Instructions to use issdandavis/tongue-table-lora-brick2-hf-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use issdandavis/tongue-table-lora-brick2-hf-v1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("issdandavis/tongue-table-lora-brick2-hf-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0673400673400675, | |
| "eval_steps": 500, | |
| "global_step": 750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0364963503649635, | |
| "grad_norm": 0.828892171382904, | |
| "learning_rate": 1.08e-05, | |
| "loss": 0.4354942798614502, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 0.9289367198944092, | |
| "learning_rate": 2.2800000000000002e-05, | |
| "loss": 0.36432347297668455, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10948905109489052, | |
| "grad_norm": 2.0873074531555176, | |
| "learning_rate": 2.999774682924681e-05, | |
| "loss": 0.32090737819671633, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 4.841006278991699, | |
| "learning_rate": 2.9972406431448155e-05, | |
| "loss": 0.43266544342041013, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18248175182481752, | |
| "grad_norm": 2.7465760707855225, | |
| "learning_rate": 2.9918956905010563e-05, | |
| "loss": 0.5646582126617432, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21897810218978103, | |
| "grad_norm": 1.030403971672058, | |
| "learning_rate": 2.983749859583509e-05, | |
| "loss": 0.3808066129684448, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.25547445255474455, | |
| "grad_norm": 0.7817710041999817, | |
| "learning_rate": 2.9728184433385794e-05, | |
| "loss": 0.4072124481201172, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 1.3247804641723633, | |
| "learning_rate": 2.9591219643580672e-05, | |
| "loss": 0.3555629730224609, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3284671532846715, | |
| "grad_norm": 3.1126701831817627, | |
| "learning_rate": 2.9426861363501402e-05, | |
| "loss": 0.3507055759429932, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.36496350364963503, | |
| "grad_norm": 1.0930603742599487, | |
| "learning_rate": 2.9235418158645382e-05, | |
| "loss": 0.33841102123260497, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.40145985401459855, | |
| "grad_norm": 1.4056899547576904, | |
| "learning_rate": 2.9017249443626213e-05, | |
| "loss": 0.3785548210144043, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.43795620437956206, | |
| "grad_norm": 1.8448857069015503, | |
| "learning_rate": 2.8772764807410347e-05, | |
| "loss": 0.3630043029785156, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4744525547445255, | |
| "grad_norm": 0.9118333458900452, | |
| "learning_rate": 2.8502423244356567e-05, | |
| "loss": 0.3892256736755371, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5109489051094891, | |
| "grad_norm": 3.103043794631958, | |
| "learning_rate": 2.820673229250209e-05, | |
| "loss": 0.40395588874816896, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5474452554744526, | |
| "grad_norm": 1.371759057044983, | |
| "learning_rate": 2.7886247080712864e-05, | |
| "loss": 0.3903501510620117, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "grad_norm": 0.7535229325294495, | |
| "learning_rate": 2.7541569286487182e-05, | |
| "loss": 0.35717196464538575, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6204379562043796, | |
| "grad_norm": 1.2660030126571655, | |
| "learning_rate": 2.7173346006369036e-05, | |
| "loss": 0.26791996955871583, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2154882154882154, | |
| "grad_norm": 23.720056533813477, | |
| "learning_rate": 2.6260084578790863e-05, | |
| "loss": 5.0859, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2828282828282829, | |
| "grad_norm": 7.147736072540283, | |
| "learning_rate": 2.5829341409317866e-05, | |
| "loss": 3.2131, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.3501683501683501, | |
| "grad_norm": 4.732028484344482, | |
| "learning_rate": 2.5379083034663196e-05, | |
| "loss": 1.8717, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4175084175084174, | |
| "grad_norm": 2.9123284816741943, | |
| "learning_rate": 2.491012085085122e-05, | |
| "loss": 0.9048, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4848484848484849, | |
| "grad_norm": 1.7257939577102661, | |
| "learning_rate": 2.4423299959434637e-05, | |
| "loss": 0.6315, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.5521885521885523, | |
| "grad_norm": 1.5153653621673584, | |
| "learning_rate": 2.3919497644564302e-05, | |
| "loss": 0.5315, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.6195286195286194, | |
| "grad_norm": 1.7134076356887817, | |
| "learning_rate": 2.339962179206393e-05, | |
| "loss": 0.4746, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.6868686868686869, | |
| "grad_norm": 1.3939902782440186, | |
| "learning_rate": 2.2864609253358477e-05, | |
| "loss": 0.4457, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7542087542087543, | |
| "grad_norm": 1.5202797651290894, | |
| "learning_rate": 2.231542415720452e-05, | |
| "loss": 0.4148, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.8215488215488216, | |
| "grad_norm": 3.209591865539551, | |
| "learning_rate": 2.17530561722651e-05, | |
| "loss": 0.4057, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 1.0990711450576782, | |
| "learning_rate": 2.117851872365989e-05, | |
| "loss": 0.4023, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.9562289562289563, | |
| "grad_norm": 1.259845495223999, | |
| "learning_rate": 2.059284716670463e-05, | |
| "loss": 0.3876, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.026936026936027, | |
| "grad_norm": 1.3019286394119263, | |
| "learning_rate": 1.9997096921130865e-05, | |
| "loss": 0.4163, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0942760942760943, | |
| "grad_norm": 1.3461154699325562, | |
| "learning_rate": 1.9392341569148254e-05, | |
| "loss": 0.3977, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.1616161616161618, | |
| "grad_norm": 1.1439738273620605, | |
| "learning_rate": 1.877967092077688e-05, | |
| "loss": 0.3716, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.228956228956229, | |
| "grad_norm": 1.1023906469345093, | |
| "learning_rate": 1.8160189049935895e-05, | |
| "loss": 0.3774, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.2962962962962963, | |
| "grad_norm": 1.4419972896575928, | |
| "learning_rate": 1.7535012304827737e-05, | |
| "loss": 0.3775, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.3636363636363638, | |
| "grad_norm": 0.8919001221656799, | |
| "learning_rate": 1.6905267296203182e-05, | |
| "loss": 0.3826, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.430976430976431, | |
| "grad_norm": 1.0658531188964844, | |
| "learning_rate": 1.627208886713264e-05, | |
| "loss": 0.3735, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.4983164983164983, | |
| "grad_norm": 1.0677207708358765, | |
| "learning_rate": 1.5636618047942225e-05, | |
| "loss": 0.3608, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.5656565656565657, | |
| "grad_norm": 1.1946293115615845, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.3667, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.6329966329966332, | |
| "grad_norm": 0.9220478534698486, | |
| "learning_rate": 1.4363381952057779e-05, | |
| "loss": 0.3608, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.7003367003367003, | |
| "grad_norm": 1.3499350547790527, | |
| "learning_rate": 1.3727911132867368e-05, | |
| "loss": 0.3745, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.7676767676767677, | |
| "grad_norm": 1.3389482498168945, | |
| "learning_rate": 1.3094732703796819e-05, | |
| "loss": 0.3586, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.8350168350168348, | |
| "grad_norm": 1.209559679031372, | |
| "learning_rate": 1.2464987695172267e-05, | |
| "loss": 0.3448, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.9023569023569022, | |
| "grad_norm": 1.0429422855377197, | |
| "learning_rate": 1.183981095006411e-05, | |
| "loss": 0.3682, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.9696969696969697, | |
| "grad_norm": 1.270484209060669, | |
| "learning_rate": 1.1220329079223125e-05, | |
| "loss": 0.3574, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.04040404040404, | |
| "grad_norm": 1.0506254434585571, | |
| "learning_rate": 1.0607658430851745e-05, | |
| "loss": 0.3901, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.1077441077441077, | |
| "grad_norm": 0.8597121834754944, | |
| "learning_rate": 1.0002903078869137e-05, | |
| "loss": 0.3483, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.175084175084175, | |
| "grad_norm": 0.8475470542907715, | |
| "learning_rate": 9.407152833295373e-06, | |
| "loss": 0.3607, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.242424242424242, | |
| "grad_norm": 0.8766200542449951, | |
| "learning_rate": 8.821481276340111e-06, | |
| "loss": 0.3551, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.3097643097643097, | |
| "grad_norm": 1.0985888242721558, | |
| "learning_rate": 8.246943827734899e-06, | |
| "loss": 0.3562, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.377104377104377, | |
| "grad_norm": 0.8100714683532715, | |
| "learning_rate": 7.684575842795486e-06, | |
| "loss": 0.3623, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.377104377104377, | |
| "eval_loss": 0.36943843960762024, | |
| "eval_runtime": 4.1729, | |
| "eval_samples_per_second": 61.588, | |
| "eval_steps_per_second": 15.577, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.4444444444444446, | |
| "grad_norm": 1.0126490592956543, | |
| "learning_rate": 7.135390746641527e-06, | |
| "loss": 0.3508, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.5117845117845117, | |
| "grad_norm": 0.8240623474121094, | |
| "learning_rate": 6.60037820793607e-06, | |
| "loss": 0.3466, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.579124579124579, | |
| "grad_norm": 0.7924415469169617, | |
| "learning_rate": 6.080502355435702e-06, | |
| "loss": 0.3488, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.6464646464646466, | |
| "grad_norm": 0.9690365791320801, | |
| "learning_rate": 5.5767000405653645e-06, | |
| "loss": 0.3506, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.7138047138047137, | |
| "grad_norm": 0.8754220008850098, | |
| "learning_rate": 5.089879149148781e-06, | |
| "loss": 0.3442, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.781144781144781, | |
| "grad_norm": 0.8320648670196533, | |
| "learning_rate": 4.620916965336809e-06, | |
| "loss": 0.3549, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.8484848484848486, | |
| "grad_norm": 1.1898738145828247, | |
| "learning_rate": 4.170658590682134e-06, | |
| "loss": 0.3472, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.915824915824916, | |
| "grad_norm": 1.111453890800476, | |
| "learning_rate": 3.7399154212091336e-06, | |
| "loss": 0.3548, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.983164983164983, | |
| "grad_norm": 0.9030128121376038, | |
| "learning_rate": 3.329463685223411e-06, | |
| "loss": 0.3445, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.053872053872054, | |
| "grad_norm": 0.8622605204582214, | |
| "learning_rate": 2.940043044495894e-06, | |
| "loss": 0.3847, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.121212121212121, | |
| "grad_norm": 0.7712292075157166, | |
| "learning_rate": 2.572355261342369e-06, | |
| "loss": 0.3399, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.188552188552189, | |
| "grad_norm": 0.9418888092041016, | |
| "learning_rate": 2.2270629340003306e-06, | |
| "loss": 0.3389, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.255892255892256, | |
| "grad_norm": 0.6980782747268677, | |
| "learning_rate": 1.9047883025821777e-06, | |
| "loss": 0.3418, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.3232323232323235, | |
| "grad_norm": 0.7036774754524231, | |
| "learning_rate": 1.6061121277564743e-06, | |
| "loss": 0.3542, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.390572390572391, | |
| "grad_norm": 0.7862967252731323, | |
| "learning_rate": 1.331572644177963e-06, | |
| "loss": 0.351, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.457912457912458, | |
| "grad_norm": 0.9763192534446716, | |
| "learning_rate": 1.0816645905523598e-06, | |
| "loss": 0.3431, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.525252525252525, | |
| "grad_norm": 0.9646930694580078, | |
| "learning_rate": 8.568383180837369e-07, | |
| "loss": 0.3566, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.592592592592593, | |
| "grad_norm": 0.7037179470062256, | |
| "learning_rate": 6.574989789112374e-07, | |
| "loss": 0.344, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.65993265993266, | |
| "grad_norm": 1.0083799362182617, | |
| "learning_rate": 4.840057959975169e-07, | |
| "loss": 0.3488, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.7272727272727275, | |
| "grad_norm": 0.7868887186050415, | |
| "learning_rate": 3.3667141578470785e-07, | |
| "loss": 0.3442, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.794612794612795, | |
| "grad_norm": 1.0048251152038574, | |
| "learning_rate": 2.1576134478437315e-07, | |
| "loss": 0.3568, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.861952861952862, | |
| "grad_norm": 0.9245824217796326, | |
| "learning_rate": 1.214934711168475e-07, | |
| "loss": 0.347, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.929292929292929, | |
| "grad_norm": 0.9527543783187866, | |
| "learning_rate": 5.403767186210218e-08, | |
| "loss": 0.3379, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.9966329966329965, | |
| "grad_norm": 0.9715042114257812, | |
| "learning_rate": 1.3515506929778765e-08, | |
| "loss": 0.3439, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.0673400673400675, | |
| "grad_norm": 0.8542423844337463, | |
| "learning_rate": 0.0, | |
| "loss": 0.3763, | |
| "step": 750 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5364040369493760.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |