{ "best_metric": 11.755621910095215, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.025288179883252902, "eval_steps": 50, "global_step": 75, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00033717573177670536, "grad_norm": 0.020519904792308807, "learning_rate": 5e-06, "loss": 11.7663, "step": 1 }, { "epoch": 0.00033717573177670536, "eval_loss": 11.765796661376953, "eval_runtime": 90.5321, "eval_samples_per_second": 110.348, "eval_steps_per_second": 27.592, "step": 1 }, { "epoch": 0.0006743514635534107, "grad_norm": 0.02136598899960518, "learning_rate": 1e-05, "loss": 11.7656, "step": 2 }, { "epoch": 0.0010115271953301161, "grad_norm": 0.024068046361207962, "learning_rate": 1.5e-05, "loss": 11.7673, "step": 3 }, { "epoch": 0.0013487029271068215, "grad_norm": 0.02285166271030903, "learning_rate": 2e-05, "loss": 11.7653, "step": 4 }, { "epoch": 0.0016858786588835268, "grad_norm": 0.028022553771734238, "learning_rate": 2.5e-05, "loss": 11.7642, "step": 5 }, { "epoch": 0.0020230543906602323, "grad_norm": 0.019944753497838974, "learning_rate": 3e-05, "loss": 11.7667, "step": 6 }, { "epoch": 0.002360230122436938, "grad_norm": 0.019216399639844894, "learning_rate": 3.5e-05, "loss": 11.7662, "step": 7 }, { "epoch": 0.002697405854213643, "grad_norm": 0.024231871590018272, "learning_rate": 4e-05, "loss": 11.7652, "step": 8 }, { "epoch": 0.0030345815859903484, "grad_norm": 0.024706153199076653, "learning_rate": 4.5e-05, "loss": 11.7671, "step": 9 }, { "epoch": 0.0033717573177670535, "grad_norm": 0.02115534618496895, "learning_rate": 5e-05, "loss": 11.7663, "step": 10 }, { "epoch": 0.003708933049543759, "grad_norm": 0.022423913702368736, "learning_rate": 5.500000000000001e-05, "loss": 11.7643, "step": 11 }, { "epoch": 0.004046108781320465, "grad_norm": 0.025999922305345535, "learning_rate": 6e-05, "loss": 11.766, "step": 12 }, { "epoch": 0.00438328451309717, "grad_norm": 0.02133255824446678, "learning_rate": 6.500000000000001e-05, "loss": 11.7667, "step": 13 }, { "epoch": 0.004720460244873876, "grad_norm": 0.02341216616332531, "learning_rate": 7e-05, "loss": 11.7651, "step": 14 }, { "epoch": 0.00505763597665058, "grad_norm": 0.023417755961418152, "learning_rate": 7.500000000000001e-05, "loss": 11.7655, "step": 15 }, { "epoch": 0.005394811708427286, "grad_norm": 0.026899263262748718, "learning_rate": 8e-05, "loss": 11.7654, "step": 16 }, { "epoch": 0.005731987440203991, "grad_norm": 0.02089621126651764, "learning_rate": 8.5e-05, "loss": 11.7665, "step": 17 }, { "epoch": 0.006069163171980697, "grad_norm": 0.026373911648988724, "learning_rate": 9e-05, "loss": 11.7652, "step": 18 }, { "epoch": 0.006406338903757402, "grad_norm": 0.027122709900140762, "learning_rate": 9.5e-05, "loss": 11.7648, "step": 19 }, { "epoch": 0.006743514635534107, "grad_norm": 0.025863196700811386, "learning_rate": 0.0001, "loss": 11.7656, "step": 20 }, { "epoch": 0.007080690367310813, "grad_norm": 0.030005380511283875, "learning_rate": 9.991845519630678e-05, "loss": 11.7637, "step": 21 }, { "epoch": 0.007417866099087518, "grad_norm": 0.026818403974175453, "learning_rate": 9.967408676742751e-05, "loss": 11.7646, "step": 22 }, { "epoch": 0.007755041830864224, "grad_norm": 0.037829820066690445, "learning_rate": 9.926769179238466e-05, "loss": 11.7642, "step": 23 }, { "epoch": 0.00809221756264093, "grad_norm": 0.0359400175511837, "learning_rate": 9.870059584711668e-05, "loss": 11.7632, "step": 24 }, { "epoch": 0.008429393294417635, "grad_norm": 0.03318438678979874, "learning_rate": 9.797464868072488e-05, "loss": 11.7645, "step": 25 }, { "epoch": 0.00876656902619434, "grad_norm": 0.04368651658296585, "learning_rate": 9.709221818197624e-05, "loss": 11.7636, "step": 26 }, { "epoch": 0.009103744757971046, "grad_norm": 0.04104924201965332, "learning_rate": 9.60561826557425e-05, "loss": 11.7644, "step": 27 }, { "epoch": 0.009440920489747751, "grad_norm": 0.04168568551540375, "learning_rate": 9.486992143456792e-05, "loss": 11.7639, "step": 28 }, { "epoch": 0.009778096221524455, "grad_norm": 0.056156519800424576, "learning_rate": 9.353730385598887e-05, "loss": 11.7625, "step": 29 }, { "epoch": 0.01011527195330116, "grad_norm": 0.05746406316757202, "learning_rate": 9.206267664155907e-05, "loss": 11.7629, "step": 30 }, { "epoch": 0.010452447685077866, "grad_norm": 0.06729119271039963, "learning_rate": 9.045084971874738e-05, "loss": 11.7626, "step": 31 }, { "epoch": 0.010789623416854572, "grad_norm": 0.05893301963806152, "learning_rate": 8.870708053195413e-05, "loss": 11.7608, "step": 32 }, { "epoch": 0.011126799148631277, "grad_norm": 0.05561688914895058, "learning_rate": 8.683705689382024e-05, "loss": 11.7623, "step": 33 }, { "epoch": 0.011463974880407983, "grad_norm": 0.060429636389017105, "learning_rate": 8.484687843276469e-05, "loss": 11.7611, "step": 34 }, { "epoch": 0.011801150612184688, "grad_norm": 0.06633422523736954, "learning_rate": 8.274303669726426e-05, "loss": 11.7608, "step": 35 }, { "epoch": 0.012138326343961394, "grad_norm": 0.0642361268401146, "learning_rate": 8.053239398177191e-05, "loss": 11.7627, "step": 36 }, { "epoch": 0.0124755020757381, "grad_norm": 0.07594206184148788, "learning_rate": 7.822216094333847e-05, "loss": 11.7593, "step": 37 }, { "epoch": 0.012812677807514805, "grad_norm": 0.07679452002048492, "learning_rate": 7.58198730819481e-05, "loss": 11.7591, "step": 38 }, { "epoch": 0.01314985353929151, "grad_norm": 0.07356266677379608, "learning_rate": 7.333336616128369e-05, "loss": 11.7604, "step": 39 }, { "epoch": 0.013487029271068214, "grad_norm": 0.08774743974208832, "learning_rate": 7.077075065009433e-05, "loss": 11.7583, "step": 40 }, { "epoch": 0.01382420500284492, "grad_norm": 0.09124322235584259, "learning_rate": 6.814038526753205e-05, "loss": 11.7581, "step": 41 }, { "epoch": 0.014161380734621625, "grad_norm": 0.08625766634941101, "learning_rate": 6.545084971874738e-05, "loss": 11.7565, "step": 42 }, { "epoch": 0.01449855646639833, "grad_norm": 0.08285637944936752, "learning_rate": 6.271091670967436e-05, "loss": 11.7579, "step": 43 }, { "epoch": 0.014835732198175036, "grad_norm": 0.08066917955875397, "learning_rate": 5.992952333228728e-05, "loss": 11.7594, "step": 44 }, { "epoch": 0.015172907929951742, "grad_norm": 0.07849095016717911, "learning_rate": 5.7115741913664264e-05, "loss": 11.7539, "step": 45 }, { "epoch": 0.015510083661728447, "grad_norm": 0.06046842038631439, "learning_rate": 5.427875042394199e-05, "loss": 11.7571, "step": 46 }, { "epoch": 0.01584725939350515, "grad_norm": 0.0802258625626564, "learning_rate": 5.142780253968481e-05, "loss": 11.7566, "step": 47 }, { "epoch": 0.01618443512528186, "grad_norm": 0.07960178703069687, "learning_rate": 4.85721974603152e-05, "loss": 11.7563, "step": 48 }, { "epoch": 0.016521610857058562, "grad_norm": 0.08732843399047852, "learning_rate": 4.5721249576058027e-05, "loss": 11.7573, "step": 49 }, { "epoch": 0.01685878658883527, "grad_norm": 0.061963461339473724, "learning_rate": 4.288425808633575e-05, "loss": 11.7561, "step": 50 }, { "epoch": 0.01685878658883527, "eval_loss": 11.755621910095215, "eval_runtime": 90.4062, "eval_samples_per_second": 110.501, "eval_steps_per_second": 27.631, "step": 50 }, { "epoch": 0.017195962320611973, "grad_norm": 0.070088692009449, "learning_rate": 4.007047666771274e-05, "loss": 11.7571, "step": 51 }, { "epoch": 0.01753313805238868, "grad_norm": 0.06235595792531967, "learning_rate": 3.728908329032567e-05, "loss": 11.7546, "step": 52 }, { "epoch": 0.017870313784165384, "grad_norm": 0.059733107686042786, "learning_rate": 3.4549150281252636e-05, "loss": 11.756, "step": 53 }, { "epoch": 0.01820748951594209, "grad_norm": 0.05899588763713837, "learning_rate": 3.1859614732467954e-05, "loss": 11.7558, "step": 54 }, { "epoch": 0.018544665247718795, "grad_norm": 0.06057891994714737, "learning_rate": 2.9229249349905684e-05, "loss": 11.7538, "step": 55 }, { "epoch": 0.018881840979495502, "grad_norm": 0.06534547358751297, "learning_rate": 2.6666633838716314e-05, "loss": 11.7541, "step": 56 }, { "epoch": 0.019219016711272206, "grad_norm": 0.06708380579948425, "learning_rate": 2.418012691805191e-05, "loss": 11.7548, "step": 57 }, { "epoch": 0.01955619244304891, "grad_norm": 0.0493924543261528, "learning_rate": 2.1777839056661554e-05, "loss": 11.7566, "step": 58 }, { "epoch": 0.019893368174825617, "grad_norm": 0.05886533483862877, "learning_rate": 1.946760601822809e-05, "loss": 11.7567, "step": 59 }, { "epoch": 0.02023054390660232, "grad_norm": 0.05675411969423294, "learning_rate": 1.725696330273575e-05, "loss": 11.7544, "step": 60 }, { "epoch": 0.02056771963837903, "grad_norm": 0.0635736808180809, "learning_rate": 1.5153121567235335e-05, "loss": 11.7544, "step": 61 }, { "epoch": 0.020904895370155732, "grad_norm": 0.06321845203638077, "learning_rate": 1.3162943106179749e-05, "loss": 11.7532, "step": 62 }, { "epoch": 0.02124207110193244, "grad_norm": 0.056579649448394775, "learning_rate": 1.1292919468045877e-05, "loss": 11.7571, "step": 63 }, { "epoch": 0.021579246833709143, "grad_norm": 0.052547961473464966, "learning_rate": 9.549150281252633e-06, "loss": 11.7533, "step": 64 }, { "epoch": 0.02191642256548585, "grad_norm": 0.049376729875802994, "learning_rate": 7.937323358440935e-06, "loss": 11.7545, "step": 65 }, { "epoch": 0.022253598297262554, "grad_norm": 0.08245162665843964, "learning_rate": 6.462696144011149e-06, "loss": 11.757, "step": 66 }, { "epoch": 0.02259077402903926, "grad_norm": 0.05794164538383484, "learning_rate": 5.13007856543209e-06, "loss": 11.7554, "step": 67 }, { "epoch": 0.022927949760815965, "grad_norm": 0.04932315647602081, "learning_rate": 3.9438173442575e-06, "loss": 11.7546, "step": 68 }, { "epoch": 0.02326512549259267, "grad_norm": 0.05570968613028526, "learning_rate": 2.9077818180237693e-06, "loss": 11.7549, "step": 69 }, { "epoch": 0.023602301224369376, "grad_norm": 0.042931802570819855, "learning_rate": 2.0253513192751373e-06, "loss": 11.7553, "step": 70 }, { "epoch": 0.02393947695614608, "grad_norm": 0.05428018793463707, "learning_rate": 1.2994041528833266e-06, "loss": 11.754, "step": 71 }, { "epoch": 0.024276652687922787, "grad_norm": 0.048408687114715576, "learning_rate": 7.323082076153509e-07, "loss": 11.7557, "step": 72 }, { "epoch": 0.02461382841969949, "grad_norm": 0.05267668515443802, "learning_rate": 3.2591323257248893e-07, "loss": 11.754, "step": 73 }, { "epoch": 0.0249510041514762, "grad_norm": 0.05194791406393051, "learning_rate": 8.15448036932176e-08, "loss": 11.7525, "step": 74 }, { "epoch": 0.025288179883252902, "grad_norm": 0.05502924695611, "learning_rate": 0.0, "loss": 11.7538, "step": 75 } ], "logging_steps": 1, "max_steps": 75, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "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": 126479072231424.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }