wehub-resource-sync
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
359 lines
13 KiB
JSON
359 lines
13 KiB
JSON
{
|
|
"run_info": {
|
|
"created_at": "2026-01-10T10:03:45+00:00",
|
|
"total_time": 1442.0607667469885,
|
|
"experiment_name": "vblora/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": "VBLORA",
|
|
"auto_mapping": null,
|
|
"peft_version": "0.18.1.dev0@UNKNOWN",
|
|
"base_model_name_or_path": "meta-llama/Llama-3.2-3B",
|
|
"revision": null,
|
|
"inference_mode": false,
|
|
"r": 4,
|
|
"num_vectors": 256,
|
|
"vector_length": 256,
|
|
"topk": 2,
|
|
"target_modules": [
|
|
"q_proj",
|
|
"v_proj"
|
|
],
|
|
"exclude_modules": null,
|
|
"save_only_topk_weights": false,
|
|
"vblora_dropout": 0.0,
|
|
"fan_in_fan_out": false,
|
|
"bias": "none",
|
|
"modules_to_save": null,
|
|
"init_vector_bank_bound": 0.02,
|
|
"init_logits_std": 0.1,
|
|
"layers_to_transform": null,
|
|
"layers_pattern": null
|
|
},
|
|
"error_msg": ""
|
|
},
|
|
"train_info": {
|
|
"accelerator_memory_reserved_avg": 14315209883,
|
|
"accelerator_memory_max": 22168993792,
|
|
"accelerator_memory_reserved_99th": 20019412992,
|
|
"train_time": 1188.2950591499684,
|
|
"file_size": 4864912,
|
|
"num_trainable_params": 1212416,
|
|
"num_total_params": 3213962240,
|
|
"status": "success",
|
|
"metrics": [
|
|
{
|
|
"step": 250,
|
|
"valid accuracy": 0.0,
|
|
"train loss": 1.3084168200492858,
|
|
"train samples": 1000,
|
|
"train time": 38.33692664222326,
|
|
"eval time": 13.785690262040589,
|
|
"tokens / sec": 5522.586668875496,
|
|
"mem allocated avg": 6799863355.392,
|
|
"mem reserved avg": 14422449848.32,
|
|
"elapsed time": 74.86309108795831
|
|
},
|
|
{
|
|
"step": 500,
|
|
"valid accuracy": 0.38,
|
|
"train loss": 1.0353211274147034,
|
|
"train samples": 2000,
|
|
"train time": 38.09402504004538,
|
|
"eval time": 13.701952785020694,
|
|
"tokens / sec": 5460.042612492392,
|
|
"mem allocated avg": 6792844609.536,
|
|
"mem reserved avg": 14055465025.536,
|
|
"elapsed time": 129.952204842004
|
|
},
|
|
{
|
|
"step": 750,
|
|
"valid accuracy": 0.3,
|
|
"train loss": 0.8149400570392609,
|
|
"train samples": 3000,
|
|
"train time": 38.48971955140587,
|
|
"eval time": 13.7833748270059,
|
|
"tokens / sec": 5570.344562101877,
|
|
"mem allocated avg": 6803264000.0,
|
|
"mem reserved avg": 14282477535.232,
|
|
"elapsed time": 185.41029871697538
|
|
},
|
|
{
|
|
"step": 1000,
|
|
"valid accuracy": 0.3,
|
|
"train loss": 0.7666769211292267,
|
|
"train samples": 4000,
|
|
"train time": 38.318057818338275,
|
|
"eval time": 13.802792146976572,
|
|
"tokens / sec": 5437.018780745575,
|
|
"mem allocated avg": 6793968019.456,
|
|
"mem reserved avg": 14342078595.072,
|
|
"elapsed time": 240.8755328389816
|
|
},
|
|
{
|
|
"step": 1250,
|
|
"valid accuracy": 0.34,
|
|
"train loss": 0.7546750259399414,
|
|
"train samples": 5000,
|
|
"train time": 38.47422462084796,
|
|
"eval time": 10.539507273002528,
|
|
"tokens / sec": 5420.200200395978,
|
|
"mem allocated avg": 6794672488.448,
|
|
"mem reserved avg": 14357513633.792,
|
|
"elapsed time": 293.10720169899287
|
|
},
|
|
{
|
|
"step": 1500,
|
|
"valid accuracy": 0.34,
|
|
"train loss": 0.7437419641017914,
|
|
"train samples": 6000,
|
|
"train time": 38.40448851091787,
|
|
"eval time": 13.719243174011353,
|
|
"tokens / sec": 5450.691002966751,
|
|
"mem allocated avg": 6796510103.552,
|
|
"mem reserved avg": 14279759626.24,
|
|
"elapsed time": 348.5309307149728
|
|
},
|
|
{
|
|
"step": 1750,
|
|
"valid accuracy": 0.4,
|
|
"train loss": 0.7351079850196839,
|
|
"train samples": 7000,
|
|
"train time": 38.52799471229082,
|
|
"eval time": 13.719382153009064,
|
|
"tokens / sec": 5433.8410696784495,
|
|
"mem allocated avg": 6797950621.696,
|
|
"mem reserved avg": 14646685728.768,
|
|
"elapsed time": 404.0734379639616
|
|
},
|
|
{
|
|
"step": 2000,
|
|
"valid accuracy": 0.34,
|
|
"train loss": 0.7361109793186188,
|
|
"train samples": 8000,
|
|
"train time": 38.6812528463779,
|
|
"eval time": 13.746708846010733,
|
|
"tokens / sec": 5369.422775029082,
|
|
"mem allocated avg": 6793576230.912,
|
|
"mem reserved avg": 14290614484.992,
|
|
"elapsed time": 459.8579424939817
|
|
},
|
|
{
|
|
"step": 2250,
|
|
"valid accuracy": 0.42,
|
|
"train loss": 0.7294788275957107,
|
|
"train samples": 9000,
|
|
"train time": 38.70111024065409,
|
|
"eval time": 9.169133496005088,
|
|
"tokens / sec": 5554.052549484873,
|
|
"mem allocated avg": 6804150888.448,
|
|
"mem reserved avg": 14586505854.976,
|
|
"elapsed time": 510.9330796489958
|
|
},
|
|
{
|
|
"step": 2500,
|
|
"valid accuracy": 0.42,
|
|
"train loss": 0.7272682936191559,
|
|
"train samples": 10000,
|
|
"train time": 38.18993485230021,
|
|
"eval time": 13.75650224700803,
|
|
"tokens / sec": 5393.22732014544,
|
|
"mem allocated avg": 6791362646.016,
|
|
"mem reserved avg": 14089313058.816,
|
|
"elapsed time": 566.1566062810016
|
|
},
|
|
{
|
|
"step": 2750,
|
|
"valid accuracy": 0.34,
|
|
"train loss": 0.7220834786891938,
|
|
"train samples": 11000,
|
|
"train time": 38.772894190915395,
|
|
"eval time": 13.813729731016792,
|
|
"tokens / sec": 5464.668150814606,
|
|
"mem allocated avg": 6800614600.704,
|
|
"mem reserved avg": 14463805685.76,
|
|
"elapsed time": 621.9531869380153
|
|
},
|
|
{
|
|
"step": 3000,
|
|
"valid accuracy": 0.32,
|
|
"train loss": 0.7162344917058945,
|
|
"train samples": 12000,
|
|
"train time": 38.64312012627488,
|
|
"eval time": 13.718790433020331,
|
|
"tokens / sec": 5401.504829784076,
|
|
"mem allocated avg": 6796550658.048,
|
|
"mem reserved avg": 14397560848.384,
|
|
"elapsed time": 677.6688264649711
|
|
},
|
|
{
|
|
"step": 3250,
|
|
"valid accuracy": 0.3,
|
|
"train loss": 0.7240759524106979,
|
|
"train samples": 13000,
|
|
"train time": 38.53601192642236,
|
|
"eval time": 8.802515299990773,
|
|
"tokens / sec": 5472.828906184632,
|
|
"mem allocated avg": 6799288741.888,
|
|
"mem reserved avg": 14244904960.0,
|
|
"elapsed time": 728.1590657840134
|
|
},
|
|
{
|
|
"step": 3500,
|
|
"valid accuracy": 0.34,
|
|
"train loss": 0.7126485753059387,
|
|
"train samples": 14000,
|
|
"train time": 38.67533435986843,
|
|
"eval time": 10.104931714013219,
|
|
"tokens / sec": 5423.353242361304,
