Instructions to use socius/Llama-Centaur-3B-LoRA-r8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use socius/Llama-Centaur-3B-LoRA-r8 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.2-3B") model = PeftModel.from_pretrained(base_model, "socius/Llama-Centaur-3B-LoRA-r8") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download checkpoint-500/trainer_state.json from socius/Llama-Centaur-3B-LoRA-r8: direct link, hf CLI and curl.
- Browser
- Download file 10.1 kB
-
https://huggingface.co/socius/Llama-Centaur-3B-LoRA-r8/resolve/main/checkpoint-500/trainer_state.json
- Command line
-
hf download hf://socius/Llama-Centaur-3B-LoRA-r8/checkpoint-500/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/socius/Llama-Centaur-3B-LoRA-r8/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": 0.20683516561985016, | |
| "learning_rate": 4.787234042553191e-06, | |
| "loss": 0.7822918891906738, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010650336151234773, | |
| "grad_norm": 0.3277234733104706, | |
| "learning_rate": 1.0106382978723404e-05, | |
| "loss": 0.7612236499786377, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01597550422685216, | |
| "grad_norm": 0.36984074115753174, | |
| "learning_rate": 1.5425531914893617e-05, | |
| "loss": 0.6511845111846923, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021300672302469546, | |
| "grad_norm": 0.20985147356987, | |
| "learning_rate": 2.074468085106383e-05, | |
| "loss": 0.6681060314178466, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026625840378086935, | |
| "grad_norm": 0.7140442728996277, | |
| "learning_rate": 2.6063829787234046e-05, | |
| "loss": 0.659309196472168, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03195100845370432, | |
| "grad_norm": 0.42718973755836487, | |
| "learning_rate": 3.1382978723404254e-05, | |
| "loss": 0.6909014225006104, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.037276176529321706, | |
| "grad_norm": 0.3533357083797455, | |
| "learning_rate": 3.670212765957447e-05, | |
| "loss": 0.5650594711303711, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04260134460493909, | |
| "grad_norm": 0.417624831199646, | |
| "learning_rate": 4.2021276595744684e-05, | |
| "loss": 0.6802642345428467, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04792651268055648, | |
| "grad_norm": 0.35949471592903137, | |
| "learning_rate": 4.734042553191489e-05, | |
| "loss": 0.5739238739013672, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05325168075617387, | |
| "grad_norm": 0.3818545937538147, | |
| "learning_rate": 4.985986547085202e-05, | |
| "loss": 0.5993009090423584, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.058576848831791255, | |
| "grad_norm": 0.4698786437511444, | |
| "learning_rate": 4.9579596412556055e-05, | |
| "loss": 0.557436180114746, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06390201690740864, | |
| "grad_norm": 0.35443201661109924, | |
| "learning_rate": 4.9299327354260097e-05, | |
| "loss": 0.581347131729126, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06922718498302603, | |
| "grad_norm": 0.7349355220794678, | |
| "learning_rate": 4.9019058295964125e-05, | |
| "loss": 0.5600838661193848, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07455235305864341, | |
| "grad_norm": 0.5207298398017883, | |
| "learning_rate": 4.8738789237668166e-05, | |
| "loss": 0.6590728282928466, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0798775211342608, | |
| "grad_norm": 0.6123145222663879, | |
| "learning_rate": 4.84585201793722e-05, | |
| "loss": 0.5984565734863281, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08520268920987818, | |
| "grad_norm": 0.37944698333740234, | |
| "learning_rate": 4.8178251121076236e-05, | |
| "loss": 0.5809710502624512, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09052785728549557, | |
| "grad_norm": 0.48942145705223083, | |
| "learning_rate": 4.789798206278027e-05, | |
| "loss": 0.5642497062683105, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09585302536111295, | |
| "grad_norm": 0.42988479137420654, | |
| "learning_rate": 4.7617713004484306e-05, | |
| "loss": 0.5531106472015381, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.10117819343673035, | |
| "grad_norm": 0.4417687654495239, | |
| "learning_rate": 4.733744394618834e-05, | |
| "loss": 0.5732029438018799, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.10650336151234774, | |
| "grad_norm": 0.2549873888492584, | |
| "learning_rate": 4.705717488789238e-05, | |
| "loss": 0.5021458625793457, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11182852958796512, | |
| "grad_norm": 0.4950169622898102, | |
| "learning_rate": 4.677690582959641e-05, | |
| "loss": 0.641213846206665, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11715369766358251, | |
| "grad_norm": 0.456673264503479, | |
| "learning_rate": 4.649663677130045e-05, | |
| "loss": 0.5225620746612549, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.12247886573919989, | |
| "grad_norm": 0.6995387077331543, | |
| "learning_rate": 4.621636771300449e-05, | |
| "loss": 0.5139231204986572, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.12780403381481728, | |
| "grad_norm": 0.26585784554481506, | |
| "learning_rate": 4.593609865470852e-05, | |
| "loss": 0.5961785793304444, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.13312920189043467, | |
| "grad_norm": 0.5705807209014893, | |
| "learning_rate": 4.565582959641256e-05, | |
| "loss": 0.5149649143218994, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13845436996605207, | |
| "grad_norm": 0.39890748262405396, | |
| "learning_rate": 4.537556053811659e-05, | |
| "loss": 0.5415900230407715, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.14377953804166943, | |
| "grad_norm": 0.32965633273124695, | |
| "learning_rate": 4.509529147982063e-05, | |
| "loss": 0.5950401782989502, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.14910470611728682, | |
| "grad_norm": 0.6010472178459167, | |
| "learning_rate": 4.481502242152467e-05, | |
| "loss": 0.5145067691802978, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.15442987419290422, | |
| "grad_norm": 0.3178304135799408, | |
| "learning_rate": 4.4534753363228704e-05, | |
| "loss": 0.505909013748169, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.1597550422685216, | |
| "grad_norm": 0.48335757851600647, | |
| "learning_rate": 4.425448430493274e-05, | |
| "loss": 0.6062196254730224, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.165080210344139, | |
| "grad_norm": 0.6835651993751526, | |
| "learning_rate": 4.3974215246636774e-05, | |
| "loss": 0.6059549808502197, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.17040537841975636, | |
| "grad_norm": 0.3845309019088745, | |
| "learning_rate": 4.369394618834081e-05, | |
| "loss": 0.5377228736877442, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.17573054649537376, | |
| "grad_norm": 0.7088361382484436, | |
| "learning_rate": 4.3413677130044844e-05, | |
| "loss": 0.6384317398071289, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.18105571457099115, | |
| "grad_norm": 0.33346283435821533, | |
| "learning_rate": 4.313340807174888e-05, | |
| "loss": 0.5557454586029053, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.18638088264660854, | |
| "grad_norm": 0.3019021153450012, | |
| "learning_rate": 4.2853139013452914e-05, | |
| "loss": 0.518170690536499, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1917060507222259, | |
| "grad_norm": 0.5704140067100525, | |
| "learning_rate": 4.257286995515695e-05, | |
| "loss": 0.524034070968628, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.1970312187978433, | |
| "grad_norm": 0.6912387013435364, | |
| "learning_rate": 4.229260089686099e-05, | |
| "loss": 0.6240747451782227, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2023563868734607, | |
| "grad_norm": 0.35987111926078796, | |
| "learning_rate": 4.201233183856502e-05, | |
| "loss": 0.45235018730163573, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.20768155494907808, | |
| "grad_norm": 0.3558119535446167, | |
| "learning_rate": 4.173206278026906e-05, | |
| "loss": 0.4568950176239014, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.21300672302469548, | |
| "grad_norm": 0.44445547461509705, | |
| "learning_rate": 4.1451793721973096e-05, | |
| "loss": 0.5185273647308349, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21833189110031284, | |
| "grad_norm": 0.6698095798492432, | |
| "learning_rate": 4.117152466367713e-05, | |
| "loss": 0.6193028450012207, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.22365705917593023, | |
| "grad_norm": 0.7176916599273682, | |
| "learning_rate": 4.0891255605381166e-05, | |
| "loss": 0.5141634464263916, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.22898222725154763, | |
| "grad_norm": 0.3718442916870117, | |
| "learning_rate": 4.061098654708521e-05, | |
| "loss": 0.49727892875671387, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.23430739532716502, | |
| "grad_norm": 0.47129976749420166, | |
| "learning_rate": 4.0330717488789236e-05, | |
| "loss": 0.4925837993621826, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.2396325634027824, | |
| "grad_norm": 0.5557712912559509, | |
| "learning_rate": 4.005044843049328e-05, | |
| "loss": 0.5097068786621094, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.24495773147839978, | |
| "grad_norm": 0.5537528395652771, | |
| "learning_rate": 3.977017937219731e-05, | |
| "loss": 0.5421949863433838, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.25028289955401717, | |
| "grad_norm": 0.32208332419395447, | |
| "learning_rate": 3.948991031390135e-05, | |
| "loss": 0.4985233783721924, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.25560806762963456, | |
| "grad_norm": 0.381181538105011, | |
| "learning_rate": 3.920964125560538e-05, | |
| "loss": 0.4739542007446289, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.26093323570525195, | |
| "grad_norm": 0.39554715156555176, | |
| "learning_rate": 3.8929372197309424e-05, | |
| "loss": 0.5237335681915283, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.26625840378086935, | |
| "grad_norm": 0.710545539855957, | |
| "learning_rate": 3.864910313901345e-05, | |
| "loss": 0.5354659080505371, | |
| "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": 1.1165404548635136e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |