calculator_model_test

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1301

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: 0.001
• train_batch_size: 512
• eval_batch_size: 512
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.1429	1.0	4	2.2337
2.0240	2.0	8	1.7621
1.6595	3.0	12	1.4806
1.3784	4.0	16	1.1427
1.0363	5.0	20	0.8139
0.7381	6.0	24	0.6046
0.5807	7.0	28	0.5287
0.5117	8.0	32	0.4774
0.4641	9.0	36	0.4449
0.4274	10.0	40	0.4155
0.3970	11.0	44	0.3787
0.3664	12.0	48	0.3443
0.3391	13.0	52	0.3224
0.3196	14.0	56	0.3062
0.3033	15.0	60	0.2950
0.2938	16.0	64	0.2804
0.2757	17.0	68	0.2682
0.2641	18.0	72	0.2580
0.2551	19.0	76	0.2474
0.2441	20.0	80	0.2430
0.2358	21.0	84	0.2323
0.2284	22.0	88	0.2258
0.2149	23.0	92	0.2129
0.2098	24.0	96	0.2078
0.2005	25.0	100	0.1975
0.1898	26.0	104	0.1901
0.1845	27.0	108	0.1790
0.1771	28.0	112	0.1746
0.1708	29.0	116	0.1668
0.1657	30.0	120	0.1610
0.1600	31.0	124	0.1581
0.1559	32.0	128	0.1510
0.1498	33.0	132	0.1475
0.1451	34.0	136	0.1432
0.1426	35.0	140	0.1417
0.1373	36.0	144	0.1365
0.1334	37.0	148	0.1345
0.1335	38.0	152	0.1318
0.1309	39.0	156	0.1303
0.1308	40.0	160	0.1301

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2