| { | |
| "best_metric": 0.58182692527771, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7428040854224698, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014856081708449397, | |
| "grad_norm": 2.610515594482422, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1361, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014856081708449397, | |
| "eval_loss": 5.050648212432861, | |
| "eval_runtime": 5.1786, | |
| "eval_samples_per_second": 87.668, | |
| "eval_steps_per_second": 11.007, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029712163416898793, | |
| "grad_norm": 3.7614471912384033, | |
| "learning_rate": 0.0001, | |
| "loss": 3.057, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04456824512534819, | |
| "grad_norm": 4.077634334564209, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.2764, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.059424326833797586, | |
| "grad_norm": 3.6998331546783447, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.0714, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07428040854224698, | |
| "grad_norm": 4.662728309631348, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.7839, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08913649025069638, | |
| "grad_norm": 4.841126918792725, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.5833, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10399257195914577, | |
| "grad_norm": 5.116450786590576, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.4072, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11884865366759517, | |
| "grad_norm": 4.954044342041016, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2774, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13370473537604458, | |
| "grad_norm": 4.885868072509766, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.0489, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14856081708449395, | |
| "grad_norm": 6.445369243621826, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.9678, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16341689879294335, | |
| "grad_norm": 8.372828483581543, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.7259, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17827298050139276, | |
| "grad_norm": 9.731806755065918, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.5738, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19312906220984216, | |
| "grad_norm": 16.889236450195312, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1633, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20798514391829154, | |
| "grad_norm": 17.37698745727539, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1063, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22284122562674094, | |
| "grad_norm": 6.022202014923096, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9184, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23769730733519034, | |
| "grad_norm": 5.323773384094238, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8956, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2525533890436397, | |
| "grad_norm": 5.486806869506836, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8577, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.26740947075208915, | |
| "grad_norm": 4.066508769989014, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7928, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2822655524605385, | |
| "grad_norm": 3.2595717906951904, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7804, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2971216341689879, | |
| "grad_norm": 4.657059669494629, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7327, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.31197771587743733, | |
| "grad_norm": 3.3269941806793213, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6436, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3268337975858867, | |
| "grad_norm": 3.9602112770080566, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7062, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.34168987929433614, | |
| "grad_norm": 2.979060173034668, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6314, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3565459610027855, | |
| "grad_norm": 6.694536209106445, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6207, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3714020427112349, | |
| "grad_norm": 7.613925457000732, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7685, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3714020427112349, | |
| "eval_loss": 1.1770575046539307, | |
| "eval_runtime": 5.1605, | |
| "eval_samples_per_second": 87.976, | |
| "eval_steps_per_second": 11.045, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3862581244196843, | |
| "grad_norm": 36.5875129699707, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5001, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4011142061281337, | |
| "grad_norm": 34.303001403808594, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4433, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4159702878365831, | |
| "grad_norm": 23.18646240234375, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1508, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4308263695450325, | |
| "grad_norm": 11.81425952911377, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8306, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4456824512534819, | |
| "grad_norm": 2.6169583797454834, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7217, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4605385329619313, | |
| "grad_norm": 3.431042194366455, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6407, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4753946146703807, | |
| "grad_norm": 4.28667688369751, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6873, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.49025069637883006, | |
| "grad_norm": 4.567568302154541, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7423, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5051067780872794, | |
| "grad_norm": 4.059289932250977, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6076, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5199628597957289, | |
| "grad_norm": 3.825510263442993, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6326, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5348189415041783, | |
| "grad_norm": 3.840282917022705, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6146, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5496750232126276, | |
| "grad_norm": 3.1612565517425537, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.592, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.564531104921077, | |
| "grad_norm": 7.4375152587890625, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6791, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5793871866295265, | |
| "grad_norm": 9.302700996398926, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.7181, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5942432683379758, | |
| "grad_norm": 10.623868942260742, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7565, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6090993500464252, | |
| "grad_norm": 9.322834014892578, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7648, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6239554317548747, | |
| "grad_norm": 8.413629531860352, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7066, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6388115134633241, | |
| "grad_norm": 8.376091957092285, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6616, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6536675951717734, | |
| "grad_norm": 5.510131359100342, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6197, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6685236768802229, | |
| "grad_norm": 3.85404109954834, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6553, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6833797585886723, | |
| "grad_norm": 3.293433904647827, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5575, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6982358402971216, | |
| "grad_norm": 2.279066324234009, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5872, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.713091922005571, | |
| "grad_norm": 1.610314965248108, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5384, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7279480037140205, | |
| "grad_norm": 2.1705985069274902, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5126, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7428040854224698, | |
| "grad_norm": 7.541657447814941, | |
| "learning_rate": 0.0, | |
| "loss": 0.6703, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7428040854224698, | |
| "eval_loss": 0.58182692527771, | |
| "eval_runtime": 5.1498, | |
| "eval_samples_per_second": 88.16, | |
| "eval_steps_per_second": 11.068, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0598674582837658e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |