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: 0.5755

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
3.5109	1.0	5	2.9231
2.5933	2.0	10	2.1372
1.9903	3.0	15	1.7721
1.6888	4.0	20	1.5962
1.5851	5.0	25	1.5193
1.5000	6.0	30	1.4443
1.4623	7.0	35	1.4404
1.4350	8.0	40	1.3478
1.3625	9.0	45	1.3444
1.3062	10.0	50	1.2294
1.2398	11.0	55	1.1624
1.1527	12.0	60	1.1024
1.0817	13.0	65	1.0244
1.0249	14.0	70	0.9749
0.9751	15.0	75	0.9366
0.9442	16.0	80	0.9510
0.9472	17.0	85	0.8966
0.9045	18.0	90	0.8965
0.8895	19.0	95	0.8266
0.8608	20.0	100	0.8087
0.8268	21.0	105	0.7818
0.8539	22.0	110	0.9394
0.8426	23.0	115	0.7818
0.7937	24.0	120	0.7712
0.7927	25.0	125	0.7393
0.7540	26.0	130	0.7141
0.7365	27.0	135	0.6940
0.7154	28.0	140	0.6860
0.7077	29.0	145	0.7073
0.7219	30.0	150	0.6690
0.7012	31.0	155	0.6384
0.6862	32.0	160	0.6405
0.6717	33.0	165	0.6330
0.6607	34.0	170	0.6153
0.6484	35.0	175	0.6049
0.6376	36.0	180	0.5999
0.6287	37.0	185	0.5846
0.6232	38.0	190	0.5806
0.6172	39.0	195	0.5780
0.6125	40.0	200	0.5755

Framework versions

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