| { | |
| "run_info": { | |
| "created_at": "2025-06-19T18:02:52+00:00", | |
| "total_time": 2068.5078051540004, | |
| "experiment_name": "lora/llama-3.2-3B-rank64-rslora", | |
| "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": "CAUSAL_LM", | |
| "peft_type": "LORA", | |
| "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, | |
| "lora_alpha": 64, | |
| "lora_dropout": 0.0, | |
| "fan_in_fan_out": false, | |
| "bias": "none", | |
| "use_rslora": true, | |
| "modules_to_save": null, | |
| "init_lora_weights": true, | |
| "layers_to_transform": null, | |
| "layers_pattern": null, | |
| "rank_pattern": {}, | |
| "alpha_pattern": {}, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "trainable_token_indices": null, | |
| "loftq_config": {}, | |
| "eva_config": null, | |
| "corda_config": null, | |
| "use_dora": false, | |
| "layer_replication": null, | |
| "lora_bias": false | |
| }, | |
| "error_msg": "" | |
| }, | |
| "train_info": { | |
| "accelerator_memory_reserved_avg": 12128059444, | |
| "accelerator_memory_max": 22538092544, | |
| "accelerator_memory_reserved_99th": 17953927987, | |
| "train_time": 1871.457509397991, | |
| "file_size": 73415408, | |
| "num_trainable_params": 18350080, | |
| "num_total_params": 3231099904, | |
| "status": "success", | |
| "metrics": [ | |
| { | |
| "step": 250, | |
| "valid accuracy": 0.36, | |
| "train loss": 0.8666043817996979, | |
| "train samples": 1000, | |
| "train time": 31.633613975991466, | |
| "eval time": 11.220254406001914, | |
| "tokens / sec": 6692.848947347132, | |
| "mem allocated avg": 7072427177.984, | |
| "mem reserved avg": 12177985503.232, | |
| "elapsed time": 97.06891104899842 | |
| }, | |
| { | |
| "step": 500, | |
| "valid accuracy": 0.32, | |
| "train loss": 0.697043846487999, | |
| "train samples": 2000, | |
| "train time": 31.400947067988454, | |
| "eval time": 11.24747418500192, | |
| "tokens / sec": 6623.844801548661, | |
| "mem allocated avg": 7064966957.056, | |
| "mem reserved avg": 12070787481.6, | |
| "elapsed time": 188.02626212299947 | |
| }, | |
| { | |
| "step": 750, | |
| "valid accuracy": 0.38, | |
| "train loss": 0.6723507121801376, | |
| "train samples": 3000, | |
| "train time": 31.849995732016396, | |
| "eval time": 11.249978227999236, | |
| "tokens / sec": 6731.586459350098, | |
| "mem allocated avg": 7075822055.424, | |
| "mem reserved avg": 12225037205.504, | |
| "elapsed time": 280.16055655299715 | |
| }, | |
| { | |
| "step": 1000, | |
| "valid accuracy": 0.38, | |
| "train loss": 0.6529685587882995, | |
| "train samples": 4000, | |
| "train time": 31.612207354013663, | |
| "eval time": 11.24677863100078, | |
| "tokens / sec": 6590.365477074112, | |
| "mem allocated avg": 7066256992.256, | |
| "mem reserved avg": 12092287483.904, | |
| "elapsed time": 371.5183315869981 | |
| }, | |
| { | |
| "step": 1250, | |
| "valid accuracy": 0.38, | |
| "train loss": 0.6472815409898758, | |
| "train samples": 5000, | |
| "train time": 31.26670297003875, | |
| "eval time": 8.06907803500144, | |
| "tokens / sec": 6669.651104557813, | |
| "mem allocated avg": 7066435080.192, | |
| "mem reserved avg": 12087824744.448, | |
| "elapsed time": 459.33407214199906 | |
| }, | |
| { | |
| "step": 1500, | |
| "valid accuracy": 0.44, | |
| "train loss": 0.6395461517572403, | |
| "train samples": 6000, | |
| "train time": 31.471468601008382, | |
| "eval time": 6.4898526670003776, | |
| "tokens / sec": 6651.4531830043925, | |
| "mem allocated avg": 7067292080.128, | |
| "mem reserved avg": 12121664389.12, | |
| "elapsed time": 545.9371380269986 | |
| }, | |
| { | |
| "step": 1750, | |
| "valid accuracy": 0.5, | |
| "train loss": 0.629749027967453, | |
| "train samples": 7000, | |
| "train time": 31.650018079009897, | |
| "eval time": 11.247470542999508, | |
| "tokens / sec": 6614.688164707337, | |
| "mem allocated avg": 7069213276.16, | |
| "mem reserved avg": 12130329821.184, | |
| "elapsed time": 637.2524904149977 | |
| }, | |
| { | |
| "step": 2000, | |
| "valid accuracy": 0.4, | |
| "train loss": 0.6293291836977005, | |
| "train samples": 8000, | |
| "train time": 31.45956211398152, | |
| "eval time": 11.187045163998846, | |
| "tokens / sec": 6601.999075749819, | |
| "mem allocated avg": 7066587928.576, | |
| "mem reserved avg": 12076634341.376, | |
| "elapsed time": 728.2233991199973 | |
| }, | |
| { | |
| "step": 2250, | |
| "valid accuracy": 0.4, | |
| "train loss": 0.6171289530992508, | |
| "train samples": 9000, | |
| "train time": 31.87981533700804, | |
| "eval time": 6.866186073002609, | |
| "tokens / sec": 6742.448089104055, | |
| "mem allocated avg": 7077788481.536, | |
| "mem reserved avg": 12265227026.432, | |
| "elapsed time": 815.9717469499992 | |
| }, | |
| { | |
| "step": 2500, | |
| "valid accuracy": 0.44, | |
| "train loss": 0.6119417071342468, | |
| "train samples": 10000, | |
| "train time": 31.067599171023176, | |
| "eval time": 10.55572699700133, | |
| "tokens / sec": 6629.640058962326, | |
| "mem allocated avg": 7062992943.104, | |
| "mem reserved avg": 12015850487.808, | |
| "elapsed time": 905.6140671029971 | |
| }, | |
| { | |
| "step": 2750, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.5985908216238022, | |
| "train samples": 11000, | |
| "train time": 31.864849751029396, | |
| "eval time": 6.1964339680016565, | |
| "tokens / sec": 6649.364477017663, | |
| "mem allocated avg": 7072847513.6, | |
| "mem reserved avg": 12192229359.616, | |
| "elapsed time": 992.5055643979977 | |
| }, | |
| { | |
| "step": 3000, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.5865949945449829, | |
| "train samples": 12000, | |
| "train time": 31.337576934987737, | |
| "eval time": 7.105518241998652, | |
| "tokens / sec": 6660.725570232467, | |
| "mem allocated avg": 7068560369.664, | |
| "mem reserved avg": 12111589670.912, | |
| "elapsed time": 1079.4884613180002 | |
| }, | |
| { | |
| "step": 3250, | |
| "valid accuracy": 0.56, | |
| "train loss": 0.5926763614416123, | |
| "train samples": 13000, | |
| "train time": 31.477448584984813, | |
| "eval time": 11.220603736997873, | |
| "tokens / sec": 6700.066539084199, | |
| "mem allocated avg": 7070318487.552, | |
| "mem reserved avg": 12143046950.912, | |
| "elapsed time": 1171.2174267509981 | |
| }, | |
| { | |
| "step": 3500, | |
| "valid accuracy": 0.54, | |
| "train loss": 0.5736529529094696, | |
| "train samples": 14000, | |
| "train time": 31.59231336902303, | |
| "eval time": 11.215632880001067, | |
| "tokens / sec": 6639.273216556042, | |
| "mem allocated avg": 7068978995.2, | |
| "mem reserved avg": 12124969500.672, | |
| "elapsed time": 1263.2709914519983 | |
| }, | |
| { | |
| "step": 3750, | |
| "valid accuracy": 0.54, | |
| "train loss": 0.5691816571950913, | |
| "train samples": 15000, | |
| "train time": 31.92663248500321, | |
| "eval time": 6.89942428699942, | |
| "tokens / sec": 6787.530758271833, | |
| "mem allocated avg": 7079011248.128, | |
| "mem reserved avg": 12298890510.336, | |
| "elapsed time": 1351.894684084 | |
| }, | |
| { | |
| "step": 4000, | |
| "valid accuracy": 0.56, | |
| "train loss": 0.5762648656368256, | |
| "train samples": 16000, | |
| "train time": 31.08475098094641, | |
| "eval time": 6.668889390999539, | |
| "tokens / sec": 6574.7028221416895, | |
| "mem allocated avg": 7061224237.056, | |
| "mem reserved avg": 12000969097.216, | |
| "elapsed time": 1437.9300296759975 | |
| }, | |
| { | |
| "step": 4250, | |
| "valid accuracy": 0.52, | |
| "train loss": 0.562865238904953, | |
| "train samples": 17000, | |
| "train time": 31.594970259979164, | |
| "eval time": 11.218020562002494, | |
| "tokens / sec": 6690.590250935068, | |
| "mem allocated avg": 7071853715.456, | |
| "mem reserved avg": 12157852844.032, | |
| "elapsed time": 1529.7590418299988 | |
| }, | |
| { | |
| "step": 4500, | |
| "valid accuracy": 0.5, | |
| "train loss": 0.568256908416748, | |
| "train samples": 18000, | |
| "train time": 31.334908029966755, | |
| "eval time": 11.24515695700029, | |
| "tokens / sec": 6632.156054240077, | |
| "mem allocated avg": 7066128418.816, | |
| "mem reserved avg": 12073245343.744, | |
| "elapsed time": 1620.988001589998 | |
| }, | |
| { | |
| "step": 4750, | |
| "valid accuracy": 0.52, | |
| "train loss": 0.5585172891616821, | |
| "train samples": 19000, | |
| "train time": 31.425996138961636, | |
| "eval time": 11.202903266999783, | |
| "tokens / sec": 6680.4246736261675, | |
| "mem allocated avg": 7068498065.408, | |
| "mem reserved avg": 12124491350.016, | |
| "elapsed time": 1712.544705993998 | |
| }, | |
| { | |
| "step": 5000, | |
| "valid accuracy": 0.52, | |
| "train loss": 0.5657225311994553, | |
| "train samples": 20000, | |
| "train time": 31.088545892969705, | |
| "eval time": 11.224285021999094, | |
| "tokens / sec": 6699.573557317776, | |
| "mem allocated avg": 7064964919.296, | |
| "mem reserved avg": 12070275776.512, | |
| "elapsed time": 1803.3861051699969 | |
| }, | |
| { | |
| "step": 5000, | |
| "test accuracy": 0.5299469294920395, | |
| "train loss": 0.5657225311994553, | |
| "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" | |
| } | |
| } | |