| { | |
| "best_metric": 0.8787677884101868, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.16877637130801687, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0033755274261603376, | |
| "grad_norm": 4.169283390045166, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6278, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033755274261603376, | |
| "eval_loss": 1.606489658355713, | |
| "eval_runtime": 16.5982, | |
| "eval_samples_per_second": 30.063, | |
| "eval_steps_per_second": 3.796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006751054852320675, | |
| "grad_norm": 4.4363322257995605, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6154, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010126582278481013, | |
| "grad_norm": 3.6695597171783447, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4751, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01350210970464135, | |
| "grad_norm": 1.6475915908813477, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2909, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016877637130801686, | |
| "grad_norm": 1.360341191291809, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2384, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020253164556962026, | |
| "grad_norm": 1.5259308815002441, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.1394, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02362869198312236, | |
| "grad_norm": 1.1091194152832031, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.0784, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0270042194092827, | |
| "grad_norm": 0.7985029816627502, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.0213, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.030379746835443037, | |
| "grad_norm": 0.7641896605491638, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.9896, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03375527426160337, | |
| "grad_norm": 0.7662172317504883, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.0089, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03713080168776371, | |
| "grad_norm": 0.7473912835121155, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.0172, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04050632911392405, | |
| "grad_norm": 0.6838369965553284, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.9845, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04388185654008439, | |
| "grad_norm": 0.6678991913795471, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.9658, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04725738396624472, | |
| "grad_norm": 0.6504063606262207, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.9731, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05063291139240506, | |
| "grad_norm": 0.6322726011276245, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.9777, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0540084388185654, | |
| "grad_norm": 0.5897281169891357, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.9138, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05738396624472574, | |
| "grad_norm": 0.6413071155548096, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.8757, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.060759493670886074, | |
| "grad_norm": 0.5967020988464355, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.9405, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06413502109704641, | |
| "grad_norm": 0.5878992080688477, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.9215, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06751054852320675, | |
| "grad_norm": 0.596689760684967, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.918, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07088607594936709, | |
| "grad_norm": 0.7080620527267456, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.9025, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07426160337552742, | |
| "grad_norm": 0.6239933967590332, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.9832, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07763713080168777, | |
| "grad_norm": 0.6565373539924622, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.8988, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0810126582278481, | |
| "grad_norm": 0.6067308187484741, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.8713, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08438818565400844, | |
| "grad_norm": 0.6106895804405212, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.9113, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08438818565400844, | |
| "eval_loss": 0.9000408053398132, | |
| "eval_runtime": 16.7707, | |
| "eval_samples_per_second": 29.754, | |
| "eval_steps_per_second": 3.757, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08776371308016878, | |
| "grad_norm": 0.6180962324142456, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.9031, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09113924050632911, | |
| "grad_norm": 0.5998266935348511, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.9706, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09451476793248945, | |
| "grad_norm": 0.5918096899986267, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.8448, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09789029535864979, | |
| "grad_norm": 0.5581284761428833, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.8772, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 0.5750042796134949, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.8812, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10464135021097046, | |
| "grad_norm": 0.5918043851852417, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.8839, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1080168776371308, | |
| "grad_norm": 0.589953601360321, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.8633, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11139240506329114, | |
| "grad_norm": 0.6130343079566956, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.9368, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11476793248945148, | |
| "grad_norm": 0.5803126096725464, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.8662, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11814345991561181, | |
| "grad_norm": 0.5708263516426086, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8669, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12151898734177215, | |
| "grad_norm": 0.578863263130188, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.8797, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1248945147679325, | |
| "grad_norm": 0.5792142748832703, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.8665, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12827004219409283, | |
| "grad_norm": 0.6031744480133057, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.895, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13164556962025317, | |
| "grad_norm": 0.6153518557548523, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.911, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1350210970464135, | |
| "grad_norm": 0.6126015186309814, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.8387, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13839662447257384, | |
| "grad_norm": 0.5898735523223877, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.8764, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14177215189873418, | |
| "grad_norm": 0.5841656923294067, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.86, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1451476793248945, | |
| "grad_norm": 0.6128556728363037, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.8682, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14852320675105485, | |
| "grad_norm": 0.6161452531814575, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.8521, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1518987341772152, | |
| "grad_norm": 0.6541045308113098, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.8808, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15527426160337554, | |
| "grad_norm": 0.6270753741264343, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.9077, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15864978902953586, | |
| "grad_norm": 0.6266160607337952, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.8956, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1620253164556962, | |
| "grad_norm": 0.6659855246543884, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.9096, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16540084388185655, | |
| "grad_norm": 0.6978780031204224, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.9074, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16877637130801687, | |
| "grad_norm": 0.8016338348388672, | |
| "learning_rate": 0.0, | |
| "loss": 0.9513, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16877637130801687, | |
| "eval_loss": 0.8787677884101868, | |
| "eval_runtime": 16.923, | |
| "eval_samples_per_second": 29.486, | |
| "eval_steps_per_second": 3.723, | |
| "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": 1.9646261602811904e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |