| { | |
| "best_metric": 1.0833667516708374, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.32663726931242854, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006532745386248571, | |
| "eval_loss": 1.8997453451156616, | |
| "eval_runtime": 135.0082, | |
| "eval_samples_per_second": 19.095, | |
| "eval_steps_per_second": 4.777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006532745386248571, | |
| "grad_norm": 0.5372188687324524, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0612, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013065490772497142, | |
| "grad_norm": 0.3328971266746521, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 1.022, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019598236158745713, | |
| "grad_norm": 0.5935003161430359, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 1.0128, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.026130981544994283, | |
| "grad_norm": 2.405089855194092, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 1.2233, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03266372693124286, | |
| "grad_norm": 3.8762905597686768, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 1.6253, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03266372693124286, | |
| "eval_loss": 1.367977261543274, | |
| "eval_runtime": 137.0715, | |
| "eval_samples_per_second": 18.808, | |
| "eval_steps_per_second": 4.706, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.039196472317491425, | |
| "grad_norm": 0.32745811343193054, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 0.9681, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04572921770374, | |
| "grad_norm": 0.3707106113433838, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 0.9395, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05226196308998857, | |
| "grad_norm": 0.5433753728866577, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 1.0418, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05879470847623714, | |
| "grad_norm": 0.9471728205680847, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 1.1623, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06532745386248572, | |
| "grad_norm": 2.322746753692627, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 1.533, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06532745386248572, | |
| "eval_loss": 1.3632649183273315, | |
| "eval_runtime": 136.6492, | |
| "eval_samples_per_second": 18.866, | |
| "eval_steps_per_second": 4.72, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07186019924873428, | |
| "grad_norm": 0.3458673059940338, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 0.9667, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07839294463498285, | |
| "grad_norm": 0.34533071517944336, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 0.9634, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08492569002123142, | |
| "grad_norm": 0.5500729084014893, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 1.0725, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09145843540748, | |
| "grad_norm": 0.853624701499939, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 1.152, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09799118079372857, | |
| "grad_norm": 2.3200571537017822, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 1.5809, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09799118079372857, | |
| "eval_loss": 1.2978923320770264, | |
| "eval_runtime": 136.7406, | |
| "eval_samples_per_second": 18.853, | |
| "eval_steps_per_second": 4.717, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10452392617997713, | |
| "grad_norm": 0.3230119049549103, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 0.9422, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1110566715662257, | |
| "grad_norm": 0.34993496537208557, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 0.9937, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11758941695247428, | |
| "grad_norm": 0.6289933323860168, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 1.042, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12412216233872285, | |
| "grad_norm": 1.0999337434768677, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 1.1156, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13065490772497143, | |
| "grad_norm": 2.4530375003814697, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 1.503, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13065490772497143, | |
| "eval_loss": 1.2213399410247803, | |
| "eval_runtime": 136.9165, | |
| "eval_samples_per_second": 18.829, | |
| "eval_steps_per_second": 4.711, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13718765311122, | |
| "grad_norm": 0.23753122985363007, | |
| "learning_rate": 0.00014845508703326504, | |
| "loss": 0.9201, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14372039849746857, | |
| "grad_norm": 0.32499635219573975, | |
| "learning_rate": 0.00014373073204588556, | |
| "loss": 0.9755, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15025314388371713, | |
| "grad_norm": 0.38442739844322205, | |
| "learning_rate": 0.00013888241754733208, | |
| "loss": 1.0136, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.1567858892699657, | |
| "grad_norm": 0.8352793455123901, | |
| "learning_rate": 0.00013392388661180303, | |
| "loss": 1.1551, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.16331863465621427, | |
| "grad_norm": 2.5753586292266846, | |
| "learning_rate": 0.0001288691947339621, | |
| "loss": 1.5156, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16331863465621427, | |
| "eval_loss": 1.155815839767456, | |
| "eval_runtime": 137.0554, | |
| "eval_samples_per_second": 18.81, | |
| "eval_steps_per_second": 4.706, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16985138004246284, | |
| "grad_norm": 0.2267913520336151, | |
| "learning_rate": 0.0001237326699871115, | |
| "loss": 0.8876, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.1763841254287114, | |
| "grad_norm": 0.3093341886997223, | |
| "learning_rate": 0.00011852887240871145, | |
| "loss": 0.9403, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.18291687081496, | |
| "grad_norm": 0.43315809965133667, | |
| "learning_rate": 0.00011327255272837221, | |
| "loss": 0.9982, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.18944961620120856, | |
| "grad_norm": 0.8610518574714661, | |
| "learning_rate": 0.00010797861055530831, | |
| "loss": 1.1578, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.19598236158745713, | |
| "grad_norm": 3.0702617168426514, | |
| "learning_rate": 0.00010266205214377748, | |
| "loss": 1.3948, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19598236158745713, | |
| "eval_loss": 1.1323291063308716, | |
| "eval_runtime": 136.8684, | |
| "eval_samples_per_second": 18.836, | |
| "eval_steps_per_second": 4.713, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2025151069737057, | |
| "grad_norm": 0.35798534750938416, | |
| "learning_rate": 9.733794785622253e-05, | |
| "loss": 0.8783, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.20904785235995427, | |
| "grad_norm": 0.31939324736595154, | |
| "learning_rate": 9.202138944469168e-05, | |
| "loss": 0.9702, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.21558059774620283, | |
| "grad_norm": 0.5139957666397095, | |
| "learning_rate": 8.672744727162781e-05, | |
| "loss": 1.0535, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.2221133431324514, | |
| "grad_norm": 0.8899235725402832, | |
| "learning_rate": 8.147112759128859e-05, | |
| "loss": 1.1356, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2286460885187, | |
| "grad_norm": 2.6317663192749023, | |
| "learning_rate": 7.626733001288851e-05, | |
| "loss": 1.5253, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2286460885187, | |
| "eval_loss": 1.107937216758728, | |
| "eval_runtime": 136.976, | |
| "eval_samples_per_second": 18.821, | |
| "eval_steps_per_second": 4.709, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.23517883390494856, | |
| "grad_norm": 0.21436120569705963, | |
| "learning_rate": 7.113080526603792e-05, | |
| "loss": 0.8752, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.24171157929119713, | |
| "grad_norm": 0.33155834674835205, | |
| "learning_rate": 6.607611338819697e-05, | |
| "loss": 0.9239, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2482443246774457, | |
| "grad_norm": 0.44394493103027344, | |
| "learning_rate": 6.111758245266794e-05, | |
| "loss": 0.9837, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.25477707006369427, | |
| "grad_norm": 0.7826946377754211, | |
| "learning_rate": 5.626926795411447e-05, | |
| "loss": 1.1915, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.26130981544994286, | |
| "grad_norm": 2.0713536739349365, | |
| "learning_rate": 5.1544912966734994e-05, | |
| "loss": 1.431, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26130981544994286, | |
| "eval_loss": 1.0921169519424438, | |
| "eval_runtime": 136.7603, | |
| "eval_samples_per_second": 18.85, | |
| "eval_steps_per_second": 4.716, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2678425608361914, | |
| "grad_norm": 0.2013624608516693, | |
| "learning_rate": 4.695790918802576e-05, | |
| "loss": 0.898, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.27437530622244, | |
| "grad_norm": 0.35071200132369995, | |
| "learning_rate": 4.252125897855932e-05, | |
| "loss": 0.9476, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.28090805160868854, | |
| "grad_norm": 0.5039893388748169, | |
| "learning_rate": 3.824753850538082e-05, | |
| "loss": 1.0456, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.28744079699493713, | |
| "grad_norm": 0.9260233640670776, | |
| "learning_rate": 3.414886209349615e-05, | |
| "loss": 1.1276, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.29397354238118567, | |
| "grad_norm": 3.32053279876709, | |
| "learning_rate": 3.0236847886501542e-05, | |
| "loss": 1.501, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.29397354238118567, | |
| "eval_loss": 1.085567831993103, | |
| "eval_runtime": 136.7334, | |
| "eval_samples_per_second": 18.854, | |
| "eval_steps_per_second": 4.717, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.30050628776743427, | |
| "grad_norm": 0.19558390974998474, | |
| "learning_rate": 2.6522584913693294e-05, | |
| "loss": 0.89, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.30703903315368286, | |
| "grad_norm": 0.3003573715686798, | |
| "learning_rate": 2.301660165700936e-05, | |
| "loss": 0.9225, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.3135717785399314, | |
| "grad_norm": 0.584018886089325, | |
| "learning_rate": 1.9728836206903656e-05, | |
| "loss": 1.0287, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.32010452392618, | |
| "grad_norm": 0.8156113624572754, | |
| "learning_rate": 1.6668608091748495e-05, | |
| "loss": 1.0906, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.32663726931242854, | |
| "grad_norm": 2.664822816848755, | |
| "learning_rate": 1.3844591860619383e-05, | |
| "loss": 1.5452, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32663726931242854, | |
| "eval_loss": 1.0833667516708374, | |
| "eval_runtime": 136.7852, | |
| "eval_samples_per_second": 18.847, | |
| "eval_steps_per_second": 4.715, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.356406596473979e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |