| { | |
| "best_metric": 0.09957851469516754, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.6015037593984962, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02406015037593985, | |
| "grad_norm": 1.3677129745483398, | |
| "learning_rate": 5e-05, | |
| "loss": 0.617, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02406015037593985, | |
| "eval_loss": 0.7637547254562378, | |
| "eval_runtime": 13.5686, | |
| "eval_samples_per_second": 20.636, | |
| "eval_steps_per_second": 2.579, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0481203007518797, | |
| "grad_norm": 1.44648277759552, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6564, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07218045112781955, | |
| "grad_norm": 1.387004017829895, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.6, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0962406015037594, | |
| "grad_norm": 0.9299198985099792, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.3271, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 0.6560674905776978, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1985, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1443609022556391, | |
| "grad_norm": 0.2988099753856659, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.1393, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 0.7401416897773743, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.1598, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1924812030075188, | |
| "grad_norm": 0.36938604712486267, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.121, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21654135338345865, | |
| "grad_norm": 0.22712348401546478, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1083, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.24060150375939848, | |
| "grad_norm": 0.4414423108100891, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1249, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2646616541353383, | |
| "grad_norm": 0.37042954564094543, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1205, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2887218045112782, | |
| "grad_norm": 0.10716293007135391, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1069, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.31278195488721805, | |
| "grad_norm": 0.17751727998256683, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1103, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 0.2624951899051666, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1109, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3609022556390977, | |
| "grad_norm": 0.18556217849254608, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1058, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3849624060150376, | |
| "grad_norm": 0.03690000995993614, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1023, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.40902255639097745, | |
| "grad_norm": 0.08423636853694916, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1017, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4330827067669173, | |
| "grad_norm": 0.24046602845191956, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1048, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.1586795449256897, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1007, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.48120300751879697, | |
| "grad_norm": 0.09818024188280106, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0983, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 0.09239000827074051, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0997, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5293233082706766, | |
| "grad_norm": 0.11240614205598831, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1022, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5533834586466165, | |
| "grad_norm": 0.10554036498069763, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1031, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5774436090225564, | |
| "grad_norm": 0.10103685408830643, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1021, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "grad_norm": 0.07299824804067612, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0998, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "eval_loss": 0.09957851469516754, | |
| "eval_runtime": 13.5326, | |
| "eval_samples_per_second": 20.691, | |
| "eval_steps_per_second": 2.586, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "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": 5.102844201926656e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |