| { | |
| "best_metric": 1.1159125566482544, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03530969545387671, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004707959393850228, | |
| "grad_norm": 2.019765853881836, | |
| "learning_rate": 5e-06, | |
| "loss": 1.7321, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004707959393850228, | |
| "eval_loss": 1.5949971675872803, | |
| "eval_runtime": 1054.1316, | |
| "eval_samples_per_second": 6.788, | |
| "eval_steps_per_second": 1.697, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009415918787700456, | |
| "grad_norm": 1.8714739084243774, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5917, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014123878181550684, | |
| "grad_norm": 1.897204041481018, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.6, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018831837575400913, | |
| "grad_norm": 2.012906074523926, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6586, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002353979696925114, | |
| "grad_norm": 1.9945567846298218, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.5295, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002824775636310137, | |
| "grad_norm": 1.5244598388671875, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4992, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032955715756951597, | |
| "grad_norm": 1.214459776878357, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.3186, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0037663675150801826, | |
| "grad_norm": 1.1973023414611816, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3787, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0042371634544652054, | |
| "grad_norm": 0.9985453486442566, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.3009, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004707959393850228, | |
| "grad_norm": 0.8486191630363464, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1828, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005178755333235251, | |
| "grad_norm": 0.8273810744285583, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.2181, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005649551272620274, | |
| "grad_norm": 0.7928112149238586, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2206, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006120347212005296, | |
| "grad_norm": 0.7599514126777649, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.2137, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006591143151390319, | |
| "grad_norm": 0.8310830593109131, | |
| "learning_rate": 7e-05, | |
| "loss": 1.0807, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007061939090775342, | |
| "grad_norm": 0.7516305446624756, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.2852, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007532735030160365, | |
| "grad_norm": 0.8403298258781433, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2441, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008003530969545388, | |
| "grad_norm": 0.7195339202880859, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.2419, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008474326908930411, | |
| "grad_norm": 0.6701211333274841, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2008, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008945122848315433, | |
| "grad_norm": 0.7064545154571533, | |
| "learning_rate": 9.5e-05, | |
| "loss": 1.1691, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009415918787700456, | |
| "grad_norm": 0.7223305702209473, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1513, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009886714727085478, | |
| "grad_norm": 0.6430530548095703, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 1.1434, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010357510666470502, | |
| "grad_norm": 0.6965686082839966, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 1.1117, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010828306605855525, | |
| "grad_norm": 0.6954874992370605, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 1.1805, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011299102545240547, | |
| "grad_norm": 0.6635076999664307, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 1.1295, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01176989848462557, | |
| "grad_norm": 0.6618334650993347, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 1.0415, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012240694424010592, | |
| "grad_norm": 0.6411958932876587, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 1.1411, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012711490363395616, | |
| "grad_norm": 0.6791735887527466, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 1.2177, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013182286302780639, | |
| "grad_norm": 0.7023264765739441, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 1.2012, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013653082242165661, | |
| "grad_norm": 0.6761083602905273, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 1.1297, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014123878181550684, | |
| "grad_norm": 0.720009982585907, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 1.1497, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014594674120935706, | |
| "grad_norm": 0.6534513235092163, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.2473, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01506547006032073, | |
| "grad_norm": 0.62485271692276, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 1.1087, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.015536265999705753, | |
| "grad_norm": 0.6664251089096069, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 1.1532, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016007061939090777, | |
| "grad_norm": 0.6808733344078064, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 1.1473, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.016477857878475798, | |
| "grad_norm": 0.627700924873352, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 1.125, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016948653817860822, | |
| "grad_norm": 0.6665758490562439, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 1.0809, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.017419449757245842, | |
| "grad_norm": 0.6675161719322205, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 1.1696, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.017890245696630867, | |
| "grad_norm": 0.6735967993736267, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 1.1322, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01836104163601589, | |
| "grad_norm": 0.6226209402084351, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 1.1079, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01883183757540091, | |
| "grad_norm": 0.648352324962616, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 1.1011, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019302633514785936, | |
| "grad_norm": 0.6328292489051819, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 1.1568, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019773429454170956, | |
| "grad_norm": 0.7246712446212769, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.112, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02024422539355598, | |
| "grad_norm": 0.689822256565094, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 1.1909, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.020715021332941005, | |
| "grad_norm": 0.6674534678459167, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 1.1454, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.021185817272326025, | |
| "grad_norm": 0.630682647228241, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 1.1645, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02165661321171105, | |
| "grad_norm": 0.6754137277603149, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 1.1158, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02212740915109607, | |
| "grad_norm": 0.6505759358406067, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 1.0663, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022598205090481095, | |
| "grad_norm": 0.6762368083000183, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 1.1291, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02306900102986612, | |
| "grad_norm": 0.7021005749702454, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 1.1421, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02353979696925114, | |
| "grad_norm": 0.6380864381790161, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 1.0817, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02353979696925114, | |
| "eval_loss": 1.1159125566482544, | |
| "eval_runtime": 1067.2054, | |
| "eval_samples_per_second": 6.704, | |
| "eval_steps_per_second": 1.676, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024010592908636164, | |
| "grad_norm": 0.6711025834083557, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 1.0878, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.024481388848021184, | |
| "grad_norm": 0.6568624973297119, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 1.0447, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02495218478740621, | |
| "grad_norm": 0.6191370487213135, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.1122, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.025422980726791233, | |
| "grad_norm": 0.6773213744163513, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 1.1193, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.025893776666176253, | |
| "grad_norm": 0.6792715191841125, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 1.1247, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.026364572605561278, | |
| "grad_norm": 0.6690425872802734, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 1.1017, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.026835368544946298, | |
| "grad_norm": 0.6485929489135742, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 1.0747, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.027306164484331322, | |
| "grad_norm": 0.675126314163208, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 1.07, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.027776960423716347, | |
| "grad_norm": 0.6962899565696716, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 1.0591, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.028247756363101367, | |
| "grad_norm": 0.662079393863678, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 1.1415, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02871855230248639, | |
| "grad_norm": 0.6812634468078613, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 1.0937, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.029189348241871412, | |
| "grad_norm": 0.7200164198875427, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 1.2216, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.029660144181256436, | |
| "grad_norm": 0.6734728813171387, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 1.1649, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03013094012064146, | |
| "grad_norm": 0.650775671005249, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.1018, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.03060173606002648, | |
| "grad_norm": 0.6936342716217041, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 1.16, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.031072531999411505, | |
| "grad_norm": 0.6400872468948364, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 1.083, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.03154332793879653, | |
| "grad_norm": 0.6761430501937866, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 1.0366, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.032014123878181554, | |
| "grad_norm": 0.6780744194984436, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 1.1405, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.03248491981756657, | |
| "grad_norm": 0.6598646640777588, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 1.084, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.032955715756951595, | |
| "grad_norm": 0.6628397107124329, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 1.061, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03342651169633662, | |
| "grad_norm": 0.6676144599914551, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 1.1337, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.033897307635721644, | |
| "grad_norm": 0.6578212976455688, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 1.1128, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.03436810357510667, | |
| "grad_norm": 0.6542023420333862, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 1.0441, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.034838899514491685, | |
| "grad_norm": 0.6668130159378052, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 1.0559, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.03530969545387671, | |
| "grad_norm": 0.6653211712837219, | |
| "learning_rate": 0.0, | |
| "loss": 1.1329, | |
| "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": 4.26566605602816e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |