| { | |
| "best_metric": 10.378403663635254, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.10077519379845, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12403100775193798, | |
| "grad_norm": 0.05614614114165306, | |
| "learning_rate": 5e-05, | |
| "loss": 10.38, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "eval_loss": 10.383469581604004, | |
| "eval_runtime": 0.113, | |
| "eval_samples_per_second": 442.656, | |
| "eval_steps_per_second": 115.09, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "grad_norm": 0.06705408543348312, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3793, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 0.054651375859975815, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 10.3809, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.49612403100775193, | |
| "grad_norm": 0.06632470339536667, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 10.3814, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 0.05889716371893883, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 10.38, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 0.06317402422428131, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 10.3798, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.8682170542635659, | |
| "grad_norm": 0.06561880558729172, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 10.3779, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.9922480620155039, | |
| "grad_norm": 0.0650755763053894, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 10.3792, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.1162790697674418, | |
| "grad_norm": 0.1412653625011444, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 20.3287, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.2403100775193798, | |
| "grad_norm": 0.0744536966085434, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 10.5229, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.3643410852713178, | |
| "grad_norm": 0.05811828747391701, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 10.1871, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.4883720930232558, | |
| "grad_norm": 0.0669311136007309, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 10.5987, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.6124031007751938, | |
| "grad_norm": 0.05932833254337311, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 10.1312, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.7364341085271318, | |
| "grad_norm": 0.07433593273162842, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 10.6396, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "grad_norm": 0.06283493340015411, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 10.0935, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.9844961240310077, | |
| "grad_norm": 0.08435866236686707, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 10.6605, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.108527131782946, | |
| "grad_norm": 0.11522483825683594, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 20.0329, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.2325581395348837, | |
| "grad_norm": 0.07771603018045425, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 10.815, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.356589147286822, | |
| "grad_norm": 0.0636923760175705, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 9.9169, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.4806201550387597, | |
| "grad_norm": 0.08208873122930527, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 10.7926, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.604651162790698, | |
| "grad_norm": 0.05890968441963196, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 9.9517, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.7286821705426356, | |
| "grad_norm": 0.07637836039066315, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 10.8172, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.8527131782945734, | |
| "grad_norm": 0.06362668424844742, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 9.905, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.9767441860465116, | |
| "grad_norm": 0.09150923788547516, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 10.8011, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.10077519379845, | |
| "grad_norm": 0.1131504476070404, | |
| "learning_rate": 1e-05, | |
| "loss": 19.8521, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.10077519379845, | |
| "eval_loss": 10.378403663635254, | |
| "eval_runtime": 0.102, | |
| "eval_samples_per_second": 490.382, | |
| "eval_steps_per_second": 127.499, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 21384029798400.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |