SFT_Checkpoints / Qwen2.5-Math-7B-multibacktrack-sft-n2-still-numina-math-ckpt444 /trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9994372537985369, | |
| "eval_steps": 500, | |
| "global_step": 444, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022509848058525603, | |
| "grad_norm": 4.327241897583008, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 8.5214, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04501969611705121, | |
| "grad_norm": 1.7264961004257202, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 7.5546, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06752954417557681, | |
| "grad_norm": 1.0628855228424072, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 5.7526, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09003939223410241, | |
| "grad_norm": 0.6295533776283264, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 4.9589, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11254924029262803, | |
| "grad_norm": 0.5138620138168335, | |
| "learning_rate": 9.87468671679198e-06, | |
| "loss": 4.6339, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13505908835115363, | |
| "grad_norm": 0.502289891242981, | |
| "learning_rate": 9.62406015037594e-06, | |
| "loss": 4.6855, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15756893640967923, | |
| "grad_norm": 0.3467671871185303, | |
| "learning_rate": 9.3734335839599e-06, | |
| "loss": 4.4222, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18007878446820483, | |
| "grad_norm": 0.35326918959617615, | |
| "learning_rate": 9.12280701754386e-06, | |
| "loss": 4.4481, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20258863252673046, | |
| "grad_norm": 0.3369162976741791, | |
| "learning_rate": 8.87218045112782e-06, | |
| "loss": 4.3478, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22509848058525606, | |
| "grad_norm": 0.3802469074726105, | |
| "learning_rate": 8.62155388471178e-06, | |
| "loss": 4.425, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24760832864378166, | |
| "grad_norm": 0.3173699975013733, | |
| "learning_rate": 8.370927318295739e-06, | |
| "loss": 4.3924, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27011817670230726, | |
| "grad_norm": 0.3183175325393677, | |
| "learning_rate": 8.1203007518797e-06, | |
| "loss": 4.2312, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2926280247608329, | |
| "grad_norm": 0.30415669083595276, | |
| "learning_rate": 7.86967418546366e-06, | |
| "loss": 4.364, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.31513787281935846, | |
| "grad_norm": 0.3200981020927429, | |
| "learning_rate": 7.61904761904762e-06, | |
| "loss": 4.2182, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3376477208778841, | |
| "grad_norm": 0.28655463457107544, | |
| "learning_rate": 7.368421052631579e-06, | |
| "loss": 4.2388, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.36015756893640966, | |
| "grad_norm": 0.35627660155296326, | |
| "learning_rate": 7.117794486215539e-06, | |
| "loss": 4.2385, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3826674169949353, | |
| "grad_norm": 0.3535982072353363, | |
| "learning_rate": 6.867167919799499e-06, | |
| "loss": 4.256, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4051772650534609, | |
| "grad_norm": 0.29762333631515503, | |
| "learning_rate": 6.616541353383459e-06, | |
| "loss": 4.1519, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4276871131119865, | |
| "grad_norm": 0.29701927304267883, | |
| "learning_rate": 6.365914786967419e-06, | |
| "loss": 4.2534, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4501969611705121, | |
| "grad_norm": 0.3369089961051941, | |
| "learning_rate": 6.115288220551378e-06, | |
| "loss": 4.2689, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4727068092290377, | |
| "grad_norm": 0.28114861249923706, | |
| "learning_rate": 5.864661654135339e-06, | |
| "loss": 4.1793, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4952166572875633, | |
| "grad_norm": 0.29363805055618286, | |
| "learning_rate": 5.6140350877192985e-06, | |
| "loss": 4.0821, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5177265053460889, | |
| "grad_norm": 0.31713083386421204, | |
| "learning_rate": 5.363408521303258e-06, | |
| "loss": 4.1607, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5402363534046145, | |
| "grad_norm": 0.2943900227546692, | |
| "learning_rate": 5.112781954887218e-06, | |
| "loss": 4.0969, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5627462014631401, | |
| "grad_norm": 0.32129648327827454, | |
| "learning_rate": 4.862155388471178e-06, | |
| "loss": 4.2222, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5852560495216658, | |
| "grad_norm": 0.27016839385032654, | |
| "learning_rate": 4.611528822055138e-06, | |
| "loss": 4.1283, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6077658975801913, | |
| "grad_norm": 0.29647159576416016, | |
| "learning_rate": 4.360902255639098e-06, | |
| "loss": 4.0882, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6302757456387169, | |
| "grad_norm": 0.31913793087005615, | |
| "learning_rate": 4.110275689223058e-06, | |
| "loss": 4.2142, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6527855936972425, | |
| "grad_norm": 0.2767369747161865, | |
| "learning_rate": 3.859649122807018e-06, | |
| "loss": 4.1413, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6752954417557682, | |
| "grad_norm": 0.30485114455223083, | |
| "learning_rate": 3.6090225563909775e-06, | |
| "loss": 4.0782, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6978052898142938, | |
| "grad_norm": 0.26790645718574524, | |
| "learning_rate": 3.3583959899749375e-06, | |
| "loss": 4.1322, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7203151378728193, | |
| "grad_norm": 0.29677528142929077, | |
| "learning_rate": 3.107769423558897e-06, | |
| "loss": 4.0987, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7428249859313449, | |
| "grad_norm": 0.26743343472480774, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 4.0469, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7653348339898706, | |
| "grad_norm": 0.2823913097381592, | |
| "learning_rate": 2.606516290726817e-06, | |
| "loss": 3.977, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7878446820483962, | |
| "grad_norm": 0.3154824674129486, | |
| "learning_rate": 2.355889724310777e-06, | |
| "loss": 4.0915, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8103545301069218, | |
| "grad_norm": 0.27284637093544006, | |
| "learning_rate": 2.105263157894737e-06, | |
| "loss": 4.0195, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8328643781654473, | |
| "grad_norm": 0.27475491166114807, | |
| "learning_rate": 1.8546365914786967e-06, | |
| "loss": 4.0891, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.855374226223973, | |
| "grad_norm": 0.27842697501182556, | |
| "learning_rate": 1.6040100250626568e-06, | |
| "loss": 3.9718, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8778840742824986, | |
| "grad_norm": 0.28258708119392395, | |
| "learning_rate": 1.3533834586466167e-06, | |
| "loss": 4.1759, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9003939223410242, | |
| "grad_norm": 0.25824299454689026, | |
| "learning_rate": 1.1027568922305765e-06, | |
| "loss": 4.0275, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9229037703995498, | |
| "grad_norm": 0.269233375787735, | |
| "learning_rate": 8.521303258145364e-07, | |
| "loss": 3.9631, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9454136184580754, | |
| "grad_norm": 0.3044830858707428, | |
| "learning_rate": 6.015037593984962e-07, | |
| "loss": 4.1979, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.967923466516601, | |
| "grad_norm": 0.2594878673553467, | |
| "learning_rate": 3.5087719298245616e-07, | |
| "loss": 4.0824, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9904333145751266, | |
| "grad_norm": 0.26378872990608215, | |
| "learning_rate": 1.0025062656641605e-07, | |
| "loss": 3.9954, | |
| "step": 440 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 444, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.625975204144218e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |