| { | |
| "best_metric": 6.910342693328857, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.022583559168925023, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00045167118337850043, | |
| "grad_norm": 0.09511399269104004, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9411, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00045167118337850043, | |
| "eval_loss": 6.941762447357178, | |
| "eval_runtime": 4.1373, | |
| "eval_samples_per_second": 901.316, | |
| "eval_steps_per_second": 112.876, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009033423667570009, | |
| "grad_norm": 0.12681150436401367, | |
| "learning_rate": 0.0002, | |
| "loss": 6.9449, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013550135501355014, | |
| "grad_norm": 0.14625313878059387, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.9428, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018066847335140017, | |
| "grad_norm": 0.16340851783752441, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.9417, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002258355916892502, | |
| "grad_norm": 0.18675823509693146, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.9435, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0027100271002710027, | |
| "grad_norm": 0.16288436949253082, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 6.9424, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031616982836495033, | |
| "grad_norm": 0.19281183183193207, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 6.9353, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0036133694670280035, | |
| "grad_norm": 0.18037211894989014, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 6.9329, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0040650406504065045, | |
| "grad_norm": 0.18146973848342896, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 6.9382, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004516711833785004, | |
| "grad_norm": 0.2021256536245346, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 6.9314, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004968383017163505, | |
| "grad_norm": 0.20851069688796997, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 6.9346, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005420054200542005, | |
| "grad_norm": 0.20332486927509308, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 6.9377, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005871725383920506, | |
| "grad_norm": 0.11624668538570404, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 6.9365, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006323396567299007, | |
| "grad_norm": 0.13349321484565735, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.9301, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006775067750677507, | |
| "grad_norm": 0.1457970142364502, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 6.9293, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007226738934056007, | |
| "grad_norm": 0.1603357046842575, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 6.9314, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0076784101174345075, | |
| "grad_norm": 0.16457444429397583, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 6.9303, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008130081300813009, | |
| "grad_norm": 0.20100098848342896, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.9251, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008581752484191508, | |
| "grad_norm": 0.18849341571331024, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 6.9223, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009033423667570008, | |
| "grad_norm": 0.18996189534664154, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 6.9237, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009485094850948509, | |
| "grad_norm": 0.1919945478439331, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 6.9267, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00993676603432701, | |
| "grad_norm": 0.2134779840707779, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.9228, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01038843721770551, | |
| "grad_norm": 0.22595034539699554, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 6.9165, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01084010840108401, | |
| "grad_norm": 0.22315850853919983, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 6.9146, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011291779584462511, | |
| "grad_norm": 0.2357320338487625, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 6.9185, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011291779584462511, | |
| "eval_loss": 6.917991638183594, | |
| "eval_runtime": 4.0902, | |
| "eval_samples_per_second": 911.681, | |
| "eval_steps_per_second": 114.174, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011743450767841012, | |
| "grad_norm": 0.12024138867855072, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9329, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012195121951219513, | |
| "grad_norm": 0.12785819172859192, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 6.9298, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012646793134598013, | |
| "grad_norm": 0.14583264291286469, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 6.9229, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013098464317976514, | |
| "grad_norm": 0.17286351323127747, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 6.9189, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.013550135501355014, | |
| "grad_norm": 0.18918299674987793, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 6.9196, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014001806684733513, | |
| "grad_norm": 0.19743739068508148, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 6.9115, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.014453477868112014, | |
| "grad_norm": 0.20110255479812622, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 6.9122, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014905149051490514, | |
| "grad_norm": 0.19309815764427185, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 6.9141, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.015356820234869015, | |
| "grad_norm": 0.2259165495634079, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.9052, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.015808491418247517, | |
| "grad_norm": 0.2182929962873459, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 6.9042, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016260162601626018, | |
| "grad_norm": 0.23973923921585083, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 6.9081, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.016711833785004515, | |
| "grad_norm": 0.21056023240089417, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 6.9138, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.017163504968383016, | |
| "grad_norm": 0.14639106392860413, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 6.9281, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.017615176151761516, | |
| "grad_norm": 0.12287917733192444, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 6.9262, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018066847335140017, | |
| "grad_norm": 0.1542358100414276, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.9188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": 0.18276679515838623, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 6.915, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.018970189701897018, | |
| "grad_norm": 0.19573663175106049, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.9107, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01942186088527552, | |
| "grad_norm": 0.1964210867881775, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 6.9139, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01987353206865402, | |
| "grad_norm": 0.21382571756839752, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 6.9072, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02032520325203252, | |
| "grad_norm": 0.21687394380569458, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 6.9014, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02077687443541102, | |
| "grad_norm": 0.2191643863916397, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 6.9125, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02122854561878952, | |
| "grad_norm": 0.21285398304462433, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 6.9083, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02168021680216802, | |
| "grad_norm": 0.20628215372562408, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 6.9121, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.022131887985546522, | |
| "grad_norm": 0.21727484464645386, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 6.9097, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.022583559168925023, | |
| "grad_norm": 0.2488403469324112, | |
| "learning_rate": 0.0, | |
| "loss": 6.9046, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022583559168925023, | |
| "eval_loss": 6.910342693328857, | |
| "eval_runtime": 4.1189, | |
| "eval_samples_per_second": 905.333, | |
| "eval_steps_per_second": 113.379, | |
| "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": 2360158470144.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |