| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.007276696379843551, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036383481899217757, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00036383481899217757, | |
| "eval_loss": NaN, | |
| "eval_runtime": 152.6143, | |
| "eval_samples_per_second": 15.169, | |
| "eval_steps_per_second": 3.794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007276696379843551, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010915044569765327, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014553392759687103, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018191740949608877, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0018191740949608877, | |
| "eval_loss": NaN, | |
| "eval_runtime": 151.8408, | |
| "eval_samples_per_second": 15.246, | |
| "eval_steps_per_second": 3.813, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0021830089139530653, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025468437329452427, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0029106785519374206, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003274513370929598, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0036383481899217754, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0036383481899217754, | |
| "eval_loss": NaN, | |
| "eval_runtime": 150.9627, | |
| "eval_samples_per_second": 15.335, | |
| "eval_steps_per_second": 3.835, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004002183008913953, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004366017827906131, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004729852646898308, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005093687465890485, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005457522284882663, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005457522284882663, | |
| "eval_loss": NaN, | |
| "eval_runtime": 151.8582, | |
| "eval_samples_per_second": 15.244, | |
| "eval_steps_per_second": 3.813, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005821357103874841, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0061851919228670185, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006549026741859196, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006912861560851373, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007276696379843551, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007276696379843551, | |
| "eval_loss": NaN, | |
| "eval_runtime": 153.6267, | |
| "eval_samples_per_second": 15.069, | |
| "eval_steps_per_second": 3.769, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 3492686082342912.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |