| { | |
| "run_info": { | |
| "created_at": "2025-06-20T04:17:11+00:00", | |
| "total_time": 1867.121674144997, | |
| "experiment_name": "bone/llama-3.2-3B-default", | |
| "peft_branch": "main", | |
| "train_config": { | |
| "model_id": "meta-llama/Llama-3.2-3B", | |
| "dtype": "bfloat16", | |
| "max_seq_length": 768, | |
| "batch_size": 4, | |
| "batch_size_eval": 50, | |
| "max_steps": 5000, | |
| "eval_steps": 250, | |
| "compile": false, | |
| "query_template": "Question: {query} Think step by step.\nAnswer:", | |
| "seed": 0, | |
| "grad_norm_clip": 1.0, | |
| "optimizer_type": "AdamW", | |
| "optimizer_kwargs": { | |
| "lr": 0.0001, | |
| "weight_decay": 0.1 | |
| }, | |
| "lr_scheduler": "cosine", | |
| "use_amp": false, | |
| "autocast_adapter_dtype": true, | |
| "generation_kwargs": { | |
| "max_length": 800, | |
| "max_new_tokens": 300 | |
| }, | |
| "attn_implementation": null | |
| }, | |
| "peft_config": { | |
| "task_type": null, | |
| "peft_type": "BONE", | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "meta-llama/Llama-3.2-3B", | |
| "revision": null, | |
| "inference_mode": false, | |
| "r": 64, | |
| "target_modules": [ | |
| "v_proj", | |
| "q_proj" | |
| ], | |
| "exclude_modules": null, | |
| "init_weights": true, | |
| "layers_to_transform": null, | |
| "layers_pattern": null, | |
| "bias": "none", | |
| "modules_to_save": null | |
| }, | |
| "error_msg": "" | |
| }, | |
| "train_info": { | |
| "accelerator_memory_reserved_avg": 11170837063, | |
| "accelerator_memory_max": 20248002560, | |
| "accelerator_memory_reserved_99th": 16303469363, | |
| "train_time": 1664.0814183089897, | |
| "file_size": 29367496, | |
| "num_trainable_params": 7340032, | |
| "num_total_params": 3220089856, | |
| "status": "success", | |
| "metrics": [ | |
| { | |
| "step": 250, | |
| "valid accuracy": 0.34, | |
| "train loss": 0.8771067566871643, | |
| "train samples": 1000, | |
| "train time": 29.468342912026856, | |
| "eval time": 11.086663477995899, | |
| "tokens / sec": 7184.625230948821, | |
| "mem allocated avg": 6894354876.416, | |
| "mem reserved avg": 11212691603.456, | |
| "elapsed time": 88.56553585999791 | |
| }, | |
| { | |
| "step": 500, | |
| "valid accuracy": 0.38, | |
| "train loss": 0.6947847135066986, | |
| "train samples": 2000, | |
| "train time": 29.13603712292388, | |
| "eval time": 11.12908834600239, | |
| "tokens / sec": 7138.753946615206, | |
| "mem allocated avg": 6887297284.096, | |
| "mem reserved avg": 11116172279.808, | |
| "elapsed time": 169.94219922799675 | |
| }, | |
| { | |
| "step": 750, | |
| "valid accuracy": 0.42, | |
| "train loss": 0.6673308206796646, | |
| "train samples": 3000, | |
| "train time": 29.74789179801155, | |
| "eval time": 6.2111000180011615, | |
| "tokens / sec": 7207.267037805055, | |
| "mem allocated avg": 6897885888.512, | |
| "mem reserved avg": 11257109282.816, | |
| "elapsed time": 247.40845895299572 | |
| }, | |
| { | |
| "step": 1000, | |
| "valid accuracy": 0.44, | |
| "train loss": 0.6480507221221924, | |
| "train samples": 4000, | |
| "train time": 29.01437903306214, | |
| "eval time": 11.063560270995367, | |
| "tokens / sec": 7180.439731713689, | |
| "mem allocated avg": 6888501639.168, | |
| "mem reserved avg": 11141564596.224, | |
| "elapsed time": 328.43337820599845 | |
| }, | |
| { | |
| "step": 1250, | |
| "valid accuracy": 0.42, | |
| "train loss": 0.6442041766643524, | |
| "train samples": 5000, | |
| "train time": 28.86099356606428, | |
| "eval time": 11.061821620001865, | |
| "tokens / sec": 7225.600169399779, | |
| "mem allocated avg": 6888334700.544, | |
| "mem reserved avg": 11139123511.296, | |
| "elapsed time": 409.5306018880001 | |
| }, | |
| { | |
| "step": 1500, | |
| "valid accuracy": 0.52, | |
| "train loss": 0.6375475705862045, | |
| "train samples": 6000, | |
| "train time": 29.36598393299937, | |
| "eval time": 6.896059851998871, | |
| "tokens / sec": 7128.349606047729, | |
| "mem allocated avg": 6890338080.768, | |
| "mem reserved avg": 11164893315.072, | |
| "elapsed time": 487.1438905899995 | |
| }, | |
| { | |
| "step": 1750, | |
| "valid accuracy": 0.42, | |
| "train loss": 0.6282199568748474, | |
| "train samples": 7000, | |
| "train time": 29.2208460940019, | |
| "eval time": 11.139122824002698, | |
| "tokens / sec": 7164.576936838726, | |
| "mem allocated avg": 6891485964.288, | |
| "mem reserved avg": 11174582157.312, | |
| "elapsed time": 568.6407176649955 | |
| }, | |
| { | |
| "step": 2000, | |
| "valid accuracy": 0.44, | |
| "train loss": 0.628275181055069, | |
| "train samples": 8000, | |
| "train time": 28.774674860083906, | |
| "eval time": 11.096917715003656, | |
| "tokens / sec": 7218.013791986054, | |
| "mem allocated avg": 6889055956.992, | |
| "mem reserved avg": 11126481879.04, | |
| "elapsed time": 649.4662010969987 | |
| }, | |
| { | |
| "step": 2250, | |
| "valid accuracy": 0.5, | |
| "train loss": 0.6164452042579651, | |
| "train samples": 9000, | |
| "train time": 29.666104338008154, | |
| "eval time": 6.740810982002586, | |
| "tokens / sec": 7245.575541396888, | |
| "mem allocated avg": 6899385456.64, | |
| "mem reserved avg": 11287358603.264, | |
| "elapsed time": 727.5584506419982 | |
| }, | |
| { | |
| "step": 2500, | |
| "valid accuracy": 0.52, | |
| "train loss": 0.6124898854494095, | |
| "train samples": 10000, | |
| "train time": 28.952800227045373, | |
| "eval time": 11.054138113999215, | |
| "tokens / sec": 7113.888756349109, | |
| "mem allocated avg": 6884753041.408, | |
| "mem reserved avg": 11077492408.32, | |
| "elapsed time": 808.6757636719994 | |
| }, | |
| { | |
| "step": 2750, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.6010023313760757, | |
| "train samples": 11000, | |
| "train time": 29.36040201097785, | |
| "eval time": 5.933361176998005, | |
| "tokens / sec": 7216.556500853691, | |
| "mem allocated avg": 6895703631.872, | |
| "mem reserved avg": 11229007446.016, | |
| "elapsed time": 885.2688505609985 | |
| }, | |
| { | |
| "step": 3000, | |
| "valid accuracy": 0.36, | |
| "train loss": 0.590470621585846, | |
| "train samples": 12000, | |
| "train time": 29.152743853985157, | |
| "eval time": 11.051910919995862, | |
| "tokens / sec": 7159.909236861306, | |
| "mem allocated avg": 6890226739.2, | |
| "mem reserved avg": 11156563427.328, | |
| "elapsed time": 966.2876440099935 | |
| }, | |
| { | |
| "step": 3250, | |
| "valid accuracy": 0.46, | |
| "train loss": 0.5996054347753524, | |
| "train samples": 13000, | |
| "train time": 29.23224936202314, | |
| "eval time": 11.06002619300125, | |
| "tokens / sec": 7214.668888053154, | |
| "mem allocated avg": 6892138940.416, | |
| "mem reserved avg": 11182651998.208, | |
| "elapsed time": 1047.7634995759945 | |
| }, | |
| { | |
| "step": 3500, | |
| "valid accuracy": 0.46, | |
| "train loss": 0.5810788285732269, | |
| "train samples": 14000, | |
| "train time": 29.556202010979177, | |
| "eval time": 7.767598452002858, | |
| "tokens / sec": 7096.649289448104, | |
| "mem allocated avg": 6891370110.976, | |
| "mem reserved avg": 11166763974.656, | |
| "elapsed time": 1126.3068484049945 | |
| }, | |
| { | |
| "step": 3750, | |
| "valid accuracy": 0.5, | |
| "train loss": 0.5778432558774949, | |
| "train samples": 15000, | |
| "train time": 30.077826159038523, | |
| "eval time": 11.010653469995304, | |
| "tokens / sec": 7204.742751493022, | |
| "mem allocated avg": 6901065279.488, | |
| "mem reserved avg": 11319788961.792, | |
| "elapsed time": 1209.0550349339974 | |
| }, | |
| { | |
| "step": 4000, | |
| "valid accuracy": 0.4, | |
| "train loss": 0.5869229323863984, | |
| "train samples": 16000, | |
| "train time": 29.213863794990175, | |
| "eval time": 11.144038623999222, | |
| "tokens / sec": 6995.753845988955, | |
| "mem allocated avg": 6883645001.728, | |
| "mem reserved avg": 11058953584.64, | |
| "elapsed time": 1290.3985370609953 | |
| }, | |
| { | |
| "step": 4250, | |
| "valid accuracy": 0.46, | |
| "train loss": 0.5733816763162612, | |
| "train samples": 17000, | |
| "train time": 29.18649683901458, | |
| "eval time": 11.153094029003114, | |
| "tokens / sec": 7242.698607029438, | |
| "mem allocated avg": 6893432758.272, | |
| "mem reserved avg": 11193884344.32, | |
| "elapsed time": 1372.1237251569983 | |
| }, | |
| { | |
| "step": 4500, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.5803762240409851, | |
| "train samples": 18000, | |
| "train time": 29.077459994943638, | |
| "eval time": 11.118935573998897, | |
| "tokens / sec": 7147.047920834147, | |
| "mem allocated avg": 6888416004.096, | |
| "mem reserved avg": 11124485390.336, | |
| "elapsed time": 1453.4214935309938 | |
| }, | |
| { | |
| "step": 4750, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.5692038584947586, | |
| "train samples": 19000, | |
| "train time": 29.40723867896304, | |
| "eval time": 11.099454375005735, | |
| "tokens / sec": 7139.024588193769, | |
| "mem allocated avg": 6890813089.792, | |
| "mem reserved avg": 11168844349.44, | |
| "elapsed time": 1535.6791463129994 | |
| }, | |
| { | |
| "step": 5000, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.5775641392469406, | |
| "train samples": 20000, | |
| "train time": 28.941933833950316, | |
| "eval time": 11.18307958800142, | |
| "tokens / sec": 7196.47834159849, | |
| "mem allocated avg": 6887869800.448, | |
| "mem reserved avg": 11118328152.064, | |
| "elapsed time": 1617.277517963994 | |
| }, | |
| { | |
| "step": 5000, | |
| "test accuracy": 0.5079605761940864, | |
| "train loss": 0.5775641392469406, | |
| "train samples": 20000, | |
| "train total tokens": 4198051 | |
| } | |
| ] | |
| }, | |
| "meta_info": { | |
| "model_info": { | |
| "sha": "13afe5124825b4f3751f836b40dafda64c1ed062", | |
| "created_at": "2024-09-18T15:23:48+00:00" | |
| }, | |
| "dataset_info": { | |
| "metamath": { | |
| "sha": "aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18", | |
| "created_at": "2023-09-21T17:22:46+00:00" | |
| }, | |
| "gsm8k": { | |
| "sha": "e53f048856ff4f594e959d75785d2c2d37b678ee", | |
| "created_at": "2022-04-12T10:22:10+00:00" | |
| } | |
| }, | |
| "package_info": { | |
| "transformers-version": "4.52.4", | |
| "transformers-commit-hash": null, | |
| "peft-version": "0.15.2.dev0", | |
| "peft-commit-hash": "5fe7f8f8abe914d313fc3751f2ea92de7718fbaf", | |
| "datasets-version": "3.6.0", | |
| "datasets-commit-hash": null, | |
| "bitsandbytes-version": "0.46.0", | |
| "bitsandbytes-commit-hash": null, | |
| "torch-version": "2.7.1+cu126", | |
| "torch-commit-hash": null | |
| }, | |
| "system_info": { | |
| "system": "Linux", | |
| "release": "6.8.0-1029-aws", | |
| "version": "#31-Ubuntu SMP Wed Apr 23 18:42:41 UTC 2025", | |
| "machine": "x86_64", | |
| "processor": "x86_64", | |
| "accelerator": "NVIDIA L40S" | |
| }, | |
| "pytorch_info": "PyTorch built with:\n - GCC 11.2\n - C++ Version: 201703\n - Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications\n - Intel(R) MKL-DNN v3.7.1 (Git Hash 8d263e693366ef8db40acc569cc7d8edf644556d)\n - OpenMP 201511 (a.k.a. OpenMP 4.5)\n - LAPACK is enabled (usually provided by MKL)\n - NNPACK is enabled\n - CPU capability usage: AVX2\n - CUDA Runtime 12.6\n - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90\n - CuDNN 90.7.1 (built against CUDA 12.8)\n - Built with CuDNN 90.5.1\n - Magma 2.6.1\n - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=e2d141dbde55c2a4370fac5165b0561b6af4798b, CUDA_VERSION=12.6, CUDNN_VERSION=9.5.1, CXX_COMPILER=/opt/rh/gcc-toolset-11/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.7.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, \n" | |
| } | |
| } | |