| { | |
| "best_metric": 0.1227470338344574, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2242152466367713, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008968609865470852, | |
| "grad_norm": 15.662577629089355, | |
| "learning_rate": 5e-05, | |
| "loss": 9.3044, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008968609865470852, | |
| "eval_loss": 11.164280891418457, | |
| "eval_runtime": 4.3168, | |
| "eval_samples_per_second": 11.583, | |
| "eval_steps_per_second": 11.583, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017937219730941704, | |
| "grad_norm": 17.07288932800293, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1086, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026905829596412557, | |
| "grad_norm": 16.965513229370117, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 10.4629, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03587443946188341, | |
| "grad_norm": 25.09530258178711, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 8.309, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04484304932735426, | |
| "grad_norm": 31.852909088134766, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 6.2766, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.053811659192825115, | |
| "grad_norm": 27.327693939208984, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 3.9231, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06278026905829596, | |
| "grad_norm": 24.009668350219727, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 2.4886, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07174887892376682, | |
| "grad_norm": 16.70871353149414, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 1.8758, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08071748878923767, | |
| "grad_norm": 11.27795124053955, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 1.1078, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08968609865470852, | |
| "grad_norm": 11.163119316101074, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.8591, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09865470852017937, | |
| "grad_norm": 6.685216903686523, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.5124, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10762331838565023, | |
| "grad_norm": 6.182336330413818, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.4017, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11659192825112108, | |
| "grad_norm": 5.339712142944336, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.4113, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12556053811659193, | |
| "grad_norm": 10.080835342407227, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.6407, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13452914798206278, | |
| "grad_norm": 6.769567966461182, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.3512, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14349775784753363, | |
| "grad_norm": 4.424293518066406, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.2014, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15246636771300448, | |
| "grad_norm": 5.910513401031494, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.2151, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16143497757847533, | |
| "grad_norm": 3.2448790073394775, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.1428, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17040358744394618, | |
| "grad_norm": 3.8938536643981934, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.2134, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17937219730941703, | |
| "grad_norm": 2.9493601322174072, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.1612, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18834080717488788, | |
| "grad_norm": 8.059837341308594, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.1843, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19730941704035873, | |
| "grad_norm": 5.056806564331055, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.1656, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2062780269058296, | |
| "grad_norm": 6.305684566497803, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.1435, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21524663677130046, | |
| "grad_norm": 4.7027435302734375, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.1485, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2242152466367713, | |
| "grad_norm": 3.6922459602355957, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1174, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2242152466367713, | |
| "eval_loss": 0.1227470338344574, | |
| "eval_runtime": 4.3458, | |
| "eval_samples_per_second": 11.505, | |
| "eval_steps_per_second": 11.505, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 1.32442044235776e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |