| { | |
| "best_metric": 5.886590957641602, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.16597510373443983, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0033195020746887966, | |
| "grad_norm": 11.868147850036621, | |
| "learning_rate": 5e-05, | |
| "loss": 10.5687, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033195020746887966, | |
| "eval_loss": 11.261401176452637, | |
| "eval_runtime": 22.7907, | |
| "eval_samples_per_second": 89.072, | |
| "eval_steps_per_second": 11.145, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006639004149377593, | |
| "grad_norm": 13.577654838562012, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6673, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00995850622406639, | |
| "grad_norm": 11.040910720825195, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.7356, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013278008298755186, | |
| "grad_norm": 9.7022066116333, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.444, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 7.680191993713379, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.0375, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01991701244813278, | |
| "grad_norm": 4.803664207458496, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 9.645, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023236514522821577, | |
| "grad_norm": 5.210556983947754, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 9.3292, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026556016597510373, | |
| "grad_norm": 2.9458279609680176, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.13, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02987551867219917, | |
| "grad_norm": 3.136021614074707, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 8.9405, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 2.557469606399536, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 8.8243, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.036514522821576766, | |
| "grad_norm": 2.2064290046691895, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 8.7747, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03983402489626556, | |
| "grad_norm": 2.9643099308013916, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 8.5938, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.043153526970954356, | |
| "grad_norm": 2.518488883972168, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 7.9596, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.046473029045643155, | |
| "grad_norm": 2.471862554550171, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.6079, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04979253112033195, | |
| "grad_norm": 2.4168319702148438, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 7.4703, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.053112033195020746, | |
| "grad_norm": 2.3712270259857178, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 7.3073, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.056431535269709544, | |
| "grad_norm": 2.3532795906066895, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 7.2052, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05975103734439834, | |
| "grad_norm": 2.2195680141448975, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 7.0532, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06307053941908713, | |
| "grad_norm": 2.1516218185424805, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 7.0546, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06639004149377593, | |
| "grad_norm": 2.065981149673462, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.9599, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06970954356846473, | |
| "grad_norm": 2.0872349739074707, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.8226, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07302904564315353, | |
| "grad_norm": 1.99671471118927, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.6954, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07634854771784233, | |
| "grad_norm": 1.9122333526611328, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.7382, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07966804979253111, | |
| "grad_norm": 2.0224294662475586, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 6.752, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08298755186721991, | |
| "grad_norm": 2.323184013366699, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.8404, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08298755186721991, | |
| "eval_loss": 6.408796787261963, | |
| "eval_runtime": 22.7829, | |
| "eval_samples_per_second": 89.102, | |
| "eval_steps_per_second": 11.149, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08630705394190871, | |
| "grad_norm": 6.193380355834961, | |
| "learning_rate": 5e-05, | |
| "loss": 6.3512, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08962655601659751, | |
| "grad_norm": 6.526251792907715, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 6.3189, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09294605809128631, | |
| "grad_norm": 5.399415493011475, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 6.2825, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09626556016597511, | |
| "grad_norm": 3.2363271713256836, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 6.1822, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0995850622406639, | |
| "grad_norm": 1.8278745412826538, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 6.0853, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10290456431535269, | |
| "grad_norm": 1.6847590208053589, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 6.0437, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10622406639004149, | |
| "grad_norm": 2.0661935806274414, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.9981, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10954356846473029, | |
| "grad_norm": 2.292564868927002, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 6.1408, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11286307053941909, | |
| "grad_norm": 2.2145509719848633, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.1147, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11618257261410789, | |
| "grad_norm": 2.2277729511260986, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 6.1476, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11950207468879669, | |
| "grad_norm": 2.4843192100524902, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 6.2465, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12282157676348547, | |
| "grad_norm": 2.5991244316101074, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 6.3102, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12614107883817427, | |
| "grad_norm": 1.514162540435791, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.0682, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12946058091286308, | |
| "grad_norm": 1.709502935409546, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 5.7858, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13278008298755187, | |
| "grad_norm": 1.5972634553909302, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 5.7559, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13609958506224065, | |
| "grad_norm": 1.3997278213500977, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 5.8057, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13941908713692946, | |
| "grad_norm": 1.292576789855957, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 5.8228, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14273858921161825, | |
| "grad_norm": 1.3085607290267944, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 5.8759, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14605809128630706, | |
| "grad_norm": 1.286241888999939, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.8659, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14937759336099585, | |
| "grad_norm": 1.2643060684204102, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 5.8861, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15269709543568466, | |
| "grad_norm": 1.270158052444458, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 5.8817, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15601659751037344, | |
| "grad_norm": 1.4481507539749146, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 5.9544, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15933609958506223, | |
| "grad_norm": 1.435001254081726, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 5.9207, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16265560165975104, | |
| "grad_norm": 1.6827739477157593, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 6.085, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16597510373443983, | |
| "grad_norm": 2.8101089000701904, | |
| "learning_rate": 0.0, | |
| "loss": 6.3224, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16597510373443983, | |
| "eval_loss": 5.886590957641602, | |
| "eval_runtime": 22.7757, | |
| "eval_samples_per_second": 89.13, | |
| "eval_steps_per_second": 11.152, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |