| { | |
| "best_metric": 1.8889018297195435, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004609569466211856, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.219138932423711e-05, | |
| "grad_norm": 1.0880687236785889, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5748, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.219138932423711e-05, | |
| "eval_loss": 3.124889850616455, | |
| "eval_runtime": 696.4631, | |
| "eval_samples_per_second": 26.231, | |
| "eval_steps_per_second": 3.279, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018438277864847423, | |
| "grad_norm": 1.289193034172058, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6741, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00027657416797271134, | |
| "grad_norm": 1.3748584985733032, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7068, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00036876555729694845, | |
| "grad_norm": 1.3224939107894897, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6635, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00046095694662118557, | |
| "grad_norm": 1.1940001249313354, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5797, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005531483359454227, | |
| "grad_norm": 1.0044355392456055, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.5046, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006453397252696598, | |
| "grad_norm": 1.4259074926376343, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.6662, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007375311145938969, | |
| "grad_norm": 1.283603310585022, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.698, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008297225039181341, | |
| "grad_norm": 1.1590129137039185, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.6535, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009219138932423711, | |
| "grad_norm": 1.174027681350708, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.7426, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010141052825666083, | |
| "grad_norm": 1.0700634717941284, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6378, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0011062966718908454, | |
| "grad_norm": 1.1304829120635986, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.7699, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011984880612150824, | |
| "grad_norm": 1.523417353630066, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.8387, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0012906794505393197, | |
| "grad_norm": 1.4697535037994385, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.7118, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0013828708398635568, | |
| "grad_norm": 1.5495738983154297, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.7797, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014750622291877938, | |
| "grad_norm": 1.4719034433364868, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.7696, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0015672536185120309, | |
| "grad_norm": 1.6226401329040527, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.7056, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0016594450078362682, | |
| "grad_norm": 1.627495288848877, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.7557, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0017516363971605052, | |
| "grad_norm": 1.6702443361282349, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.6834, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0018438277864847423, | |
| "grad_norm": 1.5949941873550415, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.7226, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019360191758089795, | |
| "grad_norm": 1.4305518865585327, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.6224, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0020282105651332166, | |
| "grad_norm": 1.4910829067230225, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.6354, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0021204019544574537, | |
| "grad_norm": 1.780156135559082, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6865, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0022125933437816907, | |
| "grad_norm": 1.8739795684814453, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.8644, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002304784733105928, | |
| "grad_norm": 1.7289330959320068, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.9582, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002304784733105928, | |
| "eval_loss": 1.8889018297195435, | |
| "eval_runtime": 700.0167, | |
| "eval_samples_per_second": 26.098, | |
| "eval_steps_per_second": 3.263, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002396976122430165, | |
| "grad_norm": 1.6782158613204956, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.8472, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0024891675117544023, | |
| "grad_norm": 2.059053897857666, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.8412, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0025813589010786394, | |
| "grad_norm": 1.918933391571045, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.0778, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0026735502904028765, | |
| "grad_norm": 1.7663246393203735, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.7202, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0027657416797271135, | |
| "grad_norm": 2.2439804077148438, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.7479, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0028579330690513506, | |
| "grad_norm": 1.8399550914764404, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.8053, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0029501244583755876, | |
| "grad_norm": 1.9142265319824219, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.6902, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0030423158476998247, | |
| "grad_norm": 2.07477068901062, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 2.0066, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0031345072370240618, | |
| "grad_norm": 2.425363302230835, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.7472, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0032266986263482992, | |
| "grad_norm": 2.3599395751953125, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8948, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0033188900156725363, | |
| "grad_norm": 2.2230958938598633, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.7077, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0034110814049967734, | |
| "grad_norm": 2.254925489425659, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.8379, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0035032727943210104, | |
| "grad_norm": 2.3377599716186523, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.8644, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0035954641836452475, | |
| "grad_norm": 2.5051825046539307, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.2087, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0036876555729694845, | |
| "grad_norm": 2.2585108280181885, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.0316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0037798469622937216, | |
| "grad_norm": 2.4597954750061035, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.1561, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.003872038351617959, | |
| "grad_norm": 2.5078132152557373, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 2.0898, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003964229740942196, | |
| "grad_norm": 2.5703673362731934, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 2.0668, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.004056421130266433, | |
| "grad_norm": 2.4447693824768066, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.77, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.00414861251959067, | |
| "grad_norm": 2.7371108531951904, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.4302, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004240803908914907, | |
| "grad_norm": 2.6438939571380615, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.1652, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.004332995298239144, | |
| "grad_norm": 2.910571813583374, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.3887, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0044251866875633815, | |
| "grad_norm": 3.2206871509552, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.2811, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0045173780768876185, | |
| "grad_norm": 3.3698575496673584, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.4843, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.004609569466211856, | |
| "grad_norm": 4.109394073486328, | |
| "learning_rate": 0.0, | |
| "loss": 2.6098, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004609569466211856, | |
| "eval_loss": 1.9887616634368896, | |
| "eval_runtime": 700.7022, | |
| "eval_samples_per_second": 26.072, | |
| "eval_steps_per_second": 3.26, | |
| "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": 3.790140366598963e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |