train_copa_101112_1760637988

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: 0.2321
• Num Input Tokens Seen: 562848

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: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 101112
• 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
0.2227	1.0	90	0.2698	28192
0.2333	2.0	180	0.2307	56256
0.2385	3.0	270	0.2351	84320
0.233	4.0	360	0.2394	112416
0.229	5.0	450	0.2329	140544
0.2334	6.0	540	0.2320	168768
0.2539	7.0	630	0.2324	196896
0.2337	8.0	720	0.2324	225024
0.2295	9.0	810	0.2311	253152
0.2281	10.0	900	0.2320	281312
0.2294	11.0	990	0.2343	309280
0.2314	12.0	1080	0.2363	337536
0.2284	13.0	1170	0.2341	365632
0.2253	14.0	1260	0.2349	393632
0.2207	15.0	1350	0.2411	421696
0.2306	16.0	1440	0.2374	449984
0.2205	17.0	1530	0.2379	478016
0.2193	18.0	1620	0.2392	506272
0.2144	19.0	1710	0.2417	534432
0.2273	20.0	1800	0.2423	562848

Framework versions

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