| { | |
| "best_metric": 0.09621890634298325, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.18497109826589594, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003699421965317919, | |
| "grad_norm": 0.7521932125091553, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003699421965317919, | |
| "eval_loss": 0.6948966979980469, | |
| "eval_runtime": 47.9004, | |
| "eval_samples_per_second": 38.016, | |
| "eval_steps_per_second": 4.76, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007398843930635838, | |
| "grad_norm": 0.8199026584625244, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5468, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011098265895953757, | |
| "grad_norm": 0.7568219304084778, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.5254, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014797687861271676, | |
| "grad_norm": 0.4971456527709961, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.3753, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018497109826589597, | |
| "grad_norm": 0.5538675785064697, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.2861, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022196531791907514, | |
| "grad_norm": 0.5713285803794861, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.1932, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025895953757225434, | |
| "grad_norm": 0.30795109272003174, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.1421, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02959537572254335, | |
| "grad_norm": 0.11786455661058426, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1209, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03329479768786127, | |
| "grad_norm": 0.33727341890335083, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1218, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03699421965317919, | |
| "grad_norm": 0.22202248871326447, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1133, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04069364161849711, | |
| "grad_norm": 0.25751954317092896, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1073, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04439306358381503, | |
| "grad_norm": 0.12727031111717224, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1145, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.048092485549132945, | |
| "grad_norm": 0.39962953329086304, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1181, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05179190751445087, | |
| "grad_norm": 0.1137956827878952, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1176, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.055491329479768786, | |
| "grad_norm": 0.1370266228914261, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.117, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0591907514450867, | |
| "grad_norm": 0.350655734539032, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1198, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06289017341040462, | |
| "grad_norm": 0.07253460586071014, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1087, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06658959537572254, | |
| "grad_norm": 0.1392214596271515, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1102, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07028901734104047, | |
| "grad_norm": 0.32512056827545166, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1094, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07398843930635839, | |
| "grad_norm": 0.07746732980012894, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.103, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0776878612716763, | |
| "grad_norm": 0.2803148925304413, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1043, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08138728323699422, | |
| "grad_norm": 0.16201826930046082, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1048, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08508670520231214, | |
| "grad_norm": 0.13390931487083435, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1073, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08878612716763006, | |
| "grad_norm": 0.20256085693836212, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1013, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09248554913294797, | |
| "grad_norm": 0.09516842663288116, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0917, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09248554913294797, | |
| "eval_loss": 0.10299577564001083, | |
| "eval_runtime": 48.0534, | |
| "eval_samples_per_second": 37.895, | |
| "eval_steps_per_second": 4.745, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09618497109826589, | |
| "grad_norm": 0.2436722069978714, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1035, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09988439306358382, | |
| "grad_norm": 0.16461080312728882, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.1078, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10358381502890174, | |
| "grad_norm": 0.14472082257270813, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1051, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10728323699421966, | |
| "grad_norm": 0.17404970526695251, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1087, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11098265895953757, | |
| "grad_norm": 0.12008468806743622, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1049, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11468208092485549, | |
| "grad_norm": 0.13445191085338593, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0999, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1183815028901734, | |
| "grad_norm": 0.08790981024503708, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0981, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12208092485549132, | |
| "grad_norm": 0.08825737237930298, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0995, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12578034682080924, | |
| "grad_norm": 0.06886397302150726, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0978, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12947976878612716, | |
| "grad_norm": 0.15950433909893036, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0991, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13317919075144508, | |
| "grad_norm": 0.15729287266731262, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0908, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.136878612716763, | |
| "grad_norm": 0.09872325509786606, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0954, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14057803468208094, | |
| "grad_norm": 0.14306682348251343, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0959, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14427745664739886, | |
| "grad_norm": 0.06087346002459526, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.103, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14797687861271677, | |
| "grad_norm": 0.04816189408302307, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1025, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1516763005780347, | |
| "grad_norm": 0.06453908234834671, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1042, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1553757225433526, | |
| "grad_norm": 0.05799945443868637, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1007, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15907514450867052, | |
| "grad_norm": 0.08636831492185593, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0977, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16277456647398844, | |
| "grad_norm": 0.08446965366601944, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1025, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.16647398843930636, | |
| "grad_norm": 0.06017603725194931, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0972, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.17017341040462428, | |
| "grad_norm": 0.15928272902965546, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0973, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1738728323699422, | |
| "grad_norm": 0.13271377980709076, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0946, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1775722543352601, | |
| "grad_norm": 0.1516481637954712, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0962, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.18127167630057803, | |
| "grad_norm": 0.19494952261447906, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0885, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18497109826589594, | |
| "grad_norm": 0.149687722325325, | |
| "learning_rate": 0.0, | |
| "loss": 0.0891, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18497109826589594, | |
| "eval_loss": 0.09621890634298325, | |
| "eval_runtime": 48.0237, | |
| "eval_samples_per_second": 37.919, | |
| "eval_steps_per_second": 4.748, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |