pr_cricket_01

This model is a fine-tuned version of samhitmantrala/cricket3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.7288

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: 2e-06
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	2.8226
No log	2.0	2	2.8172
No log	3.0	3	2.8120
No log	4.0	4	2.8067
No log	5.0	5	2.8017
No log	6.0	6	2.7970
No log	7.0	7	2.7927
No log	8.0	8	2.7887
No log	9.0	9	2.7849
No log	10.0	10	2.7814
No log	11.0	11	2.7781
No log	12.0	12	2.7748
No log	13.0	13	2.7718
No log	14.0	14	2.7690
No log	15.0	15	2.7663
No log	16.0	16	2.7639
No log	17.0	17	2.7616
No log	18.0	18	2.7594
No log	19.0	19	2.7572
No log	20.0	20	2.7552
No log	21.0	21	2.7534
No log	22.0	22	2.7516
No log	23.0	23	2.7499
No log	24.0	24	2.7483
No log	25.0	25	2.7468
No log	26.0	26	2.7453
No log	27.0	27	2.7439
No log	28.0	28	2.7426
No log	29.0	29	2.7413
No log	30.0	30	2.7401
No log	31.0	31	2.7390
No log	32.0	32	2.7379
No log	33.0	33	2.7368
No log	34.0	34	2.7359
No log	35.0	35	2.7350
No log	36.0	36	2.7342
No log	37.0	37	2.7335
No log	38.0	38	2.7328
No log	39.0	39	2.7321
No log	40.0	40	2.7316
No log	41.0	41	2.7311
No log	42.0	42	2.7306
No log	43.0	43	2.7302
No log	44.0	44	2.7299
No log	45.0	45	2.7296
No log	46.0	46	2.7293
No log	47.0	47	2.7291
No log	48.0	48	2.7290
No log	49.0	49	2.7289
No log	50.0	50	2.7288

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2