adpretko/train-riscv-O2_epoch3_AMD

<!-- 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. -->

train-riscv-O2epoch3AMD

This model is a fine-tuned version of adpretko/train-riscv-O2_epoch1and2 on the AnghaBench-risc-o2-fullpart00, the AnghaBench-risc-o2-fullpart01, the AnghaBench-risc-o2-fullpart02, the AnghaBench-risc-o2-fullpart03, the AnghaBench-risc-o2-fullpart04, the AnghaBench-risc-o2-fullpart05, the AnghaBench-risc-o2-fullpart06, the AnghaBench-risc-o2-fullpart07, the AnghaBench-risc-o2-fullpart08, the AnghaBench-risc-o2-fullpart09, the AnghaBench-risc-o2-fullpart10, the AnghaBench-risc-o2-fullpart11, the AnghaBench-risc-o2-fullpart12, the AnghaBench-risc-o2-fullpart13, the AnghaBench-risc-o2-fullpart14, the AnghaBench-risc-o2-fullpart15, the AnghaBench-risc-o2-fullpart16, the AnghaBench-risc-o2-fullpart17, the AnghaBench-risc-o2-fullpart18, the AnghaBench-risc-o2-fullpart19, the AnghaBench-risc-o2-fullpart20, the AnghaBench-risc-o2-fullpart21, the AnghaBench-risc-o2-fullpart22, the AnghaBench-risc-o2-fullpart23, the AnghaBench-risc-o2-fullpart24, the AnghaBench-risc-o2-fullpart25, the AnghaBench-risc-o2-fullpart26, the AnghaBench-risc-o2-fullpart27, the AnghaBench-risc-o2-fullpart28, the AnghaBench-risc-o2-fullpart29, the AnghaBench-risc-o2-fullpart30, the AnghaBench-risc-o2-fullpart31, the AnghaBench-risc-o2-fullpart32, the AnghaBench-risc-o2-fullpart33, the AnghaBench-risc-o2-fullpart34, the AnghaBench-risc-o2-fullpart35, the AnghaBench-risc-o2-fullpart36, the AnghaBench-risc-o2-fullpart37, the AnghaBench-risc-o2-fullpart38, the AnghaBench-risc-o2-fullpart39, the AnghaBench-risc-o2-fullpart40, the AnghaBench-risc-o2-fullpart41, the AnghaBench-risc-o2-fullpart42, the AnghaBench-risc-o2-fullpart43, the AnghaBench-risc-o2-fullpart44, the AnghaBench-risc-o2-fullpart45, the AnghaBench-risc-o2-fullpart46, the AnghaBench-risc-o2-fullpart47, the AnghaBench-risc-o2-fullpart48 and the AnghaBench-risc-o2-fullpart49 datasets.

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
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 512
• —totalevalbatch_size: 64
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 2.0

Training results

Framework versions

• —Transformers 4.55.0
• —Pytorch 2.8.0+rocm6.3
• —Datasets 3.6.0
• —Tokenizers 0.21.1