| { | |
| "best_metric": 0.8835566639900208, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.0407239819004523, | |
| "eval_steps": 25, | |
| "global_step": 63, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.048265460030165915, | |
| "grad_norm": 0.8179398775100708, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.048265460030165915, | |
| "eval_loss": 1.9362893104553223, | |
| "eval_runtime": 3.1934, | |
| "eval_samples_per_second": 15.657, | |
| "eval_steps_per_second": 4.071, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09653092006033183, | |
| "grad_norm": 0.8880188465118408, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0026, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14479638009049775, | |
| "grad_norm": 0.865829348564148, | |
| "learning_rate": 9.994033404481737e-05, | |
| "loss": 2.0396, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19306184012066366, | |
| "grad_norm": 0.9091627597808838, | |
| "learning_rate": 9.97614944026565e-05, | |
| "loss": 2.0337, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24132730015082957, | |
| "grad_norm": 1.1735113859176636, | |
| "learning_rate": 9.946395532409847e-05, | |
| "loss": 2.102, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2895927601809955, | |
| "grad_norm": 0.6793145537376404, | |
| "learning_rate": 9.904850582929111e-05, | |
| "loss": 1.5544, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3378582202111614, | |
| "grad_norm": 0.8480486273765564, | |
| "learning_rate": 9.851624761560943e-05, | |
| "loss": 1.5623, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3861236802413273, | |
| "grad_norm": 0.8613075613975525, | |
| "learning_rate": 9.786859213615221e-05, | |
| "loss": 1.434, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4343891402714932, | |
| "grad_norm": 1.1011731624603271, | |
| "learning_rate": 9.710725685682222e-05, | |
| "loss": 1.3384, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.48265460030165913, | |
| "grad_norm": 1.5078444480895996, | |
| "learning_rate": 9.623426070191522e-05, | |
| "loss": 1.2491, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.530920060331825, | |
| "grad_norm": 0.9261085987091064, | |
| "learning_rate": 9.525191870029581e-05, | |
| "loss": 1.1621, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.579185520361991, | |
| "grad_norm": 1.253775954246521, | |
| "learning_rate": 9.4162835846357e-05, | |
| "loss": 1.2139, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": 1.0710676908493042, | |
| "learning_rate": 9.296990019204335e-05, | |
| "loss": 1.1141, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6757164404223228, | |
| "grad_norm": 0.7302868366241455, | |
| "learning_rate": 9.167627518825651e-05, | |
| "loss": 1.0311, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7239819004524887, | |
| "grad_norm": 0.6581991314888, | |
| "learning_rate": 9.028539129595199e-05, | |
| "loss": 1.0503, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7722473604826546, | |
| "grad_norm": 0.43014147877693176, | |
| "learning_rate": 8.88009368891734e-05, | |
| "loss": 1.051, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.5059635639190674, | |
| "learning_rate": 8.72268484741477e-05, | |
| "loss": 1.0703, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8687782805429864, | |
| "grad_norm": 0.5659109950065613, | |
| "learning_rate": 8.556730025037819e-05, | |
| "loss": 1.069, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9170437405731523, | |
| "grad_norm": 0.5554922223091125, | |
| "learning_rate": 8.38266930414179e-05, | |
| "loss": 0.9979, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9653092006033183, | |
| "grad_norm": 0.553922176361084, | |
| "learning_rate": 8.200964262467657e-05, | |
| "loss": 0.969, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0135746606334841, | |
| "grad_norm": 0.5600609183311462, | |
| "learning_rate": 8.01209674912089e-05, | |
| "loss": 1.3362, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.06184012066365, | |
| "grad_norm": 0.3536495566368103, | |
| "learning_rate": 7.81656760679424e-05, | |
| "loss": 0.9588, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.110105580693816, | |
| "grad_norm": 0.413228303194046, | |
| "learning_rate": 7.614895343622941e-05, | |
| "loss": 0.9448, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1583710407239818, | |
| "grad_norm": 0.4351142346858978, | |
| "learning_rate": 7.407614758194375e-05, | |
| "loss": 0.9537, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2066365007541477, | |
| "grad_norm": 0.4623880684375763, | |
| "learning_rate": 7.195275521358334e-05, | |
| "loss": 0.9933, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2066365007541477, | |
| "eval_loss": 0.907273530960083, | |
| "eval_runtime": 3.2352, | |
| "eval_samples_per_second": 15.455, | |
| "eval_steps_per_second": 4.018, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2549019607843137, | |
| "grad_norm": 0.5164334177970886, | |
| "learning_rate": 6.978440718598757e-05, | |
| "loss": 0.9255, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3031674208144797, | |
| "grad_norm": 0.3558405339717865, | |
| "learning_rate": 6.757685356832243e-05, | |
| "loss": 0.9118, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3514328808446456, | |
| "grad_norm": 0.3763732314109802, | |
| "learning_rate": 6.533594839593081e-05, | |
| "loss": 0.9167, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3996983408748114, | |
| "grad_norm": 0.41895684599876404, | |
| "learning_rate": 6.306763414648311e-05, | |
| "loss": 0.8792, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4479638009049773, | |
| "grad_norm": 0.4729040861129761, | |
| "learning_rate": 6.07779259815948e-05, | |
| "loss": 0.8689, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4962292609351433, | |
| "grad_norm": 0.4113113284111023, | |
| "learning_rate": 5.84728957956991e-05, | |
| "loss": 0.8323, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.544494720965309, | |
| "grad_norm": 0.38738012313842773, | |
| "learning_rate": 5.61586561144745e-05, | |
| "loss": 0.9668, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5927601809954752, | |
| "grad_norm": 0.4025406241416931, | |
| "learning_rate": 5.384134388552552e-05, | |
| "loss": 0.9097, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.641025641025641, | |
| "grad_norm": 0.4479067027568817, | |
| "learning_rate": 5.152710420430091e-05, | |
| "loss": 0.9427, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.689291101055807, | |
| "grad_norm": 0.44481536746025085, | |
| "learning_rate": 4.9222074018405206e-05, | |
| "loss": 0.8624, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.737556561085973, | |
| "grad_norm": 0.46713030338287354, | |
| "learning_rate": 4.693236585351691e-05, | |
| "loss": 0.8882, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.7858220211161386, | |
| "grad_norm": 0.3744671642780304, | |
| "learning_rate": 4.4664051604069214e-05, | |
| "loss": 0.9416, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8340874811463048, | |
| "grad_norm": 0.44846299290657043, | |
| "learning_rate": 4.2423146431677585e-05, | |
| "loss": 1.0138, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.4410933256149292, | |
| "learning_rate": 4.021559281401244e-05, | |
| "loss": 0.8851, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9306184012066365, | |
| "grad_norm": 0.47139236330986023, | |
| "learning_rate": 3.804724478641667e-05, | |
| "loss": 0.8259, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9788838612368025, | |
| "grad_norm": 0.5577002167701721, | |
| "learning_rate": 3.592385241805628e-05, | |
| "loss": 1.0754, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.0271493212669682, | |
| "grad_norm": 0.4690263569355011, | |
| "learning_rate": 3.385104656377062e-05, | |
| "loss": 0.9935, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.0754147812971344, | |
| "grad_norm": 0.38023629784584045, | |
| "learning_rate": 3.183432393205763e-05, | |
| "loss": 0.8952, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.1236802413273, | |
| "grad_norm": 0.41368529200553894, | |
| "learning_rate": 2.9879032508791093e-05, | |
| "loss": 0.9206, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.171945701357466, | |
| "grad_norm": 0.4637509882450104, | |
| "learning_rate": 2.799035737532344e-05, | |
| "loss": 0.826, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.220211161387632, | |
| "grad_norm": 0.510759711265564, | |
| "learning_rate": 2.6173306958582123e-05, | |
| "loss": 0.8312, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.268476621417798, | |
| "grad_norm": 0.4286244511604309, | |
| "learning_rate": 2.443269974962181e-05, | |
| "loss": 0.7866, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.3167420814479636, | |
| "grad_norm": 0.37086257338523865, | |
| "learning_rate": 2.277315152585231e-05, | |
| "loss": 0.7716, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.3650075414781297, | |
| "grad_norm": 0.415539026260376, | |
| "learning_rate": 2.1199063110826618e-05, | |
| "loss": 0.7904, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.4132730015082955, | |
| "grad_norm": 0.47227543592453003, | |
| "learning_rate": 1.9714608704048037e-05, | |
| "loss": 0.7771, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4132730015082955, | |
| "eval_loss": 0.8835566639900208, | |
| "eval_runtime": 3.2406, | |
| "eval_samples_per_second": 15.429, | |
| "eval_steps_per_second": 4.012, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 0.4867364466190338, | |
| "learning_rate": 1.8323724811743496e-05, | |
| "loss": 0.7947, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.5098039215686274, | |
| "grad_norm": 0.4455429017543793, | |
| "learning_rate": 1.703009980795665e-05, | |
| "loss": 0.8328, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.558069381598793, | |
| "grad_norm": 0.46695399284362793, | |
| "learning_rate": 1.5837164153643015e-05, | |
| "loss": 0.9561, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.6063348416289593, | |
| "grad_norm": 0.4342208206653595, | |
| "learning_rate": 1.474808129970421e-05, | |
| "loss": 0.7705, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.654600301659125, | |
| "grad_norm": 0.45350006222724915, | |
| "learning_rate": 1.3765739298084793e-05, | |
| "loss": 0.7835, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.7028657616892913, | |
| "grad_norm": 0.5114506483078003, | |
| "learning_rate": 1.2892743143177793e-05, | |
| "loss": 0.7688, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.751131221719457, | |
| "grad_norm": 0.458067923784256, | |
| "learning_rate": 1.2131407863847787e-05, | |
| "loss": 0.8188, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.7993966817496228, | |
| "grad_norm": 0.396027535200119, | |
| "learning_rate": 1.1483752384390584e-05, | |
| "loss": 0.803, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.847662141779789, | |
| "grad_norm": 0.5041918158531189, | |
| "learning_rate": 1.09514941707089e-05, | |
| "loss": 0.9092, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.8959276018099547, | |
| "grad_norm": 0.49184009432792664, | |
| "learning_rate": 1.0536044675901534e-05, | |
| "loss": 0.8057, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.944193061840121, | |
| "grad_norm": 0.5316694974899292, | |
| "learning_rate": 1.0238505597343493e-05, | |
| "loss": 0.7522, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.9924585218702866, | |
| "grad_norm": 0.5798410773277283, | |
| "learning_rate": 1.0059665955182628e-05, | |
| "loss": 0.9344, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.0407239819004523, | |
| "grad_norm": 0.40940624475479126, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8405, | |
| "step": 63 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 63, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 7.086312841417851e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |