train_mrpc_789_1760637910

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

• Loss: 0.1258
• Num Input Tokens Seen: 6772448

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: 4
• eval_batch_size: 4
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.2112	1.0	826	0.1850	338792
0.1743	2.0	1652	0.1608	677792
0.1157	3.0	2478	0.1466	1016968
0.2048	4.0	3304	0.1407	1355576
0.1566	5.0	4130	0.1440	1694240
0.2413	6.0	4956	0.1397	2032216
0.0604	7.0	5782	0.1317	2370752
0.1455	8.0	6608	0.1314	2708952
0.0816	9.0	7434	0.1272	3047656
0.0841	10.0	8260	0.1275	3386008
0.048	11.0	9086	0.1327	3724536
0.0668	12.0	9912	0.1269	4063536
0.0262	13.0	10738	0.1280	4402704
0.1085	14.0	11564	0.1281	4740960
0.0647	15.0	12390	0.1269	5078920
0.1221	16.0	13216	0.1280	5417832
0.0964	17.0	14042	0.1266	5755672
0.0603	18.0	14868	0.1284	6094000
0.0567	19.0	15694	0.1268	6433272
0.0751	20.0	16520	0.1258	6772448

Framework versions

• PEFT 0.17.1
• Transformers 4.51.3
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4