train_record_42_1773159747

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

• Loss: 0.4154
• Num Input Tokens Seen: 245808128

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: 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
0.6189	0.2500	3906	0.6394	12292032
0.5393	0.5001	7812	0.5500	24620672
0.5028	0.7501	11718	0.5072	36894016
0.3815	1.0002	15624	0.4872	49176512
0.5595	1.2502	19530	0.4700	61465280
0.4085	1.5003	23436	0.4594	73739776
0.4661	1.7503	27342	0.4472	86015936
0.4054	2.0004	31248	0.4402	98341056
0.4217	2.2504	35154	0.4363	110649216
0.3233	2.5005	39060	0.4314	122910592
0.3875	2.7505	42966	0.4261	135222656
0.336	3.0006	46872	0.4220	147516736
0.2617	3.2506	50778	0.4272	159826368
0.4998	3.5007	54684	0.4193	172084032
0.4191	3.7507	58590	0.4184	184402752
0.3614	4.0008	62496	0.4154	196687936
0.3211	4.2508	66402	0.4205	209017024
0.3259	4.5009	70308	0.4172	221278272
0.314	4.7509	74214	0.4179	233564288

Framework versions

• PEFT 0.17.1
• Transformers 4.51.3
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4