CoolFace
Modelpublic

a3ilab-llm-uncertainty/xlam_8B_bfcl_lr1_5e5_ep15_new

sourceHugging Faceotherupdated 9mo agoView on Hugging Face
0likes7downloads
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. -->

xlam8Bbfcllr15e5ep15new

This model is a fine-tuned version of Salesforce/Llama-xLAM-2-8b-fc-r on the sampled20newfix2fix2toollistremovesysAnyscalenotail_dropped dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.1257

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: 1.5e-05
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 4
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_ratio: 0.05
  • —num_epochs: 15

Training results

Training LossEpochStepValidation Loss
0.88921.0200.7338
0.38642.0400.3644
0.25163.0600.2695
0.22474.0800.1961
0.17965.01000.1542
0.18126.01200.1392
0.06567.01400.1305
0.13738.01600.1262
0.08039.01800.1250
0.062210.02000.1230
0.033811.02200.1250
0.06812.02400.1253
0.035313.02600.1253
0.040614.02800.1253
0.030915.03000.1257

Framework versions

  • —PEFT 0.17.0
  • —Transformers 4.55.2
  • —Pytorch 2.4.1+cu121
  • —Datasets 4.0.0
  • —Tokenizers 0.21.4