| { | |
| "best_metric": 1.01275634765625, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03391267486222976, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006782534972445952, | |
| "grad_norm": 14.803535461425781, | |
| "learning_rate": 5e-05, | |
| "loss": 13.4569, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006782534972445952, | |
| "eval_loss": 14.130653381347656, | |
| "eval_runtime": 669.6095, | |
| "eval_samples_per_second": 14.834, | |
| "eval_steps_per_second": 1.855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013565069944891904, | |
| "grad_norm": 14.392424583435059, | |
| "learning_rate": 0.0001, | |
| "loss": 12.527, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020347604917337857, | |
| "grad_norm": 15.631271362304688, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.1606, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027130139889783808, | |
| "grad_norm": 18.245677947998047, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.7625, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003391267486222976, | |
| "grad_norm": 15.866408348083496, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.0025, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004069520983467571, | |
| "grad_norm": 14.519718170166016, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.3537, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004747774480712166, | |
| "grad_norm": 8.656271934509277, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.8476, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0054260279779567615, | |
| "grad_norm": 10.097105026245117, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2157, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006104281475201356, | |
| "grad_norm": 6.234673023223877, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6922, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006782534972445952, | |
| "grad_norm": 7.798948764801025, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.6576, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007460788469690547, | |
| "grad_norm": 6.963011741638184, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.2868, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008139041966935143, | |
| "grad_norm": 4.4558939933776855, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1949, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008817295464179737, | |
| "grad_norm": 5.854774475097656, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.6873, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009495548961424332, | |
| "grad_norm": 8.775835990905762, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3765, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010173802458668928, | |
| "grad_norm": 5.595000267028809, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.1991, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010852055955913523, | |
| "grad_norm": 5.6219072341918945, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7277, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011530309453158118, | |
| "grad_norm": 4.934707164764404, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.5532, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012208562950402712, | |
| "grad_norm": 5.352980136871338, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5094, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012886816447647309, | |
| "grad_norm": 4.896200180053711, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.2864, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013565069944891903, | |
| "grad_norm": 3.2947072982788086, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0972, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014243323442136498, | |
| "grad_norm": 3.437858819961548, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9828, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014921576939381094, | |
| "grad_norm": 3.5444886684417725, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.9269, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015599830436625689, | |
| "grad_norm": 3.3804261684417725, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8762, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.016278083933870285, | |
| "grad_norm": 2.846210241317749, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5165, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01695633743111488, | |
| "grad_norm": 3.1749045848846436, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4188, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01695633743111488, | |
| "eval_loss": 1.1890568733215332, | |
| "eval_runtime": 669.6578, | |
| "eval_samples_per_second": 14.833, | |
| "eval_steps_per_second": 1.855, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017634590928359475, | |
| "grad_norm": 6.018980026245117, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1423, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01831284442560407, | |
| "grad_norm": 4.701257705688477, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.8068, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018991097922848664, | |
| "grad_norm": 3.3165788650512695, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.4779, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01966935142009326, | |
| "grad_norm": 3.4257826805114746, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.242, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.020347604917337857, | |
| "grad_norm": 4.026438236236572, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2729, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02102585841458245, | |
| "grad_norm": 3.5555081367492676, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.3512, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.021704111911827046, | |
| "grad_norm": 3.55861496925354, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1249, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02238236540907164, | |
| "grad_norm": 3.6784932613372803, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8738, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.023060618906316235, | |
| "grad_norm": 2.483609914779663, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6447, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02373887240356083, | |
| "grad_norm": 2.8854124546051025, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8838, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.024417125900805425, | |
| "grad_norm": 2.638995885848999, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5454, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02509537939805002, | |
| "grad_norm": 2.463036298751831, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6331, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.025773632895294617, | |
| "grad_norm": 2.2768940925598145, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1571, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02645188639253921, | |
| "grad_norm": 2.529445171356201, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5317, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.027130139889783807, | |
| "grad_norm": 2.4773786067962646, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.463, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.027808393387028403, | |
| "grad_norm": 2.9906861782073975, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4364, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.028486646884272996, | |
| "grad_norm": 2.9122350215911865, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.2862, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.029164900381517592, | |
| "grad_norm": 2.940488338470459, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0787, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02984315387876219, | |
| "grad_norm": 2.749434471130371, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0091, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03052140737600678, | |
| "grad_norm": 2.78676176071167, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8398, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.031199660873251378, | |
| "grad_norm": 2.7963085174560547, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.7188, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.031877914370495974, | |
| "grad_norm": 3.1949076652526855, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6096, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03255616786774057, | |
| "grad_norm": 2.1205198764801025, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6106, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03323442136498516, | |
| "grad_norm": 2.295241355895996, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4533, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03391267486222976, | |
| "grad_norm": 3.1803605556488037, | |
| "learning_rate": 0.0, | |
| "loss": 0.5063, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03391267486222976, | |
| "eval_loss": 1.01275634765625, | |
| "eval_runtime": 669.4553, | |
| "eval_samples_per_second": 14.837, | |
| "eval_steps_per_second": 1.855, | |
| "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": 5.968186696531968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |