| { | |
| "run_info": { | |
| "created_at": "2025-06-19T18:37:24+00:00", | |
| "total_time": 2286.5437473089987, | |
| "experiment_name": "lora/llama-3.2-3B-rank32-dora", | |
| "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": 32, | |
| "target_modules": [ | |
| "q_proj", | |
| "v_proj" | |
| ], | |
| "exclude_modules": null, | |
| "lora_alpha": 64, | |
| "lora_dropout": 0.0, | |
| "fan_in_fan_out": false, | |
| "bias": "none", | |
| "use_rslora": false, | |
| "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": true, | |
| "layer_replication": null, | |
| "lora_bias": false | |
| }, | |
| "error_msg": "" | |
| }, | |
| "train_info": { | |
| "accelerator_memory_reserved_avg": 12490471636, | |
| "accelerator_memory_max": 24553455616, | |
| "accelerator_memory_reserved_99th": 19189150515, | |
| "train_time": 2022.7454924520134, | |
| "file_size": 37181760, | |
| "num_trainable_params": 9289728, | |
| "num_total_params": 3222039552, | |
| "status": "success", | |
| "metrics": [ | |
| { | |
| "step": 250, | |
| "valid accuracy": 0.36, | |
| "train loss": 0.9800839998722076, | |
| "train samples": 1000, | |
| "train time": 35.42731901501611, | |
| "eval time": 16.70931195599769, | |
| "tokens / sec": 5976.150775345474, | |
| "mem allocated avg": 6924859500.544, | |
| "mem reserved avg": 12552201306.112, | |
| "elapsed time": 105.33911871900273 | |
| }, | |
| { | |
| "step": 500, | |
| "valid accuracy": 0.44, | |
| "train loss": 0.7162023800611496, | |
| "train samples": 2000, | |
| "train time": 35.53461015297944, | |
| "eval time": 16.7331051809997, | |
| "tokens / sec": 5853.307496678993, | |
| "mem allocated avg": 6917484427.264, | |
| "mem reserved avg": 12427118772.224, | |
| "elapsed time": 204.02196035100133 | |
| }, | |
| { | |
| "step": 750, | |
| "valid accuracy": 0.42, | |
| "train loss": 0.6790966511964798, | |
| "train samples": 3000, | |
| "train time": 35.395415813978616, | |
| "eval time": 10.35499690800134, | |
| "tokens / sec": 6057.309825848329, | |
| "mem allocated avg": 6927996166.144, | |
| "mem reserved avg": 12609050902.528, | |
| "elapsed time": 296.3724143870022 | |
| }, | |
| { | |
| "step": 1000, | |
| "valid accuracy": 0.42, | |
| "train loss": 0.6590274780988693, | |
| "train samples": 4000, | |
| "train time": 35.01134122798976, | |
| "eval time": 16.638093278997985, | |
| "tokens / sec": 5950.528962696411, | |
| "mem allocated avg": 6919690883.072, | |
| "mem reserved avg": 12464313860.096, | |
| "elapsed time": 394.33112582000103 | |
| }, | |
| { | |
| "step": 1250, | |
| "valid accuracy": 0.42, | |
| "train loss": 0.6542477097511291, | |
| "train samples": 5000, | |
| "train time": 34.85555366096378, | |
| "eval time": 16.627405782997812, | |
| "tokens / sec": 5982.920312453697, | |
| "mem allocated avg": 6919055253.504, | |
| "mem reserved avg": 12449952563.2, | |
| "elapsed time": 492.1167898590029 | |
| }, | |
| { | |
| "step": 1500, | |
| "valid accuracy": 0.4, | |
| "train loss": 0.6471435966491699, | |
| "train samples": 6000, | |
| "train time": 35.407848127983016, | |
| "eval time": 10.318167828998412, | |
| "tokens / sec": 5911.994404273457, | |
| "mem allocated avg": 6921185224.704, | |
| "mem reserved avg": 12477500751.872, | |
| "elapsed time": 584.325913470002 | |
| }, | |
| { | |
| "step": 1750, | |
| "valid accuracy": 0.42, | |
| "train loss": 0.6376023133993148, | |
| "train samples": 7000, | |
| "train time": 35.61810469696138, | |
| "eval time": 10.057756549002079, | |
| "tokens / sec": 5877.7692350896, | |
| "mem allocated avg": 6922196224.0, | |
| "mem reserved avg": 12495888580.608, | |
| "elapsed time": 676.5556904380028 | |
| }, | |
| { | |
| "step": 2000, | |
| "valid accuracy": 0.36, | |
| "train loss": 0.6404745506048203, | |
| "train samples": 8000, | |
| "train time": 35.01814225999988, | |
| "eval time": 10.846777078000741, | |
| "tokens / sec": 5931.097042724754, | |
| "mem allocated avg": 6919877345.28, | |
| "mem reserved avg": 12428771328.0, | |
| "elapsed time": 768.7593245980024 | |
| }, | |
| { | |
| "step": 2250, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.6327905882596969, | |
| "train samples": 9000, | |
| "train time": 35.941867801058834, | |
| "eval time": 16.654083295998134, | |
| "tokens / sec": 5980.434884178939, | |
| "mem allocated avg": 6930785019.904, | |
| "mem reserved avg": 12637135962.112, | |
| "elapsed time": 868.0876048490027 | |
| }, | |
| { | |
| "step": 2500, | |
| "valid accuracy": 0.44, | |
| "train loss": 0.6293514591455459, | |
| "train samples": 10000, | |
| "train time": 35.19044898093853, | |
| "eval time": 16.654415837998386, | |
| "tokens / sec": 5852.923334725435, | |
| "mem allocated avg": 6914962546.688, | |
| "mem reserved avg": 12361175924.736, | |
| "elapsed time": 965.9673830700012 | |
| }, | |
| { | |
| "step": 2750, | |
| "valid accuracy": 0.34, | |
| "train loss": 0.6212090995311738, | |
| "train samples": 11000, | |
| "train time": 35.78923041201051, | |
| "eval time": 12.364532577001228, | |
| "tokens / sec": 5920.2446535116005, | |
| "mem allocated avg": 6926067247.104, | |
| "mem reserved avg": 12561110007.808, | |
| "elapsed time": 1060.7434992320013 | |
| }, | |
| { | |
| "step": 3000, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.6132309092283249, | |
| "train samples": 12000, | |
| "train time": 35.434680095979274, | |
| "eval time": 10.902270734000922, | |
| "tokens / sec": 5890.585139604081, | |
| "mem allocated avg": 6921261266.944, | |
| "mem reserved avg": 12472811520.0, | |
| "elapsed time": 1153.3681941970026 | |
| }, | |
| { | |
| "step": 3250, | |
| "valid accuracy": 0.5, | |
| "train loss": 0.6223928620815277, | |
| "train samples": 13000, | |
| "train time": 35.475069620017166, | |
| "eval time": 9.885322058999009, | |
| "tokens / sec": 5945.048234126565, | |
| "mem allocated avg": 6922737405.952, | |
| "mem reserved avg": 12498002509.824, | |
| "elapsed time": 1245.241280964001 | |
| }, | |
| { | |
| "step": 3500, | |
| "valid accuracy": 0.5, | |
| "train loss": 0.605602259516716, | |
| "train samples": 14000, | |
| "train time": 35.607162244014035, | |
| "eval time": 10.090815307001321, | |
| "tokens / sec": 5890.668808780496, | |
| "mem allocated avg": 6920974434.304, | |
| "mem reserved avg": 12474329858.048, | |
| "elapsed time": 1337.4724736530006 | |
| }, | |
| { | |
| "step": 3750, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.6031041693687439, | |
| "train samples": 15000, | |
| "train time": 36.209776319014054, | |
| "eval time": 10.371932055000798, | |
| "tokens / sec": 5984.6544781390285, | |
| "mem allocated avg": 6933558140.928, | |
| "mem reserved avg": 12681738190.848, | |
| "elapsed time": 1431.2058649130013 | |
| }, | |
| { | |
| "step": 4000, | |
| "valid accuracy": 0.46, | |
| "train loss": 0.6162525477409363, | |
| "train samples": 16000, | |
| "train time": 35.48366187599095, | |
| "eval time": 12.394127589999698, | |
| "tokens / sec": 5759.636666425441, | |
| "mem allocated avg": 6914222096.384, | |
| "mem reserved avg": 12349406707.712, | |
| "elapsed time": 1525.3134414390006 | |
| }, | |
| { | |
| "step": 4250, | |
| "valid accuracy": 0.5, | |
| "train loss": 0.6013483003377914, | |
| "train samples": 17000, | |
| "train time": 35.15769277801883, | |
| "eval time": 16.63699178299794, | |
| "tokens / sec": 6012.59591562743, | |
| "mem allocated avg": 6924507731.968, | |
| "mem reserved avg": 12521616441.344, | |
| "elapsed time": 1623.6120678540028 | |
| }, | |
| { | |
| "step": 4500, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.6073888168334961, | |
| "train samples": 18000, | |
| "train time": 34.98748015804085, | |
| "eval time": 12.561758541996824, | |
| "tokens / sec": 5939.781860861995, | |
| "mem allocated avg": 6918951696.384, | |
| "mem reserved avg": 12432495869.952, | |
| "elapsed time": 1717.352138276001 | |
| }, | |
| { | |
| "step": 4750, | |
| "valid accuracy": 0.5, | |
| "train loss": 0.5993685643672944, | |
| "train samples": 19000, | |
| "train time": 35.57701125005042, | |
| "eval time": 13.379837485997996, | |
| "tokens / sec": 5900.973483254653, | |
| "mem allocated avg": 6921678901.248, | |
| "mem reserved avg": 12490880581.632, | |
| "elapsed time": 1812.886111721 | |
| }, | |
| { | |
| "step": 5000, | |
| "valid accuracy": 0.48, | |
| "train loss": 0.6068210340738297, | |
| "train samples": 20000, | |
| "train time": 35.678432397002325, | |
| "eval time": 10.087769599998865, | |
| "tokens / sec": 5837.700425916121, | |
| "mem allocated avg": 6918288025.6, | |
| "mem reserved avg": 12423931101.184, | |
| "elapsed time": 1905.221841073002 | |
| }, | |
| { | |
| "step": 5000, | |
| "test accuracy": 0.4806671721000758, | |
| "train loss": 0.6068210340738297, | |
| "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" | |
| } | |
| } | |