| { | |
| "best_metric": 0.683539867401123, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05995203836930456, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002398081534772182, | |
| "grad_norm": 0.30095940828323364, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.8193, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002398081534772182, | |
| "eval_loss": 0.7507125735282898, | |
| "eval_runtime": 0.7441, | |
| "eval_samples_per_second": 67.196, | |
| "eval_steps_per_second": 17.471, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004796163069544364, | |
| "grad_norm": 0.3760162591934204, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.7795, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007194244604316547, | |
| "grad_norm": 0.39668312668800354, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8522, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009592326139088728, | |
| "grad_norm": 0.3185388743877411, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 0.8081, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011990407673860911, | |
| "grad_norm": 0.34676116704940796, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 0.76, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014388489208633094, | |
| "grad_norm": 0.3574373722076416, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 0.7665, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016786570743405275, | |
| "grad_norm": 0.33820533752441406, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.7747, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019184652278177457, | |
| "grad_norm": 0.33398616313934326, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 0.7295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02158273381294964, | |
| "grad_norm": 0.34293198585510254, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 0.7783, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023980815347721823, | |
| "grad_norm": 0.33424755930900574, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 0.6896, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026378896882494004, | |
| "grad_norm": 0.3323270082473755, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.6557, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02877697841726619, | |
| "grad_norm": 0.37142112851142883, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 0.733, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03117505995203837, | |
| "grad_norm": 0.2586774528026581, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 0.7245, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03357314148681055, | |
| "grad_norm": 0.23137016594409943, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 0.8023, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03597122302158273, | |
| "grad_norm": 0.2453051507472992, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.8549, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03836930455635491, | |
| "grad_norm": 0.2271958887577057, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.7908, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0407673860911271, | |
| "grad_norm": 0.23564989864826202, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.8116, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04316546762589928, | |
| "grad_norm": 0.24254751205444336, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.8145, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.045563549160671464, | |
| "grad_norm": 0.23949633538722992, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.7682, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.047961630695443645, | |
| "grad_norm": 0.26809075474739075, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 0.7718, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.050359712230215826, | |
| "grad_norm": 0.282449334859848, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.76, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05275779376498801, | |
| "grad_norm": 0.27863359451293945, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 0.6711, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05515587529976019, | |
| "grad_norm": 0.2779116630554199, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.7516, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05755395683453238, | |
| "grad_norm": 0.28714075684547424, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.6643, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05995203836930456, | |
| "grad_norm": 0.33895036578178406, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.7124, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05995203836930456, | |
| "eval_loss": 0.683539867401123, | |
| "eval_runtime": 0.7562, | |
| "eval_samples_per_second": 66.123, | |
| "eval_steps_per_second": 17.192, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.476965970214912e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |