Instructions to use socius/Llama-Centaur-8B-LoRA-r4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use socius/Llama-Centaur-8B-LoRA-r4 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.1-8B") model = PeftModel.from_pretrained(base_model, "socius/Llama-Centaur-8B-LoRA-r4") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download checkpoint-500/trainer_state.json from socius/Llama-Centaur-8B-LoRA-r4: direct link, hf CLI and curl.
- Browser
- Download file 10.1 kB
-
https://huggingface.co/socius/Llama-Centaur-8B-LoRA-r4/resolve/main/checkpoint-500/trainer_state.json
- Command line
-
hf download hf://socius/Llama-Centaur-8B-LoRA-r4/checkpoint-500/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/socius/Llama-Centaur-8B-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": 0.12182320654392242, | |
| "learning_rate": 4.787234042553191e-06, | |
| "loss": 0.6409461498260498, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010650336151234773, | |
| "grad_norm": 0.1363009512424469, | |
| "learning_rate": 1.0106382978723404e-05, | |
| "loss": 0.6779457092285156, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01597550422685216, | |
| "grad_norm": 0.16375352442264557, | |
| "learning_rate": 1.5425531914893617e-05, | |
| "loss": 0.5765519142150879, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021300672302469546, | |
| "grad_norm": 0.1207907497882843, | |
| "learning_rate": 2.074468085106383e-05, | |
| "loss": 0.6171613216400147, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026625840378086935, | |
| "grad_norm": 0.17915089428424835, | |
| "learning_rate": 2.6063829787234046e-05, | |
| "loss": 0.6188801288604736, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03195100845370432, | |
| "grad_norm": 0.2441256046295166, | |
| "learning_rate": 3.1382978723404254e-05, | |
| "loss": 0.6470537662506104, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.037276176529321706, | |
| "grad_norm": 0.2620764672756195, | |
| "learning_rate": 3.670212765957447e-05, | |
| "loss": 0.5195772647857666, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04260134460493909, | |
| "grad_norm": 0.2821812033653259, | |
| "learning_rate": 4.2021276595744684e-05, | |
| "loss": 0.6430625438690185, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04792651268055648, | |
| "grad_norm": 0.36121875047683716, | |
| "learning_rate": 4.734042553191489e-05, | |
| "loss": 0.525498342514038, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05325168075617387, | |
| "grad_norm": 0.2926883399486542, | |
| "learning_rate": 4.985986547085202e-05, | |
| "loss": 0.5632081985473633, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.058576848831791255, | |
| "grad_norm": 0.3214546740055084, | |
| "learning_rate": 4.9579596412556055e-05, | |
| "loss": 0.5223509311676026, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06390201690740864, | |
| "grad_norm": 0.24347242712974548, | |
| "learning_rate": 4.9299327354260097e-05, | |
| "loss": 0.5506986618041992, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06922718498302603, | |
| "grad_norm": 0.39196303486824036, | |
| "learning_rate": 4.9019058295964125e-05, | |
| "loss": 0.5343639373779296, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07455235305864341, | |
| "grad_norm": 0.2370986044406891, | |
| "learning_rate": 4.8738789237668166e-05, | |
| "loss": 0.634202241897583, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0798775211342608, | |
| "grad_norm": 0.5534964799880981, | |
| "learning_rate": 4.84585201793722e-05, | |
| "loss": 0.5778422355651855, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08520268920987818, | |
| "grad_norm": 0.30655860900878906, | |
| "learning_rate": 4.8178251121076236e-05, | |
| "loss": 0.5519596576690674, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09052785728549557, | |
| "grad_norm": 0.4148649573326111, | |
| "learning_rate": 4.789798206278027e-05, | |
| "loss": 0.5354521751403809, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09585302536111295, | |
| "grad_norm": 0.46059107780456543, | |
| "learning_rate": 4.7617713004484306e-05, | |
| "loss": 0.5110114574432373, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.10117819343673035, | |
| "grad_norm": 0.29660817980766296, | |
| "learning_rate": 4.733744394618834e-05, | |
| "loss": 0.5167609214782715, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.10650336151234774, | |
| "grad_norm": 0.3021899461746216, | |
| "learning_rate": 4.705717488789238e-05, | |
| "loss": 0.46111321449279785, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11182852958796512, | |
| "grad_norm": 0.47710350155830383, | |
| "learning_rate": 4.677690582959641e-05, | |
| "loss": 0.5681551456451416, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11715369766358251, | |
| "grad_norm": 0.5306881666183472, | |
| "learning_rate": 4.649663677130045e-05, | |
| "loss": 0.46531901359558103, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.12247886573919989, | |
| "grad_norm": 0.513879120349884, | |
| "learning_rate": 4.621636771300449e-05, | |
| "loss": 0.4722289085388184, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.12780403381481728, | |
| "grad_norm": 0.3301677405834198, | |
| "learning_rate": 4.593609865470852e-05, | |
| "loss": 0.5384090900421142, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.13312920189043467, | |
| "grad_norm": 0.45560935139656067, | |
| "learning_rate": 4.565582959641256e-05, | |
| "loss": 0.4672722339630127, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13845436996605207, | |
| "grad_norm": 0.31638070940971375, | |
| "learning_rate": 4.537556053811659e-05, | |
| "loss": 0.4908642292022705, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.14377953804166943, | |
| "grad_norm": 0.32199767231941223, | |
| "learning_rate": 4.509529147982063e-05, | |
| "loss": 0.5462312221527099, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.14910470611728682, | |
| "grad_norm": 0.2937774062156677, | |
| "learning_rate": 4.481502242152467e-05, | |
| "loss": 0.47396349906921387, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.15442987419290422, | |
| "grad_norm": 0.2907174229621887, | |
| "learning_rate": 4.4534753363228704e-05, | |
| "loss": 0.46338305473327634, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.1597550422685216, | |
| "grad_norm": 0.4924933910369873, | |
| "learning_rate": 4.425448430493274e-05, | |
| "loss": 0.542780065536499, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.165080210344139, | |
| "grad_norm": 0.6004148125648499, | |
| "learning_rate": 4.3974215246636774e-05, | |
| "loss": 0.5385100841522217, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.17040537841975636, | |
| "grad_norm": 0.48270919919013977, | |
| "learning_rate": 4.369394618834081e-05, | |
| "loss": 0.4900692939758301, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.17573054649537376, | |
| "grad_norm": 0.7385998368263245, | |
| "learning_rate": 4.3413677130044844e-05, | |
| "loss": 0.5876289367675781, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.18105571457099115, | |
| "grad_norm": 0.3292222321033478, | |
| "learning_rate": 4.313340807174888e-05, | |
| "loss": 0.5060083866119385, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.18638088264660854, | |
| "grad_norm": 0.2551015019416809, | |
| "learning_rate": 4.2853139013452914e-05, | |
| "loss": 0.4813774585723877, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1917060507222259, | |
| "grad_norm": 0.3968099355697632, | |
| "learning_rate": 4.257286995515695e-05, | |
| "loss": 0.477051830291748, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.1970312187978433, | |
| "grad_norm": 0.5009409189224243, | |
| "learning_rate": 4.229260089686099e-05, | |
| "loss": 0.5575748920440674, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2023563868734607, | |
| "grad_norm": 0.32792729139328003, | |
| "learning_rate": 4.201233183856502e-05, | |
| "loss": 0.4213892459869385, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.20768155494907808, | |
| "grad_norm": 0.3064369559288025, | |
| "learning_rate": 4.173206278026906e-05, | |
| "loss": 0.4275490760803223, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.21300672302469548, | |
| "grad_norm": 0.3220454752445221, | |
| "learning_rate": 4.1451793721973096e-05, | |
| "loss": 0.48259787559509276, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21833189110031284, | |
| "grad_norm": 0.5888713002204895, | |
| "learning_rate": 4.117152466367713e-05, | |
| "loss": 0.578326940536499, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.22365705917593023, | |
| "grad_norm": 0.6319938898086548, | |
| "learning_rate": 4.0891255605381166e-05, | |
| "loss": 0.4845900535583496, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.22898222725154763, | |
| "grad_norm": 0.29064664244651794, | |
| "learning_rate": 4.061098654708521e-05, | |
| "loss": 0.46815996170043944, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.23430739532716502, | |
| "grad_norm": 0.3988511562347412, | |
| "learning_rate": 4.0330717488789236e-05, | |
| "loss": 0.46213793754577637, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.2396325634027824, | |
| "grad_norm": 0.3999287188053131, | |
| "learning_rate": 4.005044843049328e-05, | |
| "loss": 0.47902555465698243, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.24495773147839978, | |
| "grad_norm": 0.4859839081764221, | |
| "learning_rate": 3.977017937219731e-05, | |
| "loss": 0.515401554107666, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.25028289955401717, | |
| "grad_norm": 0.3084466755390167, | |
| "learning_rate": 3.948991031390135e-05, | |
| "loss": 0.4710197448730469, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.25560806762963456, | |
| "grad_norm": 0.28355690836906433, | |
| "learning_rate": 3.920964125560538e-05, | |
| "loss": 0.4545428276062012, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.26093323570525195, | |
| "grad_norm": 0.3173733651638031, | |
| "learning_rate": 3.8929372197309424e-05, | |
| "loss": 0.5014235019683838, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.26625840378086935, | |
| "grad_norm": 0.5729868412017822, | |
| "learning_rate": 3.864910313901345e-05, | |
| "loss": 0.508852195739746, | |
| "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": 2.9641622724399514e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |