| { | |
| "best_metric": 4.985250949859619, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1224552273075157, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002449104546150314, | |
| "grad_norm": 7.551912784576416, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4955, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002449104546150314, | |
| "eval_loss": 10.970553398132324, | |
| "eval_runtime": 5.8875, | |
| "eval_samples_per_second": 467.258, | |
| "eval_steps_per_second": 58.428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004898209092300628, | |
| "grad_norm": 7.172514915466309, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6407, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007347313638450942, | |
| "grad_norm": 6.178919315338135, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.9127, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009796418184601256, | |
| "grad_norm": 6.14189338684082, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.0827, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012245522730751569, | |
| "grad_norm": 5.81701135635376, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 9.7007, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014694627276901883, | |
| "grad_norm": 5.90933895111084, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 9.7113, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017143731823052198, | |
| "grad_norm": 5.321878433227539, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 8.9919, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01959283636920251, | |
| "grad_norm": 5.625715255737305, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.1602, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022041940915352824, | |
| "grad_norm": 5.834358215332031, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 8.9869, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024491045461503137, | |
| "grad_norm": 5.8274455070495605, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 9.0104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02694015000765345, | |
| "grad_norm": 6.095324993133545, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 9.1706, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029389254553803767, | |
| "grad_norm": 6.588826656341553, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 9.2314, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.031838359099954076, | |
| "grad_norm": 6.078140735626221, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 8.5172, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.034287463646104396, | |
| "grad_norm": 5.4950690269470215, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.5113, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03673656819225471, | |
| "grad_norm": 5.634173393249512, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 7.5182, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03918567273840502, | |
| "grad_norm": 5.851142883300781, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 7.4475, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.041634777284555335, | |
| "grad_norm": 6.017014026641846, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 7.3161, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04408388183070565, | |
| "grad_norm": 6.267073154449463, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 7.2617, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04653298637685596, | |
| "grad_norm": 6.179825305938721, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 6.8376, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.048982090923006275, | |
| "grad_norm": 6.670197010040283, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.7105, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05143119546915659, | |
| "grad_norm": 6.976203441619873, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.5332, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0538803000153069, | |
| "grad_norm": 7.678707122802734, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.7641, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05632940456145722, | |
| "grad_norm": 8.303336143493652, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.5042, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.058778509107607534, | |
| "grad_norm": 8.899639129638672, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 6.3543, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06122761365375785, | |
| "grad_norm": 10.729676246643066, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06122761365375785, | |
| "eval_loss": 6.080567359924316, | |
| "eval_runtime": 5.7939, | |
| "eval_samples_per_second": 474.806, | |
| "eval_steps_per_second": 59.372, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06367671819990815, | |
| "grad_norm": 7.234199523925781, | |
| "learning_rate": 5e-05, | |
| "loss": 5.7224, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06612582274605847, | |
| "grad_norm": 7.271491050720215, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 5.6061, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06857492729220879, | |
| "grad_norm": 6.81791353225708, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 5.5909, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0710240318383591, | |
| "grad_norm": 7.6534423828125, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 5.388, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07347313638450942, | |
| "grad_norm": 7.172658443450928, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 5.4519, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07592224093065973, | |
| "grad_norm": 7.6117048263549805, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 5.3257, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07837134547681004, | |
| "grad_norm": 7.242852687835693, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.291, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08082045002296036, | |
| "grad_norm": 8.312119483947754, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 5.1802, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08326955456911067, | |
| "grad_norm": 7.4992523193359375, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 5.2752, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08571865911526098, | |
| "grad_norm": 6.869739532470703, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 5.1967, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0881677636614113, | |
| "grad_norm": 6.3787736892700195, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 5.2088, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09061686820756161, | |
| "grad_norm": 6.979067802429199, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 5.3134, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09306597275371192, | |
| "grad_norm": 7.202182292938232, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.3527, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09551507729986224, | |
| "grad_norm": 8.028775215148926, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 5.085, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09796418184601255, | |
| "grad_norm": 7.695888042449951, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 4.9146, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10041328639216286, | |
| "grad_norm": 7.480747699737549, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 4.853, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10286239093831318, | |
| "grad_norm": 6.339000225067139, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.8266, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10531149548446349, | |
| "grad_norm": 6.702110767364502, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 5.0874, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1077606000306138, | |
| "grad_norm": 6.588842868804932, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.7769, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11020970457676411, | |
| "grad_norm": 6.282130718231201, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 4.992, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11265880912291444, | |
| "grad_norm": 6.139161586761475, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 4.8116, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11510791366906475, | |
| "grad_norm": 6.040432453155518, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 4.8607, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11755701821521507, | |
| "grad_norm": 6.295772552490234, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 5.179, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12000612276136538, | |
| "grad_norm": 6.335700035095215, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 5.0151, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1224552273075157, | |
| "grad_norm": 7.427189826965332, | |
| "learning_rate": 0.0, | |
| "loss": 5.1183, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1224552273075157, | |
| "eval_loss": 4.985250949859619, | |
| "eval_runtime": 5.7172, | |
| "eval_samples_per_second": 481.181, | |
| "eval_steps_per_second": 60.169, | |
| "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": 3506283793612800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |