cricket-project-01

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

• Loss: 0.2588
• Accuracy: 0.9361
• Precision: 0.4680
• Recall: 0.5
• F1: 0.4835

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.3406	0.4318	500	0.2407	0.9361	0.4680	0.5	0.4835
0.3133	0.8636	1000	0.2432	0.9361	0.4680	0.5	0.4835
0.3181	1.2953	1500	0.2443	0.9361	0.4680	0.5	0.4835
0.3135	1.7271	2000	0.2726	0.9361	0.4680	0.5	0.4835
0.3228	2.1589	2500	0.2730	0.9361	0.4680	0.5	0.4835
0.3226	2.5907	3000	0.2750	0.9361	0.4680	0.5	0.4835
0.3171	3.0225	3500	0.2741	0.9361	0.4680	0.5	0.4835
0.3171	3.4542	4000	0.2625	0.9361	0.4680	0.5	0.4835
0.3056	3.8860	4500	0.2791	0.9361	0.4680	0.5	0.4835
0.3468	4.3178	5000	0.2645	0.9361	0.4680	0.5	0.4835
0.3099	4.7496	5500	0.2540	0.9361	0.4680	0.5	0.4835
0.2992	5.1813	6000	0.2543	0.9361	0.4680	0.5	0.4835
0.3321	5.6131	6500	0.2719	0.9361	0.4680	0.5	0.4835
0.32	6.0449	7000	0.2699	0.9361	0.4680	0.5	0.4835
0.3153	6.4767	7500	0.2643	0.9361	0.4680	0.5	0.4835
0.3278	6.9085	8000	0.2588	0.9361	0.4680	0.5	0.4835

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Tokenizers 0.21.1