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: 0.7002

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

Training results

Training Loss	Epoch	Step	Validation Loss
3.4966	1.0	5	2.9381
2.5644	2.0	10	2.1833
1.9501	3.0	15	1.7482
1.6572	4.0	20	1.6286
1.5672	5.0	25	1.5984
1.5456	6.0	30	1.5522
1.5138	7.0	35	1.5623
1.5187	8.0	40	1.5271
1.4693	9.0	45	1.4929
1.4264	10.0	50	1.4364
1.3861	11.0	55	1.3868
1.3580	12.0	60	1.3506
1.3041	13.0	65	1.3024
1.2614	14.0	70	1.2353
1.1888	15.0	75	1.1557
1.1243	16.0	80	1.0897
1.0817	17.0	85	1.0597
1.0505	18.0	90	1.0613
1.0286	19.0	95	0.9825
0.9680	20.0	100	0.9919
0.9733	21.0	105	0.9443
0.9319	22.0	110	0.9685
0.9913	23.0	115	0.9770
0.9304	24.0	120	0.9019
0.8845	25.0	125	0.8840
0.8630	26.0	130	0.8568
0.8613	27.0	135	0.8521
0.8631	28.0	140	0.8390
0.8458	29.0	145	0.8094
0.8052	30.0	150	0.7904
0.7919	31.0	155	0.8096
0.7809	32.0	160	0.7677
0.7595	33.0	165	0.7542
0.7481	34.0	170	0.7461
0.7381	35.0	175	0.7301
0.7230	36.0	180	0.7188
0.7149	37.0	185	0.7115
0.7137	38.0	190	0.7115
0.7057	39.0	195	0.7009
0.7026	40.0	200	0.7002

Framework versions

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