train_copa_789_1768397603

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the copa dataset. It achieves the following results on the evaluation set:

• Loss: 0.0839
• Num Input Tokens Seen: 274208

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 789
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.0039	0.5	90	0.1701	13792
0.5837	1.0	180	0.1115	27424
0.0054	1.5	270	0.0873	41056
0.0005	2.0	360	0.0839	54832
0.0027	2.5	450	0.0871	68416
0.3341	3.0	540	0.0933	82160
0.0109	3.5	630	0.1026	95856
0.0009	4.0	720	0.0998	109632
0.0012	4.5	810	0.1032	123360
0.03	5.0	900	0.1080	137120
0.0015	5.5	990	0.1099	150880
0.0001	6.0	1080	0.1141	164592
0.0004	6.5	1170	0.1137	178240
0.0002	7.0	1260	0.1140	191920
0.0002	7.5	1350	0.1174	205632
0.0002	8.0	1440	0.1175	219344
0.0001	8.5	1530	0.1246	232976
0.0002	9.0	1620	0.1214	246736
0.0001	9.5	1710	0.1240	260384
0.0002	10.0	1800	0.1224	274208

Framework versions

• PEFT 0.17.1
• Transformers 4.51.3
• Pytorch 2.9.1+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4