| { | |
| "best_metric": 2.0449941158294678, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05770340450086555, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001154068090017311, | |
| "grad_norm": 10.938200950622559, | |
| "learning_rate": 2e-05, | |
| "loss": 6.2035, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001154068090017311, | |
| "eval_loss": 2.122575283050537, | |
| "eval_runtime": 54.6024, | |
| "eval_samples_per_second": 26.739, | |
| "eval_steps_per_second": 3.352, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002308136180034622, | |
| "grad_norm": 11.67940902709961, | |
| "learning_rate": 4e-05, | |
| "loss": 7.7797, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003462204270051933, | |
| "grad_norm": 11.162690162658691, | |
| "learning_rate": 6e-05, | |
| "loss": 7.6768, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004616272360069244, | |
| "grad_norm": 9.086465835571289, | |
| "learning_rate": 8e-05, | |
| "loss": 7.7911, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005770340450086555, | |
| "grad_norm": 8.803955078125, | |
| "learning_rate": 0.0001, | |
| "loss": 7.7189, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006924408540103866, | |
| "grad_norm": 8.171338081359863, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 7.5216, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008078476630121177, | |
| "grad_norm": 8.607847213745117, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 7.8374, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009232544720138488, | |
| "grad_norm": 7.716111183166504, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 7.2367, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0103866128101558, | |
| "grad_norm": 7.701160907745361, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 7.6365, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01154068090017311, | |
| "grad_norm": 8.31236743927002, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 7.4108, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012694748990190421, | |
| "grad_norm": 8.164664268493652, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 7.3503, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013848817080207732, | |
| "grad_norm": 7.869163990020752, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 7.8775, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015002885170225043, | |
| "grad_norm": 8.522551536560059, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 7.5652, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016156953260242354, | |
| "grad_norm": 8.944220542907715, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 7.72, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017311021350259664, | |
| "grad_norm": 7.63972282409668, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 7.6611, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018465089440276975, | |
| "grad_norm": 8.285905838012695, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 7.9625, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019619157530294286, | |
| "grad_norm": 9.12864875793457, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 8.054, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0207732256203116, | |
| "grad_norm": 8.1249418258667, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 7.9919, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02192729371032891, | |
| "grad_norm": 8.116121292114258, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 7.9385, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02308136180034622, | |
| "grad_norm": 8.311835289001465, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 7.4027, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024235429890363532, | |
| "grad_norm": 8.091967582702637, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 7.9201, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025389497980380843, | |
| "grad_norm": 7.40118932723999, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 7.9214, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026543566070398154, | |
| "grad_norm": 7.898697376251221, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 7.9338, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.027697634160415464, | |
| "grad_norm": 7.743147373199463, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 7.6968, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028851702250432775, | |
| "grad_norm": 8.870253562927246, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 7.362, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028851702250432775, | |
| "eval_loss": 2.0449941158294678, | |
| "eval_runtime": 55.5094, | |
| "eval_samples_per_second": 26.302, | |
| "eval_steps_per_second": 3.297, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.030005770340450086, | |
| "grad_norm": 8.109495162963867, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 7.9473, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.031159838430467397, | |
| "grad_norm": 8.148787498474121, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 7.2724, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03231390652048471, | |
| "grad_norm": 8.987346649169922, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 7.6946, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03346797461050202, | |
| "grad_norm": 8.511104583740234, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 7.9146, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03462204270051933, | |
| "grad_norm": 9.82064151763916, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 8.1611, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03577611079053664, | |
| "grad_norm": 10.174384117126465, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 8.4572, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03693017888055395, | |
| "grad_norm": 9.278128623962402, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 7.8648, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.038084246970571264, | |
| "grad_norm": 9.342947959899902, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 8.363, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03923831506058857, | |
| "grad_norm": 9.482563972473145, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 8.0515, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.040392383150605886, | |
| "grad_norm": 11.584480285644531, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 8.4733, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0415464512406232, | |
| "grad_norm": 9.485844612121582, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 7.3311, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04270051933064051, | |
| "grad_norm": 9.728912353515625, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 7.9032, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04385458742065782, | |
| "grad_norm": 9.852460861206055, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 8.1847, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04500865551067513, | |
| "grad_norm": 10.66511344909668, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 8.5239, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04616272360069244, | |
| "grad_norm": 11.959909439086914, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 8.5198, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04731679169070975, | |
| "grad_norm": 11.096136093139648, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 8.3557, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.048470859780727064, | |
| "grad_norm": 10.416865348815918, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 7.6118, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04962492787074437, | |
| "grad_norm": 12.099180221557617, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 8.1399, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.050778995960761686, | |
| "grad_norm": 11.580448150634766, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 8.2984, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05193306405077899, | |
| "grad_norm": 12.245722770690918, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 8.5435, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05308713214079631, | |
| "grad_norm": 13.376921653747559, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 8.0788, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.054241200230813615, | |
| "grad_norm": 17.974956512451172, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 8.3619, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05539526832083093, | |
| "grad_norm": 18.45572280883789, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 8.801, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05654933641084824, | |
| "grad_norm": 28.996519088745117, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 8.9224, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05770340450086555, | |
| "grad_norm": 45.305240631103516, | |
| "learning_rate": 0.0, | |
| "loss": 9.7115, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05770340450086555, | |
| "eval_loss": 2.064781904220581, | |
| "eval_runtime": 55.3206, | |
| "eval_samples_per_second": 26.392, | |
| "eval_steps_per_second": 3.308, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.595386544245965e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |