codegen-350M-mono-measurement_pred-diamonds-seed7

This model is a fine-tuned version of Salesforce/codegen-350M-mono on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5040
  • Accuracy: 0.9090
  • Accuracy Sensor 0: 0.9133
  • Auroc Sensor 0: 0.9558
  • Accuracy Sensor 1: 0.9094
  • Auroc Sensor 1: 0.9574
  • Accuracy Sensor 2: 0.9209
  • Auroc Sensor 2: 0.9484
  • Accuracy Aggregated: 0.8924
  • Auroc Aggregated: 0.9451

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-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 64
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy Accuracy Sensor 0 Auroc Sensor 0 Accuracy Sensor 1 Auroc Sensor 1 Accuracy Sensor 2 Auroc Sensor 2 Accuracy Aggregated Auroc Aggregated
0.292 0.9997 781 0.4645 0.7965 0.7764 0.9029 0.7966 0.9121 0.8383 0.9100 0.7747 0.8919
0.1979 1.9994 1562 0.3658 0.8561 0.8608 0.9319 0.8325 0.9368 0.8895 0.9374 0.8415 0.9235
0.1187 2.9990 2343 0.3611 0.8739 0.8911 0.9495 0.8882 0.9516 0.8664 0.9434 0.8497 0.9367
0.0666 4.0 3125 0.3757 0.9075 0.9064 0.9566 0.9149 0.9599 0.9146 0.9481 0.8942 0.9454
0.0267 4.9984 3905 0.5040 0.9090 0.9133 0.9558 0.9094 0.9574 0.9209 0.9484 0.8924 0.9451

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
16
Safetensors
Model size
304M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for oliverdk/codegen-350M-mono-measurement_pred-diamonds-seed7

Finetuned
(18)
this model