|
|
"mem allocated avg": 6796233105.408,
|
|
"mem reserved avg": 14249518694.4,
|
|
"elapsed time": 780.2666325760074
|
|
},
|
|
{
|
|
"step": 3750,
|
|
"valid accuracy": 0.34,
|
|
"train loss": 0.7088012579679489,
|
|
"train samples": 15000,
|
|
"train time": 39.28342586872168,
|
|
"eval time": 13.906550085986964,
|
|
"tokens / sec": 5516.397697191264,
|
|
"mem allocated avg": 6807167205.376,
|
|
"mem reserved avg": 14590800822.272,
|
|
"elapsed time": 836.7359555650037
|
|
},
|
|
{
|
|
"step": 4000,
|
|
"valid accuracy": 0.38,
|
|
"train loss": 0.7263217406272888,
|
|
"train samples": 16000,
|
|
"train time": 38.43631436518626,
|
|
"eval time": 13.765814298996702,
|
|
"tokens / sec": 5317.185150954824,
|
|
"mem allocated avg": 6788341315.584,
|
|
"mem reserved avg": 14278853656.576,
|
|
"elapsed time": 892.29195685999
|
|
},
|
|
{
|
|
"step": 4250,
|
|
"valid accuracy": 0.34,
|
|
"train loss": 0.7048129771947861,
|
|
"train samples": 17000,
|
|
"train time": 38.582715313415974,
|
|
"eval time": 10.130817791970912,
|
|
"tokens / sec": 5478.85233796637,
|
|
"mem allocated avg": 6800143554.56,
|
|
"mem reserved avg": 14243218849.792,
|
|
"elapsed time": 944.1107314319815
|
|
},
|
|
{
|
|
"step": 4500,
|
|
"valid accuracy": 0.28,
|
|
"train loss": 0.7155517739057541,
|
|
"train samples": 18000,
|
|
"train time": 38.19235976098571,
|
|
"eval time": 9.205565118987579,
|
|
"tokens / sec": 5441.3500841676305,
|
|
"mem allocated avg": 6793989150.72,
|
|
"mem reserved avg": 14201930121.216,
|
|
"elapsed time": 994.8280632529641
|
|
},
|
|
{
|
|
"step": 4750,
|
|
"valid accuracy": 0.4,
|
|
"train loss": 0.7085129739046097,
|
|
"train samples": 19000,
|
|
"train time": 38.29387024784228,
|
|
"eval time": 13.80606703099329,
|
|
"tokens / sec": 5482.313452290169,
|
|
"mem allocated avg": 6796964847.616,
|
|
"mem reserved avg": 14314161307.648,
|
|
"elapsed time": 1050.1360529760132
|
|
},
|
|
{
|
|
"step": 5000,
|
|
"valid accuracy": 0.38,
|
|
"train loss": 0.714538745880127,
|
|
"train samples": 20000,
|
|
"train time": 38.23504033399513,
|
|
"eval time": 13.824080880964175,
|
|
"tokens / sec": 5447.359233326512,
|
|
"mem allocated avg": 6793035892.736,
|
|
"mem reserved avg": 13966579335.168,
|
|
"elapsed time": 1105.3972024219693
|
|
},
|
|
{
|
|
"step": 5000,
|
|
"test accuracy": 0.354814253222138,
|
|
"train loss": 0.714538745880127,
|
|
"train samples": 20000,
|
|
"train total tokens": 4198051,
|
|
"forgetting": -0.010824203491210938
|
|
}
|
|
]
|
|
},
|
|
"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": "cc7b047b6e5bb11b4f1af84efc572db110a51b3c",
|
|
"created_at": "2022-04-12T10:22:10+00:00"
|
|
}
|
|
},
|
|
"package_info": {
|
|
"transformers-version": "4.57.1",
|
|
"transformers-commit-hash": null,
|
|
"peft-version": "0.18.1.dev0",
|
|
"peft-commit-hash": "8be1a16f5e06ca5e197d2af74bdfc5b3c8072d26",
|
|
"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": "6.14.0-1016-aws",
|
|
"version": "#16~24.04.1-Ubuntu SMP Tue Oct 14 02:15:09 UTC 2025",
|
|
"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"
|
|
}
|
|
} |