| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.0011886013134044513, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.943006567022257e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.943006567022257e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1000.9121, | |
| "eval_samples_per_second": 7.079, | |
| "eval_steps_per_second": 3.54, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011886013134044514, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001782901970106677, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023772026268089027, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 18.462, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00029715032835111283, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5762, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00029715032835111283, | |
| "eval_loss": NaN, | |
| "eval_runtime": 982.1092, | |
| "eval_samples_per_second": 7.214, | |
| "eval_steps_per_second": 3.608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003565803940213354, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00041601045969155795, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00047544052536178054, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005348705910320031, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005943006567022257, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005943006567022257, | |
| "eval_loss": NaN, | |
| "eval_runtime": 992.0263, | |
| "eval_samples_per_second": 7.142, | |
| "eval_steps_per_second": 3.571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006537307223724483, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0007131607880426708, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 46.1278, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007725908537128933, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0008320209193831159, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0008914509850533385, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008914509850533385, | |
| "eval_loss": NaN, | |
| "eval_runtime": 996.6228, | |
| "eval_samples_per_second": 7.109, | |
| "eval_steps_per_second": 3.555, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009508810507235611, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010103111163937836, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0010697411820640062, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0011291712477342287, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0011886013134044513, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011886013134044513, | |
| "eval_loss": NaN, | |
| "eval_runtime": 998.9441, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 3.547, | |
| "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": 5305639202979840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |