| { | |
| "best_metric": 0.3237687349319458, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.005743165632896853, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011486331265793706, | |
| "grad_norm": 20.194072723388672, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9961, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011486331265793706, | |
| "eval_loss": 0.5248078107833862, | |
| "eval_runtime": 617.9557, | |
| "eval_samples_per_second": 23.728, | |
| "eval_steps_per_second": 2.966, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022972662531587412, | |
| "grad_norm": 17.88739013671875, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0858, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00034458993797381116, | |
| "grad_norm": 6.636772632598877, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0479, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00045945325063174823, | |
| "grad_norm": 5.536622047424316, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7255, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005743165632896852, | |
| "grad_norm": 5.835659027099609, | |
| "learning_rate": 0.0001, | |
| "loss": 1.879, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006891798759476223, | |
| "grad_norm": 3.0433731079101562, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.8946, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008040431886055594, | |
| "grad_norm": 5.9740681648254395, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.9344, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009189065012634965, | |
| "grad_norm": 1.4726699590682983, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.8448, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010337698139214334, | |
| "grad_norm": 3.3580729961395264, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.1496, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011486331265793705, | |
| "grad_norm": 19.40848159790039, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.032, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012634964392373076, | |
| "grad_norm": 3.5965750217437744, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6346, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0013783597518952446, | |
| "grad_norm": 2.1662826538085938, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.8285, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0014932230645531817, | |
| "grad_norm": 2.366093158721924, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.6677, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0016080863772111188, | |
| "grad_norm": 1.0059821605682373, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.5528, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0017229496898690559, | |
| "grad_norm": 1.226986289024353, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.5359, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001837813002526993, | |
| "grad_norm": 1.7851588726043701, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.0056, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00195267631518493, | |
| "grad_norm": 1.310687780380249, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.7473, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002067539627842867, | |
| "grad_norm": 1.1058948040008545, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.4829, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002182402940500804, | |
| "grad_norm": 1.3350424766540527, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.5503, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002297266253158741, | |
| "grad_norm": 1.8176335096359253, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5147, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002412129565816678, | |
| "grad_norm": 1.88288152217865, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.767, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002526992878474615, | |
| "grad_norm": 1.9403029680252075, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.6289, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002641856191132552, | |
| "grad_norm": 2.1161484718322754, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6755, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0027567195037904893, | |
| "grad_norm": 1.9855263233184814, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.921, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0028715828164484264, | |
| "grad_norm": 2.2303965091705322, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.6624, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0028715828164484264, | |
| "eval_loss": 0.37796109914779663, | |
| "eval_runtime": 620.9259, | |
| "eval_samples_per_second": 23.615, | |
| "eval_steps_per_second": 2.952, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0029864461291063634, | |
| "grad_norm": 2.292692184448242, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.4062, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0031013094417643005, | |
| "grad_norm": 2.8349287509918213, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.679, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0032161727544222376, | |
| "grad_norm": 2.254132032394409, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.5455, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0033310360670801746, | |
| "grad_norm": 2.188596248626709, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.591, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0034458993797381117, | |
| "grad_norm": 1.725136399269104, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.467, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003560762692396049, | |
| "grad_norm": 1.6573512554168701, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.4838, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.003675626005053986, | |
| "grad_norm": 2.2952048778533936, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.5725, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.003790489317711923, | |
| "grad_norm": 1.939889907836914, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.6289, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00390535263036986, | |
| "grad_norm": 1.8188632726669312, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.3653, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004020215943027797, | |
| "grad_norm": 2.1988892555236816, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6012, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004135079255685734, | |
| "grad_norm": 2.2693634033203125, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.5576, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004249942568343671, | |
| "grad_norm": 1.932142734527588, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.3468, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004364805881001608, | |
| "grad_norm": 3.0825328826904297, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.333, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004479669193659545, | |
| "grad_norm": 1.783441424369812, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.1038, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.004594532506317482, | |
| "grad_norm": 1.5691484212875366, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.1039, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0047093958189754195, | |
| "grad_norm": 1.9904344081878662, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.3097, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.004824259131633356, | |
| "grad_norm": 2.1154487133026123, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.5107, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.004939122444291294, | |
| "grad_norm": 1.9345293045043945, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.3873, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.00505398575694923, | |
| "grad_norm": 1.7051095962524414, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.3449, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005168849069607168, | |
| "grad_norm": 1.8302801847457886, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.483, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005283712382265104, | |
| "grad_norm": 1.9598950147628784, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.3838, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005398575694923042, | |
| "grad_norm": 1.9354257583618164, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.422, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.005513439007580979, | |
| "grad_norm": 2.225748062133789, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.5035, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005628302320238916, | |
| "grad_norm": 1.9461932182312012, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.1787, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.005743165632896853, | |
| "grad_norm": 1.6582098007202148, | |
| "learning_rate": 0.0, | |
| "loss": 1.359, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005743165632896853, | |
| "eval_loss": 0.3237687349319458, | |
| "eval_runtime": 620.993, | |
| "eval_samples_per_second": 23.612, | |
| "eval_steps_per_second": 2.952, | |
| "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": 3.57749502246912e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |