| { | |
| "best_metric": 1.5975532531738281, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008104056080068074, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016208112160136148, | |
| "grad_norm": 24.297019958496094, | |
| "learning_rate": 2e-05, | |
| "loss": 11.3236, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016208112160136148, | |
| "eval_loss": 2.9382340908050537, | |
| "eval_runtime": 747.9836, | |
| "eval_samples_per_second": 13.893, | |
| "eval_steps_per_second": 1.737, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032416224320272295, | |
| "grad_norm": 24.249916076660156, | |
| "learning_rate": 4e-05, | |
| "loss": 11.5612, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00048624336480408443, | |
| "grad_norm": 16.707523345947266, | |
| "learning_rate": 6e-05, | |
| "loss": 11.2607, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006483244864054459, | |
| "grad_norm": 15.533491134643555, | |
| "learning_rate": 8e-05, | |
| "loss": 10.2298, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008104056080068074, | |
| "grad_norm": 14.662958145141602, | |
| "learning_rate": 0.0001, | |
| "loss": 9.4951, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009724867296081689, | |
| "grad_norm": 11.636035919189453, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 9.1814, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011345678512095303, | |
| "grad_norm": 10.30533218383789, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 9.4261, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012966489728108918, | |
| "grad_norm": 8.74864387512207, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 8.5058, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014587300944122533, | |
| "grad_norm": 8.249582290649414, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 8.7713, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016208112160136148, | |
| "grad_norm": 7.471890926361084, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 7.5653, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017828923376149762, | |
| "grad_norm": 6.764472484588623, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 7.4305, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0019449734592163377, | |
| "grad_norm": 6.544780731201172, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 7.8787, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002107054580817699, | |
| "grad_norm": 6.782019138336182, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 7.5796, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0022691357024190607, | |
| "grad_norm": 6.3458123207092285, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 7.4855, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002431216824020422, | |
| "grad_norm": 6.391896724700928, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 7.0854, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025932979456217836, | |
| "grad_norm": 6.019820213317871, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 7.2838, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002755379067223145, | |
| "grad_norm": 6.196849346160889, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 6.9194, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0029174601888245066, | |
| "grad_norm": 6.031044006347656, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 6.902, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003079541310425868, | |
| "grad_norm": 6.036059856414795, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 7.1366, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032416224320272295, | |
| "grad_norm": 5.807440280914307, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.8278, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003403703553628591, | |
| "grad_norm": 5.767394065856934, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 6.6886, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0035657846752299525, | |
| "grad_norm": 5.627509117126465, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 6.6944, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003727865796831314, | |
| "grad_norm": 6.078296184539795, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 6.8693, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0038899469184326754, | |
| "grad_norm": 5.587927341461182, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 6.6312, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004052028040034037, | |
| "grad_norm": 5.718355655670166, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 6.2087, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004052028040034037, | |
| "eval_loss": 1.6942381858825684, | |
| "eval_runtime": 753.2364, | |
| "eval_samples_per_second": 13.796, | |
| "eval_steps_per_second": 1.725, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004214109161635398, | |
| "grad_norm": 5.737252235412598, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 6.5511, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00437619028323676, | |
| "grad_norm": 5.601446151733398, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 6.1659, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004538271404838121, | |
| "grad_norm": 5.734399795532227, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 6.3028, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004700352526439483, | |
| "grad_norm": 5.821112155914307, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 6.4599, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004862433648040844, | |
| "grad_norm": 5.711313724517822, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 6.2104, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005024514769642206, | |
| "grad_norm": 5.616081237792969, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 5.9626, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005186595891243567, | |
| "grad_norm": 5.939799785614014, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 6.2108, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005348677012844929, | |
| "grad_norm": 6.253535747528076, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 6.3835, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00551075813444629, | |
| "grad_norm": 6.217836380004883, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 6.3151, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005672839256047652, | |
| "grad_norm": 6.690835475921631, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.5325, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005834920377649013, | |
| "grad_norm": 6.233741283416748, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 6.111, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005997001499250375, | |
| "grad_norm": 6.690580368041992, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 6.5764, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006159082620851736, | |
| "grad_norm": 7.05441951751709, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 6.6446, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006321163742453098, | |
| "grad_norm": 7.1699137687683105, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 6.8346, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006483244864054459, | |
| "grad_norm": 8.0182466506958, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 7.0368, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0066453259856558205, | |
| "grad_norm": 8.176334381103516, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 7.135, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006807407107257182, | |
| "grad_norm": 7.7356791496276855, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 6.6282, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0069694882288585435, | |
| "grad_norm": 8.644556045532227, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 7.1975, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007131569350459905, | |
| "grad_norm": 9.53820514678955, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 6.8888, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007293650472061266, | |
| "grad_norm": 9.34225082397461, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 6.8444, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007455731593662628, | |
| "grad_norm": 10.200462341308594, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 7.234, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007617812715263989, | |
| "grad_norm": 11.076253890991211, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 7.0912, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007779893836865351, | |
| "grad_norm": 12.434575080871582, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 7.1678, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007941974958466713, | |
| "grad_norm": 14.701952934265137, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 7.5589, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008104056080068074, | |
| "grad_norm": 20.88030433654785, | |
| "learning_rate": 0.0, | |
| "loss": 6.5856, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008104056080068074, | |
| "eval_loss": 1.5975532531738281, | |
| "eval_runtime": 754.8797, | |
| "eval_samples_per_second": 13.766, | |
| "eval_steps_per_second": 1.721, | |
| "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": 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": 6.857571679862784e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |