caf324b09d
Build documentation / build (push) Failing after 0s
Deploy "method_comparison" Gradio to Spaces / deploy (push) Has been cancelled
Deploy "PEFT shop" Gradio app to Spaces / deploy (push) Has been cancelled
tests on transformers main / tests (push) Has been cancelled
tests / check_code_quality (push) Has been cancelled
tests / tests (ubuntu-latest, 3.10) (push) Has been cancelled
tests / tests (ubuntu-latest, 3.11) (push) Has been cancelled
tests / tests (ubuntu-latest, 3.12) (push) Has been cancelled
tests / tests (ubuntu-latest, 3.13) (push) Has been cancelled
tests / tests (windows-latest, 3.10) (push) Has been cancelled
tests / tests (windows-latest, 3.11) (push) Has been cancelled
tests / tests (windows-latest, 3.12) (push) Has been cancelled
tests / tests (windows-latest, 3.13) (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
CI security linting / zizmor latest via Cargo (push) Has been cancelled
364 lines
13 KiB
JSON
364 lines
13 KiB
JSON
{
|
|
"run_info": {
|
|
"created_at": "2026-04-14T17:45:54+00:00",
|
|
"total_time": 1937.8156919419998,
|
|
"experiment_name": "psoft/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,
|
|
"init_kv_cache_prefix": null
|
|
},
|
|
"peft_config": {
|
|
"task_type": null,
|
|
"peft_type": "PSOFT",
|
|
"auto_mapping": null,
|
|
"peft_version": "0.19.0",
|
|
"base_model_name_or_path": "meta-llama/Llama-3.2-3B",
|
|
"revision": null,
|
|
"inference_mode": false,
|
|
"r": 256,
|
|
"target_modules": [
|
|
"q_proj",
|
|
"v_proj"
|
|
],
|
|
"exclude_modules": null,
|
|
"psoft_alpha": 256,
|
|
"psoft_dropout": 0.0,
|
|
"fan_in_fan_out": false,
|
|
"ab_svd_init": "psoft_init",
|
|
"psoft_svd": "full",
|
|
"psoft_svd_lowrank_niter": 10,
|
|
"psoft_orth": true,
|
|
"psoft_mag_b": true,
|
|
"psoft_mag_a": true,
|
|
"use_cayley_neumann": false,
|
|
"num_cayley_neumann_terms": 5,
|
|
"cayley_neumann_eps": null,
|
|
"modules_to_save": null,
|
|
"init_weights": true,
|
|
"layers_to_transform": null,
|
|
"layers_pattern": null
|
|
},
|
|
"error_msg": ""
|
|
},
|
|
"train_info": {
|
|
"accelerator_memory_reserved_avg": 15026516446,
|
|
"accelerator_memory_max": 21990735872,
|
|
"accelerator_memory_reserved_99th": 20199768064,
|
|
"train_time": 1505.385764200997,
|
|
"file_size": 7448144,
|
|
"num_trainable_params": 1856512,
|
|
"num_total_params": 3214606336,
|
|
"status": "success",
|
|
"metrics": [
|
|
{
|
|
"step": 250,
|
|
"valid accuracy": 0.34,
|
|
"train loss": 1.01516472530365,
|
|
"train samples": 1000,
|
|
"train time": 43.33842796702811,
|
|
"eval time": 24.252313315009815,
|
|
"tokens / sec": 4885.248725705415,
|
|
"mem allocated avg": 8375423072.256,
|
|
"mem reserved avg": 15119048245.248,
|
|
"elapsed time": 90.0036859739921
|
|
},
|
|
{
|
|
"step": 500,
|
|
"valid accuracy": 0.32,
|
|
"train loss": 0.7340580285787582,
|
|
"train samples": 2000,
|
|
"train time": 43.51892344804946,
|
|
"eval time": 24.25320322001062,
|
|
"tokens / sec": 4779.415103139975,
|
|
"mem allocated avg": 8368352468.992,
|
|
"mem reserved avg": 14813082157.056,
|
|
"elapsed time": 160.662997152991
|
|
},
|
|
{
|
|
"step": 750,
|
|
"valid accuracy": 0.44,
|
|
"train loss": 0.6879250873327255,
|
|
"train samples": 3000,
|
|
"train time": 43.93279401304608,
|
|
"eval time": 23.87379320099717,
|
|
"tokens / sec": 4880.204066609842,
|
|
"mem allocated avg": 8378198431.744,
|
|
"mem reserved avg": 14968892162.048,
|
|
"elapsed time": 231.33524189700256
|
|
},
|
|
{
|
|
"step": 1000,
|
|
"valid accuracy": 0.5,
|
|
"train loss": 0.6680566596984864,
|
|
"train samples": 4000,
|
|
"train time": 43.45829963689903,
|
|
"eval time": 24.127080324993585,
|
|
"tokens / sec": 4793.928932808698,
|
|
"mem allocated avg": 8369458450.432,
|
|
"mem reserved avg": 15005365829.632,
|
|
"elapsed time": 301.8884777850035
|
|
},
|
|
{
|
|
"step": 1250,
|
|
"valid accuracy": 0.42,
|
|
"train loss": 0.6644437726736069,
|
|
"train samples": 5000,
|
|
"train time": 42.981003544147825,
|
|
"eval time": 19.512033010993036,
|
|
"tokens / sec": 4851.864377382458,
|
|
"mem allocated avg": 8369734297.6,
|
|
"mem reserved avg": 14974629969.92,
|
|
"elapsed time": 367.2329926319944
|
|
},
|
|
{
|
|
"step": 1500,
|
|
"valid accuracy": 0.5,
|
|
"train loss": 0.656409296989441,
|
|
"train samples": 6000,
|
|
"train time": 43.40368786803447,
|
|
"eval time": 24.234126267998363,
|
|
"tokens / sec": 4822.885111432342,
|
|
"mem allocated avg": 8371589535.744,
|
|
"mem reserved avg": 14985442885.632,
|
|
"elapsed time": 437.7650993739953
|
|
},
|
|
{
|
|
"step": 1750,
|
|
"valid accuracy": 0.4,
|
|
"train loss": 0.6492917109727859,
|
|
"train samples": 7000,
|
|
"train time": 43.8191164049349,
|
|
"eval time": 17.957069406998926,
|
|
"tokens / sec": 4777.709300784131,
|
|
"mem allocated avg": 8373423994.88,
|
|
"mem reserved avg": 15362972188.672,
|
|
"elapsed time": 502.5296421480016
|
|
},
|
|
{
|
|
"step": 2000,
|
|
"valid accuracy": 0.4,
|
|
"train loss": 0.651351011633873,
|
|
"train samples": 8000,
|
|
"train time": 43.91826998388569,
|
|
"eval time": 19.85821281799872,
|
|
"tokens / sec": 4729.148030562382,
|
|
"mem allocated avg": 8368890132.48,
|
|
"mem reserved avg": 15046822330.368,
|
|
"elapsed time": 569.3082349729957
|
|
},
|
|
{
|
|
"step": 2250,
|
|
"valid accuracy": 0.46,
|
|
"train loss": 0.6434478094577789,
|
|
"train samples": 9000,
|
|
"train time": 44.214122023113305,
|
|
"eval time": 24.340498196994304,
|
|
"tokens / sec": 4861.52365272874,
|
|
"mem allocated avg": 8379377248.256,
|
|
"mem reserved avg": 15277374832.64,
|
|
"elapsed time": 640.7805861020024
|
|
},
|
|
{
|
|
"step": 2500,
|
|
"valid accuracy": 0.44,
|
|
"train loss": 0.6421752452850342,
|
|
"train samples": 10000,
|
|
"train time": 43.76370210298046,
|
|
"eval time": 24.20965617800539,
|
|
"tokens / sec": 4706.343158888583,
|
|
"mem allocated avg": 8365997271.04,
|
|
"mem reserved avg": 14821965692.928,
|
|
"elapsed time": 711.6298649300006
|
|
},
|
|
{
|
|
"step": 2750,
|
|
"valid accuracy": 0.44,
|
|
"train loss": 0.634340330004692,
|
|
"train samples": 11000,
|
|
"train time": 43.842665812029736,
|
|
"eval time": 21.91094351799984,
|
|
"tokens / sec": 4832.758138120862,
|
|
"mem allocated avg": 8375715567.616,
|
|
"mem reserved avg": 15151327608.832,
|
|
"elapsed time": 780.2465031659958
|
|
},
|
|
{
|
|
"step": 3000,
|
|
"valid accuracy": 0.4,
|
|
"train loss": 0.6267138615846634,
|
|
"train samples": 12000,
|
|
"train time": 43.95662597400951,
|
|
"eval time": 24.438440626996453,
|
|
"tokens / sec": 4748.567374652858,
|
|
"mem allocated avg": 8371726731.264,
|
|
"mem reserved avg": 15071677775.872,
|
|
"elapsed time": 851.6106786309974
|
|
},
|
|
{
|
|
"step": 3250,
|
|
"valid accuracy": 0.46,
|
|
"train loss": 0.6364041697978974,
|
|
"train samples": 13000,
|
|
"train time": 43.44346187009069,
|
|
"eval time": 13.787291264001396,
|
|
"tokens / sec": 4854.608516942293,
|
|
"mem allocated avg": 8373763536.896,
|
|
"mem reserved avg": 14988026576.896,
|
|
"elapsed time": 911.682741933997
|
|
},
|
|
{
|
|
"step": 3500,
|
|
"valid accuracy": 0.48,
|
|
"train loss": 0.6214166321754455,
|
|
"train samples": 14000,
|
|
"train time": 43.80178445095953,
|
|
"eval time": 17.285016585999983,
|
|
"tokens / sec": 4788.617692843908,
|
|
"mem allocated avg": 8371230976.0,
|
|
"mem reserved avg": 15019198644.224,
|
|
"elapsed time": 975.6572376149998
|
|
},
|
|
{
|
|
"step": 3750,
|
|
"valid accuracy": 0.48,
|
|
"train loss": 0.6196781145334244,
|
|
"train samples": 15000,
|
|
"train time": 44.90675747311616,
|
|
"eval time": 17.868283932999475,
|
|
"tokens / sec": 4825.621180280746,
|
|
"mem allocated avg": 8381897398.272,
|
|
"mem reserved avg": 15295502614.528,
|
|
"elapsed time": 1041.3160545689898
|
|
},
|
|
{
|
|
"step": 4000,
|
|
"valid accuracy": 0.46,
|
|
"train loss": 0.6325693914890289,
|
|
"train samples": 16000,
|
|
"train time": 43.95797020303144,
|
|
"eval time": 21.001378130997182,
|
|
"tokens / sec": 4649.282008610716,
|
|
"mem allocated avg": 8363390388.224,
|
|
"mem reserved avg": 15030305161.216,
|
|
"elapsed time": 1109.2579419859976
|
|
},
|
|
{
|
|
"step": 4250,
|
|
"valid accuracy": 0.48,
|
|
"train loss": 0.6181137851476669,
|
|
"train samples": 17000,
|
|
"train time": 43.63497660578287,
|
|
"eval time": 14.508927531001973,
|
|
"tokens / sec": 4844.485237376865,
|
|
"mem allocated avg": 8374695139.328,
|
|
"mem reserved avg": 15006825447.424,
|
|
"elapsed time": 1170.2475494539976
|
|
},
|
|
{
|
|
"step": 4500,
|
|
"valid accuracy": 0.44,
|
|
"train loss": 0.6251096996068954,
|
|
"train samples": 18000,
|
|
"train time": 43.71482467187161,
|
|
"eval time": 17.362020947999554,
|
|
"tokens / sec": 4753.9479240716455,
|
|
"mem allocated avg": 8369678581.76,
|
|
"mem reserved avg": 14920213069.824,
|
|
"elapsed time": 1234.2639348649973
|
|
},
|
|
{
|
|
"step": 4750,
|
|
"valid accuracy": 0.4,
|
|
"train loss": 0.6170058059692383,
|
|
"train samples": 19000,
|
|
"train time": 44.26034616607649,
|
|
"eval time": 14.061754546011798,
|
|
"tokens / sec": 4743.275147741808,
|
|
"mem allocated avg": 8372185092.096,
|
|
"mem reserved avg": 14964882407.424,
|
|
"elapsed time": 1295.4217767660011
|
|
},
|
|
{
|
|
"step": 5000,
|
|
"valid accuracy": 0.42,
|
|
"train loss": 0.6243607197999954,
|
|
"train samples": 20000,
|
|
"train time": 43.99801491193648,
|
|
"eval time": 15.62990901999001,
|
|
"tokens / sec": 4733.849934295434,
|
|
"mem allocated avg": 8368538847.232,
|
|
"mem reserved avg": 14706773327.872,
|
|
"elapsed time": 1357.9020721779962
|
|
},
|
|
{
|
|
"step": 5000,
|
|
"test accuracy": 0.4488248673237301,
|
|
"train loss": 0.6243607197999954,
|
|
"train samples": 20000,
|
|
"train total tokens": 4198051,
|
|
"forgetting": 0.5123701095581055
|
|
}
|
|
]
|
|
},
|
|
"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": "740312add88f781978c0658806c59bc2815b9866",
|
|
"created_at": "2022-04-12T10:22:10+00:00"
|
|
}
|
|
},
|
|
"package_info": {
|
|
"transformers-version": "5.5.4",
|
|
"transformers-commit-hash": null,
|
|
"peft-version": "0.19.0",
|
|
"peft-commit-hash": "6d5a6f4f2f902dbf13d21d2661d57c3c05df1dae",
|
|
"datasets-version": "4.2.0",
|
|
"datasets-commit-hash": null,
|
|
"bitsandbytes-version": "0.46.0",
|
|
"bitsandbytes-commit-hash": null,
|
|
"torch-version": "2.9.0+cu128",
|
|
"torch-commit-hash": null
|
|
},
|
|
"system_info": {
|
|
"system": "Linux",
|
|
"release": "6.17.0-1009-aws",
|
|
"version": "#9~24.04.2-Ubuntu SMP Fri Mar 6 23:50:29 UTC 2026",
|
|
"machine": "x86_64",
|
|
"processor": "x86_64",
|
|
"accelerator": "NVIDIA L40S"
|
|
},
|
|
"pytorch_info": "PyTorch built with:\n - GCC 13.3\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 12.8\n - NVCC architecture flags: -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;-gencode;arch=compute_100,code=sm_100;-gencode;arch=compute_120,code=sm_120\n - CuDNN 90.7.1\n - Built with CuDNN 90.8\n - Magma 2.6.1\n - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=0fabc3ba44823f257e70ce397d989c8de5e362c1, CUDA_VERSION=12.8, CUDNN_VERSION=9.8.0, CXX_COMPILER=/opt/rh/gcc-toolset-13/root/usr/bin/c++, CXX_FLAGS= -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 -DC10_NODEPRECATED -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 -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-dangling-reference -Wno-error=dangling-reference -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.9.0, 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, USE_XCCL=OFF, USE_XPU=OFF, \n"
|
|
}
|
|
} |