| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9908256880733946, | |
| "eval_steps": 500, | |
| "global_step": 54, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01834862385321101, | |
| "grad_norm": 0.04378490149974823, | |
| "learning_rate": 4.999989423013716e-05, | |
| "loss": 0.6713, | |
| "num_input_tokens_seen": 44136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03669724770642202, | |
| "grad_norm": 0.040646992623806, | |
| "learning_rate": 4.999957692144361e-05, | |
| "loss": 0.533, | |
| "num_input_tokens_seen": 83096, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05504587155963303, | |
| "grad_norm": 0.04658753052353859, | |
| "learning_rate": 4.999904807660428e-05, | |
| "loss": 0.6048, | |
| "num_input_tokens_seen": 122112, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07339449541284404, | |
| "grad_norm": 0.04322144016623497, | |
| "learning_rate": 4.999830770009406e-05, | |
| "loss": 0.4948, | |
| "num_input_tokens_seen": 163064, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09174311926605505, | |
| "grad_norm": 0.06536195427179337, | |
| "learning_rate": 4.999735579817769e-05, | |
| "loss": 0.6607, | |
| "num_input_tokens_seen": 203808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11009174311926606, | |
| "grad_norm": 0.059904925525188446, | |
| "learning_rate": 4.9996192378909786e-05, | |
| "loss": 0.5802, | |
| "num_input_tokens_seen": 241824, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12844036697247707, | |
| "grad_norm": 0.19818365573883057, | |
| "learning_rate": 4.999481745213471e-05, | |
| "loss": 0.5148, | |
| "num_input_tokens_seen": 287608, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14678899082568808, | |
| "grad_norm": 0.05985472351312637, | |
| "learning_rate": 4.9993231029486544e-05, | |
| "loss": 0.5714, | |
| "num_input_tokens_seen": 325320, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1651376146788991, | |
| "grad_norm": 0.061375778168439865, | |
| "learning_rate": 4.999143312438893e-05, | |
| "loss": 0.6812, | |
| "num_input_tokens_seen": 369848, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1834862385321101, | |
| "grad_norm": 0.06196414306759834, | |
| "learning_rate": 4.998942375205502e-05, | |
| "loss": 0.5358, | |
| "num_input_tokens_seen": 415104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2018348623853211, | |
| "grad_norm": 0.07861393690109253, | |
| "learning_rate": 4.9987202929487275e-05, | |
| "loss": 0.6527, | |
| "num_input_tokens_seen": 467224, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.22018348623853212, | |
| "grad_norm": 0.05596446990966797, | |
| "learning_rate": 4.99847706754774e-05, | |
| "loss": 0.5354, | |
| "num_input_tokens_seen": 502824, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23853211009174313, | |
| "grad_norm": 0.05289844051003456, | |
| "learning_rate": 4.998212701060612e-05, | |
| "loss": 0.5263, | |
| "num_input_tokens_seen": 544744, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25688073394495414, | |
| "grad_norm": 0.04996591433882713, | |
| "learning_rate": 4.997927195724303e-05, | |
| "loss": 0.5536, | |
| "num_input_tokens_seen": 591136, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.27522935779816515, | |
| "grad_norm": 0.05822828412055969, | |
| "learning_rate": 4.997620553954645e-05, | |
| "loss": 0.6106, | |
| "num_input_tokens_seen": 629664, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.29357798165137616, | |
| "grad_norm": 0.06353770196437836, | |
| "learning_rate": 4.997292778346312e-05, | |
| "loss": 0.5129, | |
| "num_input_tokens_seen": 663392, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3119266055045872, | |
| "grad_norm": 0.07256966829299927, | |
| "learning_rate": 4.996943871672807e-05, | |
| "loss": 0.6377, | |
| "num_input_tokens_seen": 698360, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3302752293577982, | |
| "grad_norm": 0.055458713322877884, | |
| "learning_rate": 4.996573836886435e-05, | |
| "loss": 0.4083, | |
| "num_input_tokens_seen": 737520, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3486238532110092, | |
| "grad_norm": 0.07792335003614426, | |
| "learning_rate": 4.9961826771182784e-05, | |
| "loss": 0.6086, | |
| "num_input_tokens_seen": 768056, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "grad_norm": 0.06627275049686432, | |
| "learning_rate": 4.995770395678171e-05, | |
| "loss": 0.4591, | |
| "num_input_tokens_seen": 806256, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3853211009174312, | |
| "grad_norm": 0.05830290913581848, | |
| "learning_rate": 4.9953369960546676e-05, | |
| "loss": 0.3731, | |
| "num_input_tokens_seen": 842336, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4036697247706422, | |
| "grad_norm": 0.07277437299489975, | |
| "learning_rate": 4.9948824819150185e-05, | |
| "loss": 0.6243, | |
| "num_input_tokens_seen": 876672, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.42201834862385323, | |
| "grad_norm": 0.07477546483278275, | |
| "learning_rate": 4.994406857105136e-05, | |
| "loss": 0.5788, | |
| "num_input_tokens_seen": 915192, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.44036697247706424, | |
| "grad_norm": 0.06912907212972641, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 0.4753, | |
| "num_input_tokens_seen": 951904, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.45871559633027525, | |
| "grad_norm": 0.0655476376414299, | |
| "learning_rate": 4.993392291751431e-05, | |
| "loss": 0.4518, | |
| "num_input_tokens_seen": 1001816, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.47706422018348627, | |
| "grad_norm": 0.06466512382030487, | |
| "learning_rate": 4.992853359792444e-05, | |
| "loss": 0.5638, | |
| "num_input_tokens_seen": 1053064, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4954128440366973, | |
| "grad_norm": 0.0645688995718956, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.4644, | |
| "num_input_tokens_seen": 1086688, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5137614678899083, | |
| "grad_norm": 0.07181251049041748, | |
| "learning_rate": 4.9917122201112656e-05, | |
| "loss": 0.6191, | |
| "num_input_tokens_seen": 1134824, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5321100917431193, | |
| "grad_norm": 0.07322589308023453, | |
| "learning_rate": 4.9911100220449293e-05, | |
| "loss": 0.6752, | |
| "num_input_tokens_seen": 1172072, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5504587155963303, | |
| "grad_norm": 0.06396070122718811, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 0.3587, | |
| "num_input_tokens_seen": 1211096, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5688073394495413, | |
| "grad_norm": 0.07803395390510559, | |
| "learning_rate": 4.989842394938482e-05, | |
| "loss": 0.459, | |
| "num_input_tokens_seen": 1259456, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5871559633027523, | |
| "grad_norm": 0.05974648892879486, | |
| "learning_rate": 4.989176976624511e-05, | |
| "loss": 0.4148, | |
| "num_input_tokens_seen": 1306944, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6055045871559633, | |
| "grad_norm": 0.09784268587827682, | |
| "learning_rate": 4.988490495917947e-05, | |
| "loss": 0.539, | |
| "num_input_tokens_seen": 1353744, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6238532110091743, | |
| "grad_norm": 0.09906516224145889, | |
| "learning_rate": 4.987782958627508e-05, | |
| "loss": 0.5453, | |
| "num_input_tokens_seen": 1394736, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6422018348623854, | |
| "grad_norm": 0.08984062820672989, | |
| "learning_rate": 4.987054370740083e-05, | |
| "loss": 0.468, | |
| "num_input_tokens_seen": 1442048, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6605504587155964, | |
| "grad_norm": 0.08672655373811722, | |
| "learning_rate": 4.9863047384206835e-05, | |
| "loss": 0.4078, | |
| "num_input_tokens_seen": 1478440, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6788990825688074, | |
| "grad_norm": 0.1327345073223114, | |
| "learning_rate": 4.9855340680123905e-05, | |
| "loss": 0.5299, | |
| "num_input_tokens_seen": 1525992, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6972477064220184, | |
| "grad_norm": 0.09178602695465088, | |
| "learning_rate": 4.9847423660363e-05, | |
| "loss": 0.439, | |
| "num_input_tokens_seen": 1555608, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7155963302752294, | |
| "grad_norm": 0.09418320655822754, | |
| "learning_rate": 4.983929639191469e-05, | |
| "loss": 0.5337, | |
| "num_input_tokens_seen": 1597392, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 0.08294719457626343, | |
| "learning_rate": 4.983095894354858e-05, | |
| "loss": 0.4536, | |
| "num_input_tokens_seen": 1649656, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7522935779816514, | |
| "grad_norm": 0.09774205833673477, | |
| "learning_rate": 4.982241138581273e-05, | |
| "loss": 0.5221, | |
| "num_input_tokens_seen": 1695952, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7706422018348624, | |
| "grad_norm": 0.09319107979536057, | |
| "learning_rate": 4.9813653791033057e-05, | |
| "loss": 0.4279, | |
| "num_input_tokens_seen": 1737224, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7889908256880734, | |
| "grad_norm": 0.09561405330896378, | |
| "learning_rate": 4.980468623331273e-05, | |
| "loss": 0.5121, | |
| "num_input_tokens_seen": 1772320, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8073394495412844, | |
| "grad_norm": 0.08274025470018387, | |
| "learning_rate": 4.979550878853154e-05, | |
| "loss": 0.54, | |
| "num_input_tokens_seen": 1823888, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8256880733944955, | |
| "grad_norm": 0.08728913217782974, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.4488, | |
| "num_input_tokens_seen": 1872488, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8440366972477065, | |
| "grad_norm": 0.0787016749382019, | |
| "learning_rate": 4.9776524550184965e-05, | |
| "loss": 0.4353, | |
| "num_input_tokens_seen": 1924744, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8623853211009175, | |
| "grad_norm": 0.10952188074588776, | |
| "learning_rate": 4.97667179172564e-05, | |
| "loss": 0.4784, | |
| "num_input_tokens_seen": 1959936, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8807339449541285, | |
| "grad_norm": 0.08525826781988144, | |
| "learning_rate": 4.975670171853926e-05, | |
| "loss": 0.3586, | |
| "num_input_tokens_seen": 2003896, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8990825688073395, | |
| "grad_norm": 0.10409987717866898, | |
| "learning_rate": 4.9746476038786496e-05, | |
| "loss": 0.4451, | |
| "num_input_tokens_seen": 2047632, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9174311926605505, | |
| "grad_norm": 0.0782993957400322, | |
| "learning_rate": 4.973604096452361e-05, | |
| "loss": 0.3591, | |
| "num_input_tokens_seen": 2096928, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9357798165137615, | |
| "grad_norm": 0.09829951077699661, | |
| "learning_rate": 4.9725396584047925e-05, | |
| "loss": 0.3415, | |
| "num_input_tokens_seen": 2129536, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.9541284403669725, | |
| "grad_norm": 0.10606162995100021, | |
| "learning_rate": 4.971454298742779e-05, | |
| "loss": 0.3758, | |
| "num_input_tokens_seen": 2169144, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.9724770642201835, | |
| "grad_norm": 0.09280356764793396, | |
| "learning_rate": 4.97034802665019e-05, | |
| "loss": 0.485, | |
| "num_input_tokens_seen": 2207720, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.9908256880733946, | |
| "grad_norm": 0.11888203024864197, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.3469, | |
| "num_input_tokens_seen": 2236392, | |
| "step": 54 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 1080, | |
| "num_input_tokens_seen": 2236392, | |
| "num_train_epochs": 20, | |
| "save_steps": 54, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8866577009855693e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |