| { | |
| "best_metric": 0.6068727970123291, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.023154848046309694, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011577424023154848, | |
| "grad_norm": 2.1934049129486084, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7474, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011577424023154848, | |
| "eval_loss": 1.5985236167907715, | |
| "eval_runtime": 52.0973, | |
| "eval_samples_per_second": 6.987, | |
| "eval_steps_per_second": 3.493, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023154848046309695, | |
| "grad_norm": 1.5156337022781372, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6254, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0034732272069464545, | |
| "grad_norm": 1.7799040079116821, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8249, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004630969609261939, | |
| "grad_norm": 1.9472581148147583, | |
| "learning_rate": 8e-05, | |
| "loss": 1.4935, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005788712011577424, | |
| "grad_norm": 2.1162898540496826, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6432, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005788712011577424, | |
| "eval_loss": 1.465311050415039, | |
| "eval_runtime": 51.5111, | |
| "eval_samples_per_second": 7.066, | |
| "eval_steps_per_second": 3.533, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006946454413892909, | |
| "grad_norm": 2.089428186416626, | |
| "learning_rate": 0.00012, | |
| "loss": 1.652, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008104196816208394, | |
| "grad_norm": 1.7722697257995605, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2282, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009261939218523878, | |
| "grad_norm": 1.4467377662658691, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2071, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010419681620839363, | |
| "grad_norm": 1.5139964818954468, | |
| "learning_rate": 0.00018, | |
| "loss": 1.202, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011577424023154847, | |
| "grad_norm": 1.4692848920822144, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9872, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011577424023154847, | |
| "eval_loss": 0.8958241939544678, | |
| "eval_runtime": 53.5236, | |
| "eval_samples_per_second": 6.801, | |
| "eval_steps_per_second": 3.4, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012735166425470333, | |
| "grad_norm": 1.6015220880508423, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.9102, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013892908827785818, | |
| "grad_norm": 1.4771215915679932, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.1241, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015050651230101303, | |
| "grad_norm": 1.1894761323928833, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.6946, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016208393632416787, | |
| "grad_norm": 1.073376178741455, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.6839, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017366136034732273, | |
| "grad_norm": 1.1312061548233032, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.7637, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017366136034732273, | |
| "eval_loss": 0.6495120525360107, | |
| "eval_runtime": 52.2238, | |
| "eval_samples_per_second": 6.97, | |
| "eval_steps_per_second": 3.485, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018523878437047756, | |
| "grad_norm": 1.0004829168319702, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.715, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019681620839363242, | |
| "grad_norm": 1.0702334642410278, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.712, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020839363241678725, | |
| "grad_norm": 0.9818086624145508, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.7343, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02199710564399421, | |
| "grad_norm": 0.9808053970336914, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.6963, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023154848046309694, | |
| "grad_norm": 1.1419761180877686, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.7567, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023154848046309694, | |
| "eval_loss": 0.6068727970123291, | |
| "eval_runtime": 52.5074, | |
| "eval_samples_per_second": 6.932, | |
| "eval_steps_per_second": 3.466, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |