hkpr_cricket_1

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.1668

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-05
• train_batch_size: 8
• eval_batch_size: 8
• 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	3.0003
No log	2.0	2	2.9375
No log	3.0	3	2.8773
No log	4.0	4	2.8241
No log	5.0	5	2.7757
No log	6.0	6	2.7318
No log	7.0	7	2.6911
No log	8.0	8	2.6538
No log	9.0	9	2.6194
No log	10.0	10	2.5878
No log	11.0	11	2.5584
No log	12.0	12	2.5304
No log	13.0	13	2.5038
No log	14.0	14	2.4789
No log	15.0	15	2.4554
No log	16.0	16	2.4340
No log	17.0	17	2.4163
No log	18.0	18	2.4008
No log	19.0	19	2.3853
No log	20.0	20	2.3716
No log	21.0	21	2.3577
No log	22.0	22	2.3425
No log	23.0	23	2.3279
No log	24.0	24	2.3151
No log	25.0	25	2.3031
No log	26.0	26	2.2914
No log	27.0	27	2.2794
No log	28.0	28	2.2679
No log	29.0	29	2.2572
No log	30.0	30	2.2468
No log	31.0	31	2.2381
No log	32.0	32	2.2299
No log	33.0	33	2.2220
No log	34.0	34	2.2150
No log	35.0	35	2.2089
No log	36.0	36	2.2028
No log	37.0	37	2.1969
No log	38.0	38	2.1915
No log	39.0	39	2.1869
No log	40.0	40	2.1832
No log	41.0	41	2.1798
No log	42.0	42	2.1768
No log	43.0	43	2.1744
No log	44.0	44	2.1724
No log	45.0	45	2.1707
No log	46.0	46	2.1693
No log	47.0	47	2.1683
No log	48.0	48	2.1676
No log	49.0	49	2.1671
No log	50.0	50	2.1668

Framework versions

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