hkpr_cricket_001

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

• Loss: 2.6178

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	2.6288
No log	2.0	2	2.6279
No log	3.0	3	2.6272
No log	4.0	4	2.6264
No log	5.0	5	2.6258
No log	6.0	6	2.6251
No log	7.0	7	2.6245
No log	8.0	8	2.6240
No log	9.0	9	2.6236
No log	10.0	10	2.6231
No log	11.0	11	2.6226
No log	12.0	12	2.6222
No log	13.0	13	2.6217
No log	14.0	14	2.6214
No log	15.0	15	2.6211
No log	16.0	16	2.6210
No log	17.0	17	2.6207
No log	18.0	18	2.6206
No log	19.0	19	2.6204
No log	20.0	20	2.6202
No log	21.0	21	2.6200
No log	22.0	22	2.6198
No log	23.0	23	2.6195
No log	24.0	24	2.6193
No log	25.0	25	2.6190
No log	26.0	26	2.6189
No log	27.0	27	2.6188
No log	28.0	28	2.6186
No log	29.0	29	2.6185
No log	30.0	30	2.6185
No log	31.0	31	2.6183
No log	32.0	32	2.6182
No log	33.0	33	2.6182
No log	34.0	34	2.6181
No log	35.0	35	2.6180
No log	36.0	36	2.6180
No log	37.0	37	2.6180
No log	38.0	38	2.6180
No log	39.0	39	2.6180
No log	40.0	40	2.6180
No log	41.0	41	2.6180
No log	42.0	42	2.6179
No log	43.0	43	2.6179
No log	44.0	44	2.6179
No log	45.0	45	2.6179
No log	46.0	46	2.6179
No log	47.0	47	2.6178
No log	48.0	48	2.6178
No log	49.0	49	2.6178
No log	50.0	50	2.6178

Framework versions

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