| { | |
| "best_metric": 11.925542831420898, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01856406924397828, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003712813848795656, | |
| "grad_norm": 0.0174246858805418, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9305, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003712813848795656, | |
| "eval_loss": 11.928313255310059, | |
| "eval_runtime": 99.5027, | |
| "eval_samples_per_second": 182.357, | |
| "eval_steps_per_second": 22.803, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007425627697591312, | |
| "grad_norm": 0.020337140187621117, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9301, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011138441546386967, | |
| "grad_norm": 0.022250287234783173, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9294, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014851255395182624, | |
| "grad_norm": 0.02357928268611431, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9299, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001856406924397828, | |
| "grad_norm": 0.02496778406202793, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9297, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022276883092773934, | |
| "grad_norm": 0.027166973799467087, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9289, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025989696941569594, | |
| "grad_norm": 0.02655761130154133, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9298, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002970251079036525, | |
| "grad_norm": 0.027253923937678337, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9285, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033415324639160904, | |
| "grad_norm": 0.03001312166452408, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9281, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003712813848795656, | |
| "grad_norm": 0.030339084565639496, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9275, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004084095233675222, | |
| "grad_norm": 0.03468618169426918, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9262, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004455376618554787, | |
| "grad_norm": 0.04213392734527588, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9246, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004826658003434353, | |
| "grad_norm": 0.018453966826200485, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9292, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005197939388313919, | |
| "grad_norm": 0.01894436776638031, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9292, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005569220773193484, | |
| "grad_norm": 0.019307918846607208, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9294, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00594050215807305, | |
| "grad_norm": 0.02206205390393734, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9293, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006311783542952615, | |
| "grad_norm": 0.022904308512806892, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9285, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006683064927832181, | |
| "grad_norm": 0.025185855105519295, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9281, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007054346312711747, | |
| "grad_norm": 0.026912720873951912, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.928, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007425627697591312, | |
| "grad_norm": 0.0287943035364151, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9273, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007796909082470878, | |
| "grad_norm": 0.03132673725485802, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9265, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008168190467350444, | |
| "grad_norm": 0.03069041110575199, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9272, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008539471852230009, | |
| "grad_norm": 0.03682119399309158, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9262, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008910753237109574, | |
| "grad_norm": 0.04099636152386665, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9249, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00928203462198914, | |
| "grad_norm": 0.05958414450287819, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9219, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00928203462198914, | |
| "eval_loss": 11.926277160644531, | |
| "eval_runtime": 98.6284, | |
| "eval_samples_per_second": 183.973, | |
| "eval_steps_per_second": 23.006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009653316006868706, | |
| "grad_norm": 0.01857578009366989, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9292, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01002459739174827, | |
| "grad_norm": 0.021577468141913414, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9293, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010395878776627837, | |
| "grad_norm": 0.022688543424010277, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9284, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010767160161507403, | |
| "grad_norm": 0.029039891436696053, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.928, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011138441546386968, | |
| "grad_norm": 0.027141861617565155, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011509722931266534, | |
| "grad_norm": 0.031942471861839294, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9279, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0118810043161461, | |
| "grad_norm": 0.03531135991215706, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9274, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012252285701025665, | |
| "grad_norm": 0.031263090670108795, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9269, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01262356708590523, | |
| "grad_norm": 0.03525080159306526, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9252, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.012994848470784796, | |
| "grad_norm": 0.04339566454291344, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9251, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013366129855664361, | |
| "grad_norm": 0.043329868465662, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.9248, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013737411240543927, | |
| "grad_norm": 0.05429895594716072, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9228, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014108692625423493, | |
| "grad_norm": 0.02292412705719471, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9292, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.014479974010303058, | |
| "grad_norm": 0.026886217296123505, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.9286, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014851255395182623, | |
| "grad_norm": 0.026999138295650482, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.928, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01522253678006219, | |
| "grad_norm": 0.027867605909705162, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.9281, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.015593818164941755, | |
| "grad_norm": 0.028749389573931694, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9278, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01596509954982132, | |
| "grad_norm": 0.0331251323223114, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.927, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.016336380934700887, | |
| "grad_norm": 0.034101732075214386, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9271, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01670766231958045, | |
| "grad_norm": 0.03889305517077446, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9268, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.017078943704460017, | |
| "grad_norm": 0.0389268584549427, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9257, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017450225089339584, | |
| "grad_norm": 0.0436691977083683, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.9256, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.017821506474219147, | |
| "grad_norm": 0.04428064823150635, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9243, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018192787859098714, | |
| "grad_norm": 0.05177050083875656, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9234, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01856406924397828, | |
| "grad_norm": 0.07301251590251923, | |
| "learning_rate": 0.0, | |
| "loss": 11.9203, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01856406924397828, | |
| "eval_loss": 11.925542831420898, | |
| "eval_runtime": 108.4513, | |
| "eval_samples_per_second": 167.31, | |
| "eval_steps_per_second": 20.922, | |
| "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": 1120029769728.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |