| { | |
| "best_metric": 1.1276743412017822, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.033818058843422386, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006763611768684477, | |
| "grad_norm": 2.2147772312164307, | |
| "learning_rate": 2e-05, | |
| "loss": 5.2324, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006763611768684477, | |
| "eval_loss": 1.3878569602966309, | |
| "eval_runtime": 62.9897, | |
| "eval_samples_per_second": 39.53, | |
| "eval_steps_per_second": 4.953, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013527223537368955, | |
| "grad_norm": 2.451791286468506, | |
| "learning_rate": 4e-05, | |
| "loss": 5.1105, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002029083530605343, | |
| "grad_norm": 2.511979818344116, | |
| "learning_rate": 6e-05, | |
| "loss": 5.0324, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002705444707473791, | |
| "grad_norm": 2.325338840484619, | |
| "learning_rate": 8e-05, | |
| "loss": 5.1899, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0033818058843422386, | |
| "grad_norm": 2.050114870071411, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6345, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004058167061210686, | |
| "grad_norm": 1.9211078882217407, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 4.8692, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0047345282380791345, | |
| "grad_norm": 2.3249716758728027, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 4.7556, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005410889414947582, | |
| "grad_norm": 2.0770318508148193, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 4.6042, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00608725059181603, | |
| "grad_norm": 1.7133581638336182, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 4.3367, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006763611768684477, | |
| "grad_norm": 1.731205940246582, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 4.7756, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0074399729455529254, | |
| "grad_norm": 1.5878700017929077, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 4.5015, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008116334122421373, | |
| "grad_norm": 1.7047429084777832, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 4.5289, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00879269529928982, | |
| "grad_norm": 1.6518176794052124, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 4.6674, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009469056476158269, | |
| "grad_norm": 1.6191649436950684, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 4.66, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010145417653026716, | |
| "grad_norm": 1.724644422531128, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 4.6459, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010821778829895164, | |
| "grad_norm": 1.6429541110992432, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 4.7986, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011498140006763611, | |
| "grad_norm": 1.6464076042175293, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 4.6725, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01217450118363206, | |
| "grad_norm": 1.6208781003952026, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 4.7407, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012850862360500507, | |
| "grad_norm": 1.601538062095642, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 4.6234, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013527223537368955, | |
| "grad_norm": 1.58771812915802, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.5835, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014203584714237404, | |
| "grad_norm": 1.5823163986206055, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 4.9363, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014879945891105851, | |
| "grad_norm": 1.507824182510376, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 4.5423, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015556307067974298, | |
| "grad_norm": 1.469377040863037, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.5491, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.016232668244842745, | |
| "grad_norm": 1.4575806856155396, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 4.5542, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016909029421711193, | |
| "grad_norm": 1.4958299398422241, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 4.6838, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016909029421711193, | |
| "eval_loss": 1.1481987237930298, | |
| "eval_runtime": 63.8055, | |
| "eval_samples_per_second": 39.025, | |
| "eval_steps_per_second": 4.89, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01758539059857964, | |
| "grad_norm": 1.4804654121398926, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 4.6336, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01826175177544809, | |
| "grad_norm": 1.5661972761154175, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 4.7698, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018938112952316538, | |
| "grad_norm": 1.5047603845596313, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 4.4571, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.019614474129184985, | |
| "grad_norm": 1.5553841590881348, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 4.4778, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.020290835306053433, | |
| "grad_norm": 1.5995780229568481, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 4.6735, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02096719648292188, | |
| "grad_norm": 1.5220364332199097, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 4.7163, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.021643557659790327, | |
| "grad_norm": 1.4890873432159424, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 4.2718, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.022319918836658775, | |
| "grad_norm": 1.648818016052246, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 4.6693, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022996280013527222, | |
| "grad_norm": 1.5415022373199463, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 4.3453, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.023672641190395673, | |
| "grad_norm": 1.60922372341156, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.606, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02434900236726412, | |
| "grad_norm": 1.661799430847168, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 4.7403, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.025025363544132567, | |
| "grad_norm": 1.6511698961257935, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 4.7336, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.025701724721001015, | |
| "grad_norm": 1.5974169969558716, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 4.6502, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.026378085897869462, | |
| "grad_norm": 1.7044310569763184, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 4.6695, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02705444707473791, | |
| "grad_norm": 1.5518771409988403, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 4.4624, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.027730808251606356, | |
| "grad_norm": 1.8471145629882812, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 4.6761, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.028407169428474807, | |
| "grad_norm": 1.697399377822876, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 4.5145, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.029083530605343254, | |
| "grad_norm": 1.636686086654663, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 4.4332, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.029759891782211702, | |
| "grad_norm": 1.6814813613891602, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 4.6082, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03043625295908015, | |
| "grad_norm": 1.770627498626709, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 4.5782, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.031112614135948596, | |
| "grad_norm": 1.9010318517684937, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 4.5493, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03178897531281705, | |
| "grad_norm": 1.9612586498260498, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 4.6045, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03246533648968549, | |
| "grad_norm": 1.9514307975769043, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 4.4648, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03314169766655394, | |
| "grad_norm": 2.2790310382843018, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 4.7822, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.033818058843422386, | |
| "grad_norm": 3.5149526596069336, | |
| "learning_rate": 0.0, | |
| "loss": 5.4604, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.033818058843422386, | |
| "eval_loss": 1.1276743412017822, | |
| "eval_runtime": 63.8973, | |
| "eval_samples_per_second": 38.969, | |
| "eval_steps_per_second": 4.883, | |
| "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": 1.935689084043264e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |