CoolFace
Modelpublic

yalhessi/lemexp-task1-v2-template_small_nodefs-Llama-3.2-1B-8lr

sourceHugging Facellama3.2updated 1y agoView on Hugging Face
0likes5downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

lemexp-task1-v2-templatesmallnodefs-Llama-3.2-1B-8lr

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

  • —Loss: 0.1422

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: 0.0008
  • —trainbatchsize: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —distributed_type: multi-GPU
  • —num_devices: 8
  • —totaltrainbatch_size: 16
  • —totalevalbatch_size: 16
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 12
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.42290.20017200.3458
0.32520.400114400.3206
0.28740.600221600.2828
0.27910.800228800.2821
0.26391.000336000.2673
0.25451.200343200.2671
0.24721.400450400.2611
0.24711.600457600.2519
0.24281.800564800.2437
0.23812.000672000.2436
0.22992.200679200.2425
0.22632.400786400.2337
0.2222.600793600.2243
0.21992.8008100800.2260
0.223.0008108000.2276
0.21033.2009115200.2268
0.21313.4009122400.2206
0.20633.6010129600.2175
0.20473.8011136800.2193
0.20264.0011144000.2091
0.19444.2012151200.2106
0.19444.4012158400.2126
0.19124.6013165600.2136
0.1914.8013172800.2084
0.18685.0014180000.2046
0.17925.2014187200.2041
0.1795.4015194400.1952
0.17965.6016201600.2018
0.17755.8016208800.1950
0.17426.0017216000.1849
0.16646.2017223200.1875
0.16776.4018230400.1848
0.16476.6018237600.1859
0.16426.8019244800.1803
0.16117.0019252000.1962
0.15357.2020259200.1797
0.15297.4021266400.1727
0.15057.6021273600.1745
0.14857.8022280800.1691
0.15188.0022288000.1676
0.13968.2023295200.1709
0.13748.4023302400.1701
0.13868.6024309600.1619
0.13528.8024316800.1619
0.13659.0025324000.1592
0.12579.2026331200.1606
0.12379.4026338400.1568
0.12499.6027345600.1579
0.12389.8027352800.1527
0.118610.0028360000.1506
0.110210.2028367200.1472
0.109710.4029374400.1478
0.108710.6029381600.1479
0.108210.8030388800.1469
0.108811.0031396000.1468
0.098111.2031403200.1470
0.097411.4032410400.1440
0.095211.6032417600.1431
0.094711.8033424800.1422

Framework versions

  • —PEFT 0.14.0
  • —Transformers 4.47.0
  • —Pytorch 2.5.1+cu124
  • —Datasets 3.2.0
  • —Tokenizers 0.21.0