| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.056657223796033995, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0056657223796034, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2059, | |
| "eval_samples_per_second": 9.194, | |
| "eval_steps_per_second": 2.345, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0169971671388102, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028328611898016998, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6293, | |
| "eval_samples_per_second": 9.533, | |
| "eval_steps_per_second": 2.431, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0339943342776204, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05099150141643059, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.056657223796033995, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6331, | |
| "eval_samples_per_second": 9.531, | |
| "eval_steps_per_second": 2.431, | |
| "step": 10 | |
| } | |
| ], | |
| "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": 1.306917209112576e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |