| { | |
| "best_metric": 1.3974195718765259, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0665889795238888, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001331779590477776, | |
| "grad_norm": 1.716598391532898, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2224, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001331779590477776, | |
| "eval_loss": 2.8852221965789795, | |
| "eval_runtime": 133.4508, | |
| "eval_samples_per_second": 37.909, | |
| "eval_steps_per_second": 4.743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002663559180955552, | |
| "grad_norm": 1.9544339179992676, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3534, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003995338771433328, | |
| "grad_norm": 1.9382542371749878, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.315, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005327118361911104, | |
| "grad_norm": 1.8056589365005493, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.223, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00665889795238888, | |
| "grad_norm": 1.8618559837341309, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.094, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007990677542866656, | |
| "grad_norm": 1.720023512840271, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.9048, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009322457133344432, | |
| "grad_norm": 1.8842785358428955, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.7269, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010654236723822208, | |
| "grad_norm": 1.7412643432617188, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7371, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011986016314299984, | |
| "grad_norm": 2.0039165019989014, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6742, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01331779590477776, | |
| "grad_norm": 1.7889673709869385, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5504, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014649575495255536, | |
| "grad_norm": 1.569449782371521, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4855, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015981355085733312, | |
| "grad_norm": 1.9054864645004272, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.5665, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017313134676211088, | |
| "grad_norm": 1.3979929685592651, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.8186, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018644914266688864, | |
| "grad_norm": 0.9748731255531311, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6544, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01997669385716664, | |
| "grad_norm": 0.8066844344139099, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5756, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021308473447644416, | |
| "grad_norm": 0.7804756164550781, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.6058, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022640253038122192, | |
| "grad_norm": 0.7928308248519897, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3039, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023972032628599968, | |
| "grad_norm": 0.8666258454322815, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3077, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025303812219077744, | |
| "grad_norm": 0.960999608039856, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4093, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02663559180955552, | |
| "grad_norm": 1.0699888467788696, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.357, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027967371400033296, | |
| "grad_norm": 1.1570630073547363, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4088, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029299150990511072, | |
| "grad_norm": 1.1443278789520264, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3868, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.030630930580988848, | |
| "grad_norm": 1.2050145864486694, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.3297, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.031962710171466624, | |
| "grad_norm": 1.2424426078796387, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1877, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0332944897619444, | |
| "grad_norm": 1.9407079219818115, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.5371, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0332944897619444, | |
| "eval_loss": 1.4364030361175537, | |
| "eval_runtime": 132.66, | |
| "eval_samples_per_second": 38.135, | |
| "eval_steps_per_second": 4.772, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034626269352422176, | |
| "grad_norm": 0.7670523524284363, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6652, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03595804894289995, | |
| "grad_norm": 0.7151476740837097, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5839, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03728982853337773, | |
| "grad_norm": 0.7840404510498047, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.4314, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.038621608123855504, | |
| "grad_norm": 0.7918953895568848, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4365, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03995338771433328, | |
| "grad_norm": 0.8279181718826294, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3891, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.041285167304811056, | |
| "grad_norm": 0.8578282594680786, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2858, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04261694689528883, | |
| "grad_norm": 0.8482633829116821, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1511, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04394872648576661, | |
| "grad_norm": 0.8851420283317566, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.4296, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.045280506076244384, | |
| "grad_norm": 1.0721423625946045, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4503, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04661228566672216, | |
| "grad_norm": 1.0197111368179321, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4107, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.047944065257199936, | |
| "grad_norm": 1.1104793548583984, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.236, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04927584484767771, | |
| "grad_norm": 1.620796799659729, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.4854, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05060762443815549, | |
| "grad_norm": 0.7224025726318359, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7413, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.051939404028633264, | |
| "grad_norm": 0.6184026598930359, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5911, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05327118361911104, | |
| "grad_norm": 0.6563757658004761, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5257, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.054602963209588816, | |
| "grad_norm": 0.7842867970466614, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4908, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05593474280006659, | |
| "grad_norm": 0.6858050227165222, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3321, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05726652239054437, | |
| "grad_norm": 0.7674694061279297, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.3322, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.058598301981022144, | |
| "grad_norm": 0.7808869481086731, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2364, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05993008157149992, | |
| "grad_norm": 0.9280687570571899, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.3535, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.061261861161977696, | |
| "grad_norm": 0.8980047702789307, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2546, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06259364075245546, | |
| "grad_norm": 0.9971718192100525, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3707, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06392542034293325, | |
| "grad_norm": 1.1494028568267822, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1686, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06525719993341102, | |
| "grad_norm": 1.1565730571746826, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.2963, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0665889795238888, | |
| "grad_norm": 1.65233314037323, | |
| "learning_rate": 0.0, | |
| "loss": 1.5058, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0665889795238888, | |
| "eval_loss": 1.3974195718765259, | |
| "eval_runtime": 132.6366, | |
| "eval_samples_per_second": 38.142, | |
| "eval_steps_per_second": 4.772, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |