| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.07216308858019123, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036081544290095615, | |
| "eval_loss": NaN, | |
| "eval_runtime": 196.169, | |
| "eval_samples_per_second": 23.796, | |
| "eval_steps_per_second": 5.949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036081544290095615, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007216308858019123, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010824463287028685, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014432617716038246, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018040772145047807, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02164892657405737, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.025257081003066933, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.028865235432076492, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.032473389861086055, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.036081544290095614, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.036081544290095614, | |
| "eval_loss": NaN, | |
| "eval_runtime": 197.2789, | |
| "eval_samples_per_second": 23.662, | |
| "eval_steps_per_second": 5.915, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03968969871910518, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04329785314811474, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0469060075771243, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.050514162006133866, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.054122316435143425, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.057730470864152984, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06133862529316255, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06494677972217211, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06855493415118168, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07216308858019123, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07216308858019123, | |
| "eval_loss": NaN, | |
| "eval_runtime": 197.0795, | |
| "eval_samples_per_second": 23.686, | |
| "eval_steps_per_second": 5.921, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.32707468181504e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |