| { | |
| "best_metric": 11.933917999267578, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0059228548160213225, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002961427408010661, | |
| "eval_loss": 11.934436798095703, | |
| "eval_runtime": 15.9653, | |
| "eval_samples_per_second": 89.068, | |
| "eval_steps_per_second": 44.534, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008884282224031983, | |
| "grad_norm": 0.046831801533699036, | |
| "learning_rate": 6e-05, | |
| "loss": 11.936, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014807137040053306, | |
| "eval_loss": 11.934361457824707, | |
| "eval_runtime": 15.9493, | |
| "eval_samples_per_second": 89.157, | |
| "eval_steps_per_second": 44.579, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017768564448063966, | |
| "grad_norm": 0.03125142306089401, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 11.9342, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002665284667209595, | |
| "grad_norm": 0.0406610444188118, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 11.9332, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0029614274080106613, | |
| "eval_loss": 11.934170722961426, | |
| "eval_runtime": 15.9818, | |
| "eval_samples_per_second": 88.976, | |
| "eval_steps_per_second": 44.488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0035537128896127933, | |
| "grad_norm": 0.05989011749625206, | |
| "learning_rate": 8.18711994874345e-05, | |
| "loss": 11.932, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004442141112015992, | |
| "grad_norm": 0.037861209362745285, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.9359, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004442141112015992, | |
| "eval_loss": 11.934015274047852, | |
| "eval_runtime": 16.0398, | |
| "eval_samples_per_second": 88.654, | |
| "eval_steps_per_second": 44.327, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00533056933441919, | |
| "grad_norm": 0.033359162509441376, | |
| "learning_rate": 4.6860474023534335e-05, | |
| "loss": 11.9323, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0059228548160213225, | |
| "eval_loss": 11.933917999267578, | |
| "eval_runtime": 15.97, | |
| "eval_samples_per_second": 89.042, | |
| "eval_steps_per_second": 44.521, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7494696960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |