Instructions to use socius/Qwentaur-14B-LoRA-r4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use socius/Qwentaur-14B-LoRA-r4 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-14B-Base") model = PeftModel.from_pretrained(base_model, "socius/Qwentaur-14B-LoRA-r4") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download checkpoint-500/trainer_state.json from socius/Qwentaur-14B-LoRA-r4: direct link, hf CLI and curl.
- Browser
- Download file 10.1 kB
-
https://huggingface.co/socius/Qwentaur-14B-LoRA-r4/resolve/main/checkpoint-500/trainer_state.json
- Command line
-
hf download hf://socius/Qwentaur-14B-LoRA-r4/checkpoint-500/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/socius/Qwentaur-14B-LoRA-r4/resolve/main/checkpoint-500/trainer_state.json
10.1 kB
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.26625840378086935, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005325168075617386, | |
| "grad_norm": 0.05487716570496559, | |
| "learning_rate": 4.787234042553191e-06, | |
| "loss": 0.5996371269226074, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010650336151234773, | |
| "grad_norm": 0.043438851833343506, | |
| "learning_rate": 1.0106382978723404e-05, | |
| "loss": 0.6392858028411865, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01597550422685216, | |
| "grad_norm": 0.04921114817261696, | |
| "learning_rate": 1.5425531914893617e-05, | |
| "loss": 0.5546797752380371, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021300672302469546, | |
| "grad_norm": 0.06968632340431213, | |
| "learning_rate": 2.074468085106383e-05, | |
| "loss": 0.598508071899414, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026625840378086935, | |
| "grad_norm": 0.07072321325540543, | |
| "learning_rate": 2.6063829787234046e-05, | |
| "loss": 0.5995429992675781, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03195100845370432, | |
| "grad_norm": 0.11021557450294495, | |
| "learning_rate": 3.1382978723404254e-05, | |
| "loss": 0.6088542938232422, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.037276176529321706, | |
| "grad_norm": 0.10559481382369995, | |
| "learning_rate": 3.670212765957447e-05, | |
| "loss": 0.4991436004638672, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04260134460493909, | |
| "grad_norm": 0.13761867582798004, | |
| "learning_rate": 4.2021276595744684e-05, | |
| "loss": 0.601447582244873, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04792651268055648, | |
| "grad_norm": 0.14284180104732513, | |
| "learning_rate": 4.734042553191489e-05, | |
| "loss": 0.49308085441589355, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05325168075617387, | |
| "grad_norm": 0.13274621963500977, | |
| "learning_rate": 4.985986547085202e-05, | |
| "loss": 0.5244489669799804, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.058576848831791255, | |
| "grad_norm": 0.14783857762813568, | |
| "learning_rate": 4.9579596412556055e-05, | |
| "loss": 0.48787918090820315, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06390201690740864, | |
| "grad_norm": 0.14742612838745117, | |
| "learning_rate": 4.9299327354260097e-05, | |
| "loss": 0.5078488349914551, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06922718498302603, | |
| "grad_norm": 0.26408520340919495, | |
| "learning_rate": 4.9019058295964125e-05, | |
| "loss": 0.48049073219299315, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07455235305864341, | |
| "grad_norm": 0.14286410808563232, | |
| "learning_rate": 4.8738789237668166e-05, | |
| "loss": 0.5604067325592041, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0798775211342608, | |
| "grad_norm": 0.1512993425130844, | |
| "learning_rate": 4.84585201793722e-05, | |
| "loss": 0.5293330669403076, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08520268920987818, | |
| "grad_norm": 0.14961321651935577, | |
| "learning_rate": 4.8178251121076236e-05, | |
| "loss": 0.5038127422332763, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09052785728549557, | |
| "grad_norm": 0.14800076186656952, | |
| "learning_rate": 4.789798206278027e-05, | |
| "loss": 0.4966014862060547, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09585302536111295, | |
| "grad_norm": 0.17610834538936615, | |
| "learning_rate": 4.7617713004484306e-05, | |
| "loss": 0.48385324478149416, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.10117819343673035, | |
| "grad_norm": 0.1252691149711609, | |
| "learning_rate": 4.733744394618834e-05, | |
| "loss": 0.4838716983795166, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.10650336151234774, | |
| "grad_norm": 0.14018668234348297, | |
| "learning_rate": 4.705717488789238e-05, | |
| "loss": 0.4520565032958984, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11182852958796512, | |
| "grad_norm": 0.1684730499982834, | |
| "learning_rate": 4.677690582959641e-05, | |
| "loss": 0.5429281711578369, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11715369766358251, | |
| "grad_norm": 0.22210614383220673, | |
| "learning_rate": 4.649663677130045e-05, | |
| "loss": 0.4519489288330078, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.12247886573919989, | |
| "grad_norm": 0.178190216422081, | |
| "learning_rate": 4.621636771300449e-05, | |
| "loss": 0.45887036323547364, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.12780403381481728, | |
| "grad_norm": 0.16266238689422607, | |
| "learning_rate": 4.593609865470852e-05, | |
| "loss": 0.52867112159729, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.13312920189043467, | |
| "grad_norm": 0.16510607302188873, | |
| "learning_rate": 4.565582959641256e-05, | |
| "loss": 0.45111827850341796, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13845436996605207, | |
| "grad_norm": 0.14936929941177368, | |
| "learning_rate": 4.537556053811659e-05, | |
| "loss": 0.4746635913848877, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.14377953804166943, | |
| "grad_norm": 0.1664894074201584, | |
| "learning_rate": 4.509529147982063e-05, | |
| "loss": 0.5356125354766845, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.14910470611728682, | |
| "grad_norm": 0.13999034464359283, | |
| "learning_rate": 4.481502242152467e-05, | |
| "loss": 0.4625279426574707, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.15442987419290422, | |
| "grad_norm": 0.14819900691509247, | |
| "learning_rate": 4.4534753363228704e-05, | |
| "loss": 0.45238590240478516, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.1597550422685216, | |
| "grad_norm": 0.2902645468711853, | |
| "learning_rate": 4.425448430493274e-05, | |
| "loss": 0.523665189743042, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.165080210344139, | |
| "grad_norm": 0.3842649757862091, | |
| "learning_rate": 4.3974215246636774e-05, | |
| "loss": 0.5117780208587647, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.17040537841975636, | |
| "grad_norm": 0.3537648916244507, | |
| "learning_rate": 4.369394618834081e-05, | |
| "loss": 0.47908267974853513, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.17573054649537376, | |
| "grad_norm": 0.24112680554389954, | |
| "learning_rate": 4.3413677130044844e-05, | |
| "loss": 0.5666882991790771, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.18105571457099115, | |
| "grad_norm": 0.16881901025772095, | |
| "learning_rate": 4.313340807174888e-05, | |
| "loss": 0.49497289657592775, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.18638088264660854, | |
| "grad_norm": 0.16978123784065247, | |
| "learning_rate": 4.2853139013452914e-05, | |
| "loss": 0.46808652877807616, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1917060507222259, | |
| "grad_norm": 0.24577109515666962, | |
| "learning_rate": 4.257286995515695e-05, | |
| "loss": 0.4676064491271973, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.1970312187978433, | |
| "grad_norm": 0.2847534418106079, | |
| "learning_rate": 4.229260089686099e-05, | |
| "loss": 0.5394676685333252, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2023563868734607, | |
| "grad_norm": 0.14291039109230042, | |
| "learning_rate": 4.201233183856502e-05, | |
| "loss": 0.4125664234161377, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.20768155494907808, | |
| "grad_norm": 0.31676554679870605, | |
| "learning_rate": 4.173206278026906e-05, | |
| "loss": 0.41750164031982423, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.21300672302469548, | |
| "grad_norm": 0.2844577133655548, | |
| "learning_rate": 4.1451793721973096e-05, | |
| "loss": 0.4729475021362305, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21833189110031284, | |
| "grad_norm": 0.2866207957267761, | |
| "learning_rate": 4.117152466367713e-05, | |
| "loss": 0.5492980003356933, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.22365705917593023, | |
| "grad_norm": 0.38996192812919617, | |
| "learning_rate": 4.0891255605381166e-05, | |
| "loss": 0.4734052181243896, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.22898222725154763, | |
| "grad_norm": 0.1881261020898819, | |
| "learning_rate": 4.061098654708521e-05, | |
| "loss": 0.4500300407409668, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.23430739532716502, | |
| "grad_norm": 0.20594148337841034, | |
| "learning_rate": 4.0330717488789236e-05, | |
| "loss": 0.4548191547393799, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.2396325634027824, | |
| "grad_norm": 0.22915281355381012, | |
| "learning_rate": 4.005044843049328e-05, | |
| "loss": 0.465634822845459, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.24495773147839978, | |
| "grad_norm": 0.3207595646381378, | |
| "learning_rate": 3.977017937219731e-05, | |
| "loss": 0.5047284603118897, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.25028289955401717, | |
| "grad_norm": 0.17310434579849243, | |
| "learning_rate": 3.948991031390135e-05, | |
| "loss": 0.45878047943115235, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.25560806762963456, | |
| "grad_norm": 0.1512192338705063, | |
| "learning_rate": 3.920964125560538e-05, | |
| "loss": 0.44451174736022947, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.26093323570525195, | |
| "grad_norm": 0.17040136456489563, | |
| "learning_rate": 3.8929372197309424e-05, | |
| "loss": 0.485479736328125, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.26625840378086935, | |
| "grad_norm": 0.3218516707420349, | |
| "learning_rate": 3.864910313901345e-05, | |
| "loss": 0.47697882652282714, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1878, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.78139605226409e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |