33.7607	116000	3.5398	0.3757

Framework versions

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