| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.12345679012345678, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006172839506172839, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006172839506172839, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.308, | |
| "eval_samples_per_second": 8.305, | |
| "eval_steps_per_second": 4.213, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012345679012345678, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.030864197530864196, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.030864197530864196, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.5363, | |
| "eval_samples_per_second": 12.463, | |
| "eval_steps_per_second": 6.322, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.043209876543209874, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04938271604938271, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06172839506172839, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06172839506172839, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.0922, | |
| "eval_samples_per_second": 11.326, | |
| "eval_steps_per_second": 5.745, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06790123456790123, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08024691358024691, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08641975308641975, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2785, | |
| "eval_samples_per_second": 13.072, | |
| "eval_steps_per_second": 6.631, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09876543209876543, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10493827160493827, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11728395061728394, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12345679012345678, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12345679012345678, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.7736, | |
| "eval_samples_per_second": 11.951, | |
| "eval_steps_per_second": 6.062, | |
| "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": 156783555379200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |