adpretko/train-riscv-O2_epoch3_AMD

1---2library_name: transformers3base_model: adpretko/train-riscv-O2_epoch1and24tags:5- llama-factory6- full7- generated_from_trainer8model-index:9- name: train-riscv-O2_epoch3_AMD10  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# train-riscv-O2_epoch3_AMD17 18This model is a fine-tuned version of [adpretko/train-riscv-O2_epoch1and2](https://huggingface.co/adpretko/train-riscv-O2_epoch1and2) on the AnghaBench-risc-o2-full_part_00, the AnghaBench-risc-o2-full_part_01, the AnghaBench-risc-o2-full_part_02, the AnghaBench-risc-o2-full_part_03, the AnghaBench-risc-o2-full_part_04, the AnghaBench-risc-o2-full_part_05, the AnghaBench-risc-o2-full_part_06, the AnghaBench-risc-o2-full_part_07, the AnghaBench-risc-o2-full_part_08, the AnghaBench-risc-o2-full_part_09, the AnghaBench-risc-o2-full_part_10, the AnghaBench-risc-o2-full_part_11, the AnghaBench-risc-o2-full_part_12, the AnghaBench-risc-o2-full_part_13, the AnghaBench-risc-o2-full_part_14, the AnghaBench-risc-o2-full_part_15, the AnghaBench-risc-o2-full_part_16, the AnghaBench-risc-o2-full_part_17, the AnghaBench-risc-o2-full_part_18, the AnghaBench-risc-o2-full_part_19, the AnghaBench-risc-o2-full_part_20, the AnghaBench-risc-o2-full_part_21, the AnghaBench-risc-o2-full_part_22, the AnghaBench-risc-o2-full_part_23, the AnghaBench-risc-o2-full_part_24, the AnghaBench-risc-o2-full_part_25, the AnghaBench-risc-o2-full_part_26, the AnghaBench-risc-o2-full_part_27, the AnghaBench-risc-o2-full_part_28, the AnghaBench-risc-o2-full_part_29, the AnghaBench-risc-o2-full_part_30, the AnghaBench-risc-o2-full_part_31, the AnghaBench-risc-o2-full_part_32, the AnghaBench-risc-o2-full_part_33, the AnghaBench-risc-o2-full_part_34, the AnghaBench-risc-o2-full_part_35, the AnghaBench-risc-o2-full_part_36, the AnghaBench-risc-o2-full_part_37, the AnghaBench-risc-o2-full_part_38, the AnghaBench-risc-o2-full_part_39, the AnghaBench-risc-o2-full_part_40, the AnghaBench-risc-o2-full_part_41, the AnghaBench-risc-o2-full_part_42, the AnghaBench-risc-o2-full_part_43, the AnghaBench-risc-o2-full_part_44, the AnghaBench-risc-o2-full_part_45, the AnghaBench-risc-o2-full_part_46, the AnghaBench-risc-o2-full_part_47, the AnghaBench-risc-o2-full_part_48 and the AnghaBench-risc-o2-full_part_49 datasets.19 20## Model description21 22More information needed23 24## Intended uses & limitations25 26More information needed27 28## Training and evaluation data29 30More information needed31 32## Training procedure33 34### Training hyperparameters35 36The following hyperparameters were used during training:37- learning_rate: 2e-0538- train_batch_size: 839- eval_batch_size: 840- seed: 4241- distributed_type: multi-GPU42- num_devices: 843- gradient_accumulation_steps: 844- total_train_batch_size: 51245- total_eval_batch_size: 6446- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments47- lr_scheduler_type: cosine48- lr_scheduler_warmup_ratio: 0.149- num_epochs: 2.050 51### Training results52 53 54 55### Framework versions56 57- Transformers 4.55.058- Pytorch 2.8.0+rocm6.359- Datasets 3.6.060- Tokenizers 0.21.161