| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.0007543896045112498, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.771948022556249e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.771948022556249e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1608.1304, | |
| "eval_samples_per_second": 6.942, | |
| "eval_steps_per_second": 3.471, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.543896045112498e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00011315844067668747, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015087792090224996, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00018859740112781245, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018859740112781245, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1606.9994, | |
| "eval_samples_per_second": 6.946, | |
| "eval_steps_per_second": 3.474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00022631688135337495, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00026403636157893746, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003017558418044999, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00033947532203006245, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003771948022556249, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003771948022556249, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1605.0223, | |
| "eval_samples_per_second": 6.955, | |
| "eval_steps_per_second": 3.478, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004149142824811874, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0004526337627067499, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004903532429323124, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005280727231578749, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005657922033834373, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0511, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005657922033834373, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1604.2886, | |
| "eval_samples_per_second": 6.958, | |
| "eval_steps_per_second": 3.479, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006035116836089999, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006412311638345624, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0006789506440601249, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007166701242856873, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0007543896045112498, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007543896045112498, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1607.3765, | |
| "eval_samples_per_second": 6.945, | |
| "eval_steps_per_second": 3.473, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6380996656103424.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |