| { | |
| "best_metric": 11.926499366760254, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11728485559302156, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002345697111860431, | |
| "grad_norm": 0.023263728246092796, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9223, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002345697111860431, | |
| "eval_loss": 11.929311752319336, | |
| "eval_runtime": 12.1067, | |
| "eval_samples_per_second": 237.223, | |
| "eval_steps_per_second": 29.653, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004691394223720862, | |
| "grad_norm": 0.023828286677598953, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9159, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007037091335581293, | |
| "grad_norm": 0.0231478288769722, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9124, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009382788447441724, | |
| "grad_norm": 0.025272436439990997, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.909, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011728485559302155, | |
| "grad_norm": 0.02534029819071293, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9057, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014074182671162587, | |
| "grad_norm": 0.02812816947698593, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9028, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016419879783023016, | |
| "grad_norm": 0.027446430176496506, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.8997, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018765576894883448, | |
| "grad_norm": 0.030333541333675385, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.896, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02111127400674388, | |
| "grad_norm": 0.0286606065928936, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.8936, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02345697111860431, | |
| "grad_norm": 0.032484058290719986, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.8902, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025802668230464742, | |
| "grad_norm": 0.028907716274261475, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.8855, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.028148365342325173, | |
| "grad_norm": 0.03208125755190849, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.8753, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030494062454185605, | |
| "grad_norm": 0.029715213924646378, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.916, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03283975956604603, | |
| "grad_norm": 0.02765621244907379, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9169, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.035185456677906464, | |
| "grad_norm": 0.02788020670413971, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9128, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.037531153789766895, | |
| "grad_norm": 0.03472643718123436, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9087, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03987685090162733, | |
| "grad_norm": 0.03742455691099167, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9057, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04222254801348776, | |
| "grad_norm": 0.038485001772642136, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9032, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04456824512534819, | |
| "grad_norm": 0.040359240025281906, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04691394223720862, | |
| "grad_norm": 0.037473585456609726, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.8976, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04925963934906905, | |
| "grad_norm": 0.04298529773950577, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.8937, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.051605336460929484, | |
| "grad_norm": 0.04474135488271713, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.891, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.053951033572789915, | |
| "grad_norm": 0.049919430166482925, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.8866, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.056296730684650347, | |
| "grad_norm": 0.0465259775519371, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.8801, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05864242779651078, | |
| "grad_norm": 0.04526961222290993, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.8617, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05864242779651078, | |
| "eval_loss": 11.927361488342285, | |
| "eval_runtime": 12.1456, | |
| "eval_samples_per_second": 236.464, | |
| "eval_steps_per_second": 29.558, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06098812490837121, | |
| "grad_norm": 0.046790074557065964, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9202, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06333382202023163, | |
| "grad_norm": 0.045101504772901535, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9141, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06567951913209207, | |
| "grad_norm": 0.0466698482632637, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9107, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0680252162439525, | |
| "grad_norm": 0.05154228210449219, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9064, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07037091335581293, | |
| "grad_norm": 0.05609067901968956, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9028, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07271661046767336, | |
| "grad_norm": 0.054825764149427414, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.8996, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07506230757953379, | |
| "grad_norm": 0.05315624177455902, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.8977, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07740800469139422, | |
| "grad_norm": 0.05658416450023651, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.8949, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07975370180325465, | |
| "grad_norm": 0.05000322312116623, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.8919, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08209939891511508, | |
| "grad_norm": 0.06540560722351074, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.8874, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08444509602697552, | |
| "grad_norm": 0.051300302147865295, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.8832, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08679079313883595, | |
| "grad_norm": 0.05268245190382004, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.8738, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08913649025069638, | |
| "grad_norm": 0.05355386808514595, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9155, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09148218736255681, | |
| "grad_norm": 0.05276748165488243, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.916, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09382788447441724, | |
| "grad_norm": 0.05582776665687561, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9113, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09617358158627767, | |
| "grad_norm": 0.06121082231402397, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.9071, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0985192786981381, | |
| "grad_norm": 0.054675329476594925, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.904, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10086497580999854, | |
| "grad_norm": 0.06488271802663803, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9007, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10321067292185897, | |
| "grad_norm": 0.0639345645904541, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.8972, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1055563700337194, | |
| "grad_norm": 0.06195634603500366, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.8954, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10790206714557983, | |
| "grad_norm": 0.06594201922416687, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.8923, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11024776425744026, | |
| "grad_norm": 0.0577872097492218, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.8897, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11259346136930069, | |
| "grad_norm": 0.057595305144786835, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.8845, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11493915848116112, | |
| "grad_norm": 0.057064544409513474, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.8792, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11728485559302156, | |
| "grad_norm": 0.05568932741880417, | |
| "learning_rate": 0.0, | |
| "loss": 11.8627, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11728485559302156, | |
| "eval_loss": 11.926499366760254, | |
| "eval_runtime": 12.1765, | |
| "eval_samples_per_second": 235.864, | |
| "eval_steps_per_second": 29.483, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |