SFT_Checkpoints / Qwen2.5-Math-7B-multibacktrack-wstep-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": 2.8050291538238525, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 6.1587, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04501969611705121, | |
| "grad_norm": 1.1963684558868408, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 5.506, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06752954417557681, | |
| "grad_norm": 0.5479600429534912, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 4.7216, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09003939223410241, | |
| "grad_norm": 0.39808419346809387, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 4.3317, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11254924029262803, | |
| "grad_norm": 0.3332847058773041, | |
| "learning_rate": 9.87468671679198e-06, | |
| "loss": 4.1643, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13505908835115363, | |
| "grad_norm": 0.37553367018699646, | |
| "learning_rate": 9.62406015037594e-06, | |
| "loss": 4.2239, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15756893640967923, | |
| "grad_norm": 0.34793761372566223, | |
| "learning_rate": 9.3734335839599e-06, | |
| "loss": 4.0662, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18007878446820483, | |
| "grad_norm": 0.3539280593395233, | |
| "learning_rate": 9.12280701754386e-06, | |
| "loss": 4.1014, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20258863252673046, | |
| "grad_norm": 0.31421107053756714, | |
| "learning_rate": 8.87218045112782e-06, | |
| "loss": 3.9875, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22509848058525606, | |
| "grad_norm": 0.3437129259109497, | |
| "learning_rate": 8.62155388471178e-06, | |
| "loss": 3.956, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24760832864378166, | |
| "grad_norm": 0.34449219703674316, | |
| "learning_rate": 8.370927318295739e-06, | |
| "loss": 4.1064, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27011817670230726, | |
| "grad_norm": 0.3443593978881836, | |
| "learning_rate": 8.1203007518797e-06, | |
| "loss": 3.964, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2926280247608329, | |
| "grad_norm": 0.3369867503643036, | |
| "learning_rate": 7.86967418546366e-06, | |
| "loss": 3.9857, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.31513787281935846, | |
| "grad_norm": 0.37080493569374084, | |
| "learning_rate": 7.61904761904762e-06, | |
| "loss": 3.961, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3376477208778841, | |
| "grad_norm": 0.2911035418510437, | |
| "learning_rate": 7.368421052631579e-06, | |
| "loss": 3.8308, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.36015756893640966, | |
| "grad_norm": 0.29406118392944336, | |
| "learning_rate": 7.117794486215539e-06, | |
| "loss": 3.911, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3826674169949353, | |
| "grad_norm": 0.3039765954017639, | |
| "learning_rate": 6.867167919799499e-06, | |
| "loss": 3.8607, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4051772650534609, | |
| "grad_norm": 0.31193187832832336, | |
| "learning_rate": 6.616541353383459e-06, | |
| "loss": 3.9159, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4276871131119865, | |
| "grad_norm": 0.30840519070625305, | |
| "learning_rate": 6.365914786967419e-06, | |
| "loss": 3.8885, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4501969611705121, | |
| "grad_norm": 0.32841718196868896, | |
| "learning_rate": 6.115288220551378e-06, | |
| "loss": 3.8233, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4727068092290377, | |
| "grad_norm": 0.2887263596057892, | |
| "learning_rate": 5.864661654135339e-06, | |
| "loss": 3.879, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4952166572875633, | |
| "grad_norm": 0.3095759451389313, | |
| "learning_rate": 5.6140350877192985e-06, | |
| "loss": 3.823, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5177265053460889, | |
| "grad_norm": 0.3127283453941345, | |
| "learning_rate": 5.363408521303258e-06, | |
| "loss": 3.8775, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5402363534046145, | |
| "grad_norm": 0.31057149171829224, | |
| "learning_rate": 5.112781954887218e-06, | |
| "loss": 3.7333, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5627462014631401, | |
| "grad_norm": 0.3335554897785187, | |
| "learning_rate": 4.862155388471178e-06, | |
| "loss": 3.906, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5852560495216658, | |
| "grad_norm": 0.2978381812572479, | |
| "learning_rate": 4.611528822055138e-06, | |
| "loss": 3.8683, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6077658975801913, | |
| "grad_norm": 0.29987016320228577, | |
| "learning_rate": 4.360902255639098e-06, | |
| "loss": 3.8687, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6302757456387169, | |
| "grad_norm": 0.274650514125824, | |
| "learning_rate": 4.110275689223058e-06, | |
| "loss": 3.6737, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6527855936972425, | |
| "grad_norm": 0.2877696454524994, | |
| "learning_rate": 3.859649122807018e-06, | |
| "loss": 3.8675, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6752954417557682, | |
| "grad_norm": 0.34041789174079895, | |
| "learning_rate": 3.6090225563909775e-06, | |
| "loss": 3.8597, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6978052898142938, | |
| "grad_norm": 0.2784375548362732, | |
| "learning_rate": 3.3583959899749375e-06, | |
| "loss": 3.7454, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7203151378728193, | |
| "grad_norm": 0.2802869379520416, | |
| "learning_rate": 3.107769423558897e-06, | |
| "loss": 3.6879, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7428249859313449, | |
| "grad_norm": 0.3532256782054901, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 3.7785, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7653348339898706, | |
| "grad_norm": 0.2827741205692291, | |
| "learning_rate": 2.606516290726817e-06, | |
| "loss": 3.6453, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7878446820483962, | |
| "grad_norm": 0.30722615122795105, | |
| "learning_rate": 2.355889724310777e-06, | |
| "loss": 3.6902, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8103545301069218, | |
| "grad_norm": 0.29311564564704895, | |
| "learning_rate": 2.105263157894737e-06, | |
| "loss": 3.7355, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8328643781654473, | |
| "grad_norm": 0.2665780484676361, | |
| "learning_rate": 1.8546365914786967e-06, | |
| "loss": 3.7245, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.855374226223973, | |
| "grad_norm": 0.2625872790813446, | |
| "learning_rate": 1.6040100250626568e-06, | |
| "loss": 3.6712, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8778840742824986, | |
| "grad_norm": 0.30255696177482605, | |
| "learning_rate": 1.3533834586466167e-06, | |
| "loss": 3.6844, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9003939223410242, | |
| "grad_norm": 0.29376691579818726, | |
| "learning_rate": 1.1027568922305765e-06, | |
| "loss": 3.665, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9229037703995498, | |
| "grad_norm": 0.28853243589401245, | |
| "learning_rate": 8.521303258145364e-07, | |
| "loss": 3.6584, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9454136184580754, | |
| "grad_norm": 0.32992106676101685, | |
| "learning_rate": 6.015037593984962e-07, | |
| "loss": 3.7337, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.967923466516601, | |
| "grad_norm": 0.3192669749259949, | |
| "learning_rate": 3.5087719298245616e-07, | |
| "loss": 3.591, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9904333145751266, | |
| "grad_norm": 0.30559441447257996, | |
| "learning_rate": 1.0025062656641605e-07, | |
| "loss": 3.7753, | |
| "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": 2.61753997427422e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |