| { | |
| "best_metric": 0.5525282621383667, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.29314767314034446, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005862953462806889, | |
| "grad_norm": 13.67885971069336, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5079, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005862953462806889, | |
| "eval_loss": 0.7135663628578186, | |
| "eval_runtime": 59.3467, | |
| "eval_samples_per_second": 19.378, | |
| "eval_steps_per_second": 2.426, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011725906925613778, | |
| "grad_norm": 14.640575408935547, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5379, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01758886038842067, | |
| "grad_norm": 7.553555488586426, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.5086, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.023451813851227556, | |
| "grad_norm": 7.898181438446045, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.5337, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.029314767314034446, | |
| "grad_norm": 6.885729789733887, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.5526, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03517772077684134, | |
| "grad_norm": 5.375410079956055, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6089, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.041040674239648224, | |
| "grad_norm": 4.5977559089660645, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.6613, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04690362770245511, | |
| "grad_norm": 4.0113959312438965, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6841, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.052766581165262, | |
| "grad_norm": 3.998295783996582, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6555, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05862953462806889, | |
| "grad_norm": 3.942673683166504, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.728, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06449248809087578, | |
| "grad_norm": 4.036313056945801, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7464, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07035544155368267, | |
| "grad_norm": 4.104882717132568, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7691, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07621839501648955, | |
| "grad_norm": 5.341107368469238, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6555, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08208134847929645, | |
| "grad_norm": 3.198674201965332, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4423, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08794430194210333, | |
| "grad_norm": 2.88740611076355, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4604, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09380725540491022, | |
| "grad_norm": 2.836839199066162, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4841, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09967020886771712, | |
| "grad_norm": 2.8243424892425537, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4718, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.105533162330524, | |
| "grad_norm": 2.985089063644409, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5811, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11139611579333089, | |
| "grad_norm": 3.213775873184204, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6096, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11725906925613779, | |
| "grad_norm": 3.2207791805267334, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6265, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12312202271894467, | |
| "grad_norm": 3.049495220184326, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6506, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12898497618175156, | |
| "grad_norm": 3.3075506687164307, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7016, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13484792964455844, | |
| "grad_norm": 3.368518352508545, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6828, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14071088310736535, | |
| "grad_norm": 3.672518014907837, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6999, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14657383657017223, | |
| "grad_norm": 5.255999565124512, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.867, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14657383657017223, | |
| "eval_loss": 0.5644305348396301, | |
| "eval_runtime": 59.2517, | |
| "eval_samples_per_second": 19.409, | |
| "eval_steps_per_second": 2.43, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1524367900329791, | |
| "grad_norm": 2.8404314517974854, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3591, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.158299743495786, | |
| "grad_norm": 2.647034168243408, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4144, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1641626969585929, | |
| "grad_norm": 2.488347053527832, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4298, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.17002565042139978, | |
| "grad_norm": 2.4996895790100098, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4348, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.17588860388420666, | |
| "grad_norm": 2.5636889934539795, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4851, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18175155734701356, | |
| "grad_norm": 2.8773529529571533, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5328, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.18761451080982045, | |
| "grad_norm": 2.9976096153259277, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5937, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.19347746427262733, | |
| "grad_norm": 3.0503299236297607, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6089, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19934041773543423, | |
| "grad_norm": 3.1507649421691895, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.615, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2052033711982411, | |
| "grad_norm": 3.176201343536377, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.663, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.211066324661048, | |
| "grad_norm": 3.4488625526428223, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6642, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2169292781238549, | |
| "grad_norm": 3.689284563064575, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7436, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.22279223158666178, | |
| "grad_norm": 4.115244388580322, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6477, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.22865518504946866, | |
| "grad_norm": 2.5662221908569336, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4257, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.23451813851227557, | |
| "grad_norm": 2.5049357414245605, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3878, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24038109197508245, | |
| "grad_norm": 2.503816843032837, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4266, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.24624404543788933, | |
| "grad_norm": 2.4777987003326416, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4366, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2521069989006962, | |
| "grad_norm": 2.5198934078216553, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5022, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2579699523635031, | |
| "grad_norm": 2.7259795665740967, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6336, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.26383290582631, | |
| "grad_norm": 2.7449092864990234, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6044, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2696958592891169, | |
| "grad_norm": 3.0662050247192383, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6305, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2755588127519238, | |
| "grad_norm": 3.1306512355804443, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6554, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2814217662147307, | |
| "grad_norm": 3.2178750038146973, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6754, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.28728471967753755, | |
| "grad_norm": 3.459937334060669, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6943, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.29314767314034446, | |
| "grad_norm": 4.89279842376709, | |
| "learning_rate": 0.0, | |
| "loss": 0.8438, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.29314767314034446, | |
| "eval_loss": 0.5525282621383667, | |
| "eval_runtime": 59.3684, | |
| "eval_samples_per_second": 19.371, | |
| "eval_steps_per_second": 2.426, | |
| "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": 8.911383602428641e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |