| { | |
| "best_metric": 0.0873224139213562, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3629764065335753, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007259528130671506, | |
| "grad_norm": 13.348132133483887, | |
| "learning_rate": 2e-05, | |
| "loss": 7.1805, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007259528130671506, | |
| "eval_loss": 1.927117109298706, | |
| "eval_runtime": 14.3372, | |
| "eval_samples_per_second": 16.182, | |
| "eval_steps_per_second": 2.023, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014519056261343012, | |
| "grad_norm": 11.873133659362793, | |
| "learning_rate": 4e-05, | |
| "loss": 7.3831, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.021778584392014518, | |
| "grad_norm": 13.255901336669922, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9679, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.029038112522686024, | |
| "grad_norm": 10.808575630187988, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3027, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.036297640653357534, | |
| "grad_norm": 9.005926132202148, | |
| "learning_rate": 0.0001, | |
| "loss": 6.5192, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.043557168784029036, | |
| "grad_norm": 42.671695709228516, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 4.1781, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.050816696914700546, | |
| "grad_norm": 21.43427848815918, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.1873, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05807622504537205, | |
| "grad_norm": 18.199893951416016, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.0368, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06533575317604355, | |
| "grad_norm": 16.338024139404297, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.9834, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "grad_norm": 27.13408851623535, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.8154, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07985480943738657, | |
| "grad_norm": 12.415433883666992, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.2718, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08711433756805807, | |
| "grad_norm": 7.741391658782959, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.2994, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09437386569872959, | |
| "grad_norm": 3.1558408737182617, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.1884, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10163339382940109, | |
| "grad_norm": 7.3041605949401855, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.6406, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1088929219600726, | |
| "grad_norm": 8.467690467834473, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.7019, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1161524500907441, | |
| "grad_norm": 12.13959789276123, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 4.2175, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12341197822141561, | |
| "grad_norm": 11.324997901916504, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 4.0096, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1306715063520871, | |
| "grad_norm": 12.869543075561523, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 3.7815, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 13.819911003112793, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 4.1328, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14519056261343014, | |
| "grad_norm": 14.06855297088623, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.6461, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15245009074410162, | |
| "grad_norm": 14.941818237304688, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 3.3731, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15970961887477314, | |
| "grad_norm": 16.980831146240234, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 3.1651, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16696914700544466, | |
| "grad_norm": 20.803871154785156, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.4116, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.17422867513611615, | |
| "grad_norm": 15.249065399169922, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.7271, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18148820326678766, | |
| "grad_norm": 13.850008964538574, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.4501, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18148820326678766, | |
| "eval_loss": 0.2671048045158386, | |
| "eval_runtime": 14.3913, | |
| "eval_samples_per_second": 16.121, | |
| "eval_steps_per_second": 2.015, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18874773139745918, | |
| "grad_norm": 12.08178997039795, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.8011, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.19600725952813067, | |
| "grad_norm": 6.6806440353393555, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.6513, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.20326678765880218, | |
| "grad_norm": 5.073172092437744, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.3096, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 9.08521842956543, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.8236, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2177858439201452, | |
| "grad_norm": 8.419458389282227, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.7502, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2250453720508167, | |
| "grad_norm": 13.598421096801758, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.3274, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2323049001814882, | |
| "grad_norm": 17.529741287231445, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.9063, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2395644283121597, | |
| "grad_norm": 22.427534103393555, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.4676, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.24682395644283123, | |
| "grad_norm": 11.120813369750977, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.2306, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2540834845735027, | |
| "grad_norm": 66.51551818847656, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.1779, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2613430127041742, | |
| "grad_norm": 25.5261287689209, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.3193, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.26860254083484575, | |
| "grad_norm": 17.919849395751953, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.2592, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 19.765296936035156, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.2518, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2831215970961887, | |
| "grad_norm": 18.46579933166504, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8273, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.29038112522686027, | |
| "grad_norm": 15.463048934936523, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.4909, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29764065335753176, | |
| "grad_norm": 5.132680416107178, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.359, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.30490018148820325, | |
| "grad_norm": 3.2728233337402344, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.2565, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3121597096188748, | |
| "grad_norm": 3.4045944213867188, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.1952, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3194192377495463, | |
| "grad_norm": 8.596439361572266, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.7799, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.32667876588021777, | |
| "grad_norm": 4.2560038566589355, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.2737, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3339382940108893, | |
| "grad_norm": 3.327805757522583, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.238, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3411978221415608, | |
| "grad_norm": 4.551213264465332, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.3053, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3484573502722323, | |
| "grad_norm": 3.6048531532287598, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.2353, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.35571687840290384, | |
| "grad_norm": 4.764666557312012, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.3829, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3629764065335753, | |
| "grad_norm": 5.7592291831970215, | |
| "learning_rate": 0.0, | |
| "loss": 0.3659, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3629764065335753, | |
| "eval_loss": 0.0873224139213562, | |
| "eval_runtime": 14.3869, | |
| "eval_samples_per_second": 16.126, | |
| "eval_steps_per_second": 2.016, | |
| "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": 6.352798148984832e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |