| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.029006526468455404, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014503263234227702, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014503263234227702, | |
| "eval_loss": NaN, | |
| "eval_runtime": 42.4095, | |
| "eval_samples_per_second": 6.862, | |
| "eval_steps_per_second": 3.443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029006526468455403, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00435097897026831, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9988, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005801305293691081, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3567, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007251631617113851, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007251631617113851, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.7604, | |
| "eval_samples_per_second": 7.139, | |
| "eval_steps_per_second": 3.582, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00870195794053662, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01015228426395939, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011602610587382161, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01305293691080493, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014503263234227702, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014503263234227702, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.8844, | |
| "eval_samples_per_second": 7.118, | |
| "eval_steps_per_second": 3.571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01595358955765047, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01740391588107324, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01885424220449601, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02030456852791878, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.021754894851341553, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021754894851341553, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.8772, | |
| "eval_samples_per_second": 7.119, | |
| "eval_steps_per_second": 3.572, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023205221174764323, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.024655547498187092, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02610587382160986, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02755620014503263, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.029006526468455404, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029006526468455404, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.6277, | |
| "eval_samples_per_second": 7.163, | |
| "eval_steps_per_second": 3.594, | |
| "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": 5038925634600960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |