train_wic_1753094170

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

• Loss: 0.2390
• Num Input Tokens Seen: 4213808

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: 123
• 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: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.3829	0.5	611	0.3071	210240
0.1971	1.0	1222	0.2813	421528
0.2298	1.5	1833	0.2601	632632
0.1462	2.0	2444	0.2633	843368
0.4035	2.5	3055	0.2592	1054024
0.1821	3.0	3666	0.2520	1264408
0.1771	3.5	4277	0.2593	1475000
0.164	4.0	4888	0.2590	1685768
0.1471	4.5	5499	0.2440	1895752
0.4103	5.0	6110	0.2552	2106968
0.4478	5.5	6721	0.2485	2318136
0.1788	6.0	7332	0.2390	2528648
0.2565	6.5	7943	0.2556	2739720
0.2295	7.0	8554	0.2675	2949592
0.2099	7.5	9165	0.2640	3160056
0.2858	8.0	9776	0.2716	3371056
0.2834	8.5	10387	0.2651	3581616
0.1544	9.0	10998	0.2651	3792672
0.1857	9.5	11609	0.2673	4003136
0.0746	10.0	12220	0.2687	4213808

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1