| { | |
| "best_metric": 1.3619989156723022, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.05821738371077604, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011643476742155208, | |
| "eval_loss": 1.8852250576019287, | |
| "eval_runtime": 341.8452, | |
| "eval_samples_per_second": 10.581, | |
| "eval_steps_per_second": 2.647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011643476742155207, | |
| "grad_norm": 1.4650214910507202, | |
| "learning_rate": 4.2600000000000005e-05, | |
| "loss": 1.5138, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023286953484310414, | |
| "grad_norm": 1.229679822921753, | |
| "learning_rate": 8.520000000000001e-05, | |
| "loss": 1.5258, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003493043022646562, | |
| "grad_norm": 1.2403314113616943, | |
| "learning_rate": 0.0001278, | |
| "loss": 1.4264, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004657390696862083, | |
| "grad_norm": 2.8764142990112305, | |
| "learning_rate": 0.00017040000000000002, | |
| "loss": 1.5789, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0058217383710776035, | |
| "grad_norm": 6.179461479187012, | |
| "learning_rate": 0.000213, | |
| "loss": 1.8489, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0058217383710776035, | |
| "eval_loss": 1.5706759691238403, | |
| "eval_runtime": 341.865, | |
| "eval_samples_per_second": 10.58, | |
| "eval_steps_per_second": 2.647, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006986086045293124, | |
| "grad_norm": 1.383204698562622, | |
| "learning_rate": 0.00021274057135267128, | |
| "loss": 1.424, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.008150433719508646, | |
| "grad_norm": 1.1531784534454346, | |
| "learning_rate": 0.00021196354932097723, | |
| "loss": 1.4689, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.009314781393724166, | |
| "grad_norm": 1.6687439680099487, | |
| "learning_rate": 0.0002106727194781503, | |
| "loss": 1.5816, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.010479129067939687, | |
| "grad_norm": 2.272064447402954, | |
| "learning_rate": 0.00020887437061743096, | |
| "loss": 1.4666, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.011643476742155207, | |
| "grad_norm": 7.06040620803833, | |
| "learning_rate": 0.00020657726411369925, | |
| "loss": 1.9486, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.011643476742155207, | |
| "eval_loss": 1.6276721954345703, | |
| "eval_runtime": 342.2738, | |
| "eval_samples_per_second": 10.568, | |
| "eval_steps_per_second": 2.644, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.012807824416370728, | |
| "grad_norm": 1.1146867275238037, | |
| "learning_rate": 0.000203792591238937, | |
| "loss": 1.3489, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.013972172090586248, | |
| "grad_norm": 1.032999038696289, | |
| "learning_rate": 0.0002005339186394757, | |
| "loss": 1.4225, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01513651976480177, | |
| "grad_norm": 1.6861324310302734, | |
| "learning_rate": 0.00019681712224065936, | |
| "loss": 1.435, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01630086743901729, | |
| "grad_norm": 2.106426239013672, | |
| "learning_rate": 0.0001926603099009319, | |
| "loss": 1.4387, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01746521511323281, | |
| "grad_norm": 5.015030860900879, | |
| "learning_rate": 0.00018808373319217114, | |
| "loss": 1.8128, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01746521511323281, | |
| "eval_loss": 1.5825364589691162, | |
| "eval_runtime": 342.2063, | |
| "eval_samples_per_second": 10.57, | |
| "eval_steps_per_second": 2.645, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01862956278744833, | |
| "grad_norm": 1.2216379642486572, | |
| "learning_rate": 0.00018310968873606635, | |
| "loss": 1.3587, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.019793910461663854, | |
| "grad_norm": 1.0753562450408936, | |
| "learning_rate": 0.0001777624095772184, | |
| "loss": 1.4036, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.020958258135879374, | |
| "grad_norm": 1.2683613300323486, | |
| "learning_rate": 0.0001720679471221826, | |
| "loss": 1.3207, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.022122605810094894, | |
| "grad_norm": 2.264540195465088, | |
| "learning_rate": 0.00016605404421963453, | |
| "loss": 1.4909, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.023286953484310414, | |
| "grad_norm": 6.5059123039245605, | |
| "learning_rate": 0.00015975, | |
| "loss": 1.5003, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.023286953484310414, | |
| "eval_loss": 1.5297727584838867, | |
| "eval_runtime": 341.8739, | |
| "eval_samples_per_second": 10.58, | |
| "eval_steps_per_second": 2.647, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.024451301158525937, | |
| "grad_norm": 1.0322542190551758, | |
| "learning_rate": 0.00015318652713303674, | |
| "loss": 1.265, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.025615648832741457, | |
| "grad_norm": 1.1514649391174316, | |
| "learning_rate": 0.00014639560219879464, | |
| "loss": 1.4101, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.026779996506956977, | |
| "grad_norm": 1.5495177507400513, | |
| "learning_rate": 0.0001394103099009319, | |
| "loss": 1.3707, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.027944344181172497, | |
| "grad_norm": 1.668436050415039, | |
| "learning_rate": 0.0001322646818813646, | |
| "loss": 1.6041, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.02910869185538802, | |
| "grad_norm": 6.893202304840088, | |
| "learning_rate": 0.0001249935309215281, | |
| "loss": 1.6849, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.02910869185538802, | |
| "eval_loss": 1.5037157535552979, | |
| "eval_runtime": 341.9268, | |
| "eval_samples_per_second": 10.578, | |
| "eval_steps_per_second": 2.647, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.03027303952960354, | |
| "grad_norm": 0.9550952315330505, | |
| "learning_rate": 0.0001176322813380051, | |
| "loss": 1.3782, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.03143738720381906, | |
| "grad_norm": 1.26908540725708, | |
| "learning_rate": 0.00011021679639881638, | |
| "loss": 1.386, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.03260173487803458, | |
| "grad_norm": 1.2255021333694458, | |
| "learning_rate": 0.00010278320360118368, | |
| "loss": 1.422, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.0337660825522501, | |
| "grad_norm": 1.647191047668457, | |
| "learning_rate": 9.536771866199493e-05, | |
| "loss": 1.4888, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.03493043022646562, | |
| "grad_norm": 3.9979913234710693, | |
| "learning_rate": 8.800646907847192e-05, | |
| "loss": 1.5099, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03493043022646562, | |
| "eval_loss": 1.43271803855896, | |
| "eval_runtime": 341.7607, | |
| "eval_samples_per_second": 10.583, | |
| "eval_steps_per_second": 2.648, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03609477790068114, | |
| "grad_norm": 0.9881057143211365, | |
| "learning_rate": 8.07353181186354e-05, | |
| "loss": 1.2903, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.03725912557489666, | |
| "grad_norm": 0.9449703097343445, | |
| "learning_rate": 7.35896900990681e-05, | |
| "loss": 1.4165, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.03842347324911218, | |
| "grad_norm": 1.3746768236160278, | |
| "learning_rate": 6.660439780120536e-05, | |
| "loss": 1.2839, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.03958782092332771, | |
| "grad_norm": 2.276339530944824, | |
| "learning_rate": 5.981347286696324e-05, | |
| "loss": 1.4299, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.04075216859754323, | |
| "grad_norm": 5.587036609649658, | |
| "learning_rate": 5.325000000000002e-05, | |
| "loss": 1.509, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04075216859754323, | |
| "eval_loss": 1.4137463569641113, | |
| "eval_runtime": 341.4095, | |
| "eval_samples_per_second": 10.594, | |
| "eval_steps_per_second": 2.651, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04191651627175875, | |
| "grad_norm": 0.9047014713287354, | |
| "learning_rate": 4.6945955780365475e-05, | |
| "loss": 1.2127, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.04308086394597427, | |
| "grad_norm": 1.1610921621322632, | |
| "learning_rate": 4.0932052877817393e-05, | |
| "loss": 1.4233, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.04424521162018979, | |
| "grad_norm": 1.44522225856781, | |
| "learning_rate": 3.523759042278163e-05, | |
| "loss": 1.374, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.04540955929440531, | |
| "grad_norm": 2.4249207973480225, | |
| "learning_rate": 2.989031126393367e-05, | |
| "loss": 1.4016, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.04657390696862083, | |
| "grad_norm": 5.2425971031188965, | |
| "learning_rate": 2.4916266807828855e-05, | |
| "loss": 1.5056, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04657390696862083, | |
| "eval_loss": 1.386236548423767, | |
| "eval_runtime": 341.385, | |
| "eval_samples_per_second": 10.595, | |
| "eval_steps_per_second": 2.651, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.047738254642836354, | |
| "grad_norm": 0.9999291896820068, | |
| "learning_rate": 2.033969009906811e-05, | |
| "loss": 1.3411, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.048902602317051874, | |
| "grad_norm": 1.680612325668335, | |
| "learning_rate": 1.6182877759340637e-05, | |
| "loss": 1.4091, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.050066949991267394, | |
| "grad_norm": 1.304457664489746, | |
| "learning_rate": 1.2466081360524275e-05, | |
| "loss": 1.3237, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.051231297665482914, | |
| "grad_norm": 2.0620386600494385, | |
| "learning_rate": 9.207408761062996e-06, | |
| "loss": 1.354, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.052395645339698434, | |
| "grad_norm": 6.1971516609191895, | |
| "learning_rate": 6.422735886300764e-06, | |
| "loss": 1.529, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.052395645339698434, | |
| "eval_loss": 1.3790680170059204, | |
| "eval_runtime": 341.5826, | |
| "eval_samples_per_second": 10.589, | |
| "eval_steps_per_second": 2.649, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.053559993013913954, | |
| "grad_norm": 0.9184896945953369, | |
| "learning_rate": 4.125629382569038e-06, | |
| "loss": 1.2853, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.05472434068812947, | |
| "grad_norm": 0.8102919459342957, | |
| "learning_rate": 2.327280521849694e-06, | |
| "loss": 1.3286, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.05588868836234499, | |
| "grad_norm": 1.2703608274459839, | |
| "learning_rate": 1.0364506790227565e-06, | |
| "loss": 1.3894, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.05705303603656052, | |
| "grad_norm": 2.265528678894043, | |
| "learning_rate": 2.5942864732872295e-07, | |
| "loss": 1.4614, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.05821738371077604, | |
| "grad_norm": 6.215338230133057, | |
| "learning_rate": 0.0, | |
| "loss": 1.4716, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05821738371077604, | |
| "eval_loss": 1.3619989156723022, | |
| "eval_runtime": 342.0703, | |
| "eval_samples_per_second": 10.574, | |
| "eval_steps_per_second": 2.646, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 1.3727480894875238e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |