train_sst2_42_1779194533/README.md

library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	llama3.2	meta-llama/Llama-3.2-1B-Instruct	peft-factory full llama-factory generated_from_trainer	name results train_sst2_42_1779194533

train_sst2_42_1779194533

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the sst2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0970
• Num Input Tokens Seen: 18647328

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-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.4074	0.2501	1895	0.1552	930944
0.3196	0.5002	3790	0.1577	1864128
0.0028	0.7503	5685	0.0970	2790656
0.0006	1.0004	7580	0.1143	3726464
0.1179	1.2505	9475	0.1166	4658240
0.1073	1.5006	11370	0.1257	5591680
0.342	1.7507	13265	0.1152	6528448
0.0004	2.0008	15160	0.1182	7463024
0.0556	2.2509	17055	0.1500	8395632
0.0962	2.5010	18950	0.1142	9326256
0.0429	2.7511	20845	0.1603	10259504
0.0352	3.0012	22740	0.1483	11196096
0.0352	3.2513	24635	0.1809	12128448
0.0	3.5014	26530	0.1809	13069824
0.0243	3.7515	28425	0.2036	13996672
0.0002	4.0016	30320	0.1816	14924944
0.0087	4.2517	32215	0.2473	15859920
0.0	4.5018	34110	0.2764	16790288
0.0	4.7519	36005	0.2836	17721744

Framework versions

• Transformers 4.51.3
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4