| { | |
| "best_metric": 10.346579551696777, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06289308176100629, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012578616352201257, | |
| "grad_norm": 0.0676870122551918, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3781, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012578616352201257, | |
| "eval_loss": 10.373727798461914, | |
| "eval_runtime": 2.8214, | |
| "eval_samples_per_second": 474.581, | |
| "eval_steps_per_second": 118.734, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025157232704402514, | |
| "grad_norm": 0.053749579936265945, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3781, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0037735849056603774, | |
| "grad_norm": 0.05700600892305374, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005031446540880503, | |
| "grad_norm": 0.05451948195695877, | |
| "learning_rate": 4e-05, | |
| "loss": 10.376, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006289308176100629, | |
| "grad_norm": 0.05333434417843819, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007547169811320755, | |
| "grad_norm": 0.053336936980485916, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3776, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00880503144654088, | |
| "grad_norm": 0.050664711743593216, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3781, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010062893081761006, | |
| "grad_norm": 0.053908322006464005, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3772, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011320754716981131, | |
| "grad_norm": 0.05347241088747978, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3755, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012578616352201259, | |
| "grad_norm": 0.06627130508422852, | |
| "learning_rate": 0.0001, | |
| "loss": 10.376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013836477987421384, | |
| "grad_norm": 0.0658232793211937, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 10.3757, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01509433962264151, | |
| "grad_norm": 0.07336028665304184, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 10.3731, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016352201257861635, | |
| "grad_norm": 0.07335679978132248, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 10.3721, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01761006289308176, | |
| "grad_norm": 0.07778532058000565, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 10.3727, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018867924528301886, | |
| "grad_norm": 0.08464192599058151, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 10.3715, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02012578616352201, | |
| "grad_norm": 0.07666515558958054, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 10.3705, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021383647798742137, | |
| "grad_norm": 0.08507933467626572, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 10.3713, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.022641509433962263, | |
| "grad_norm": 0.08501887321472168, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 10.3707, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02389937106918239, | |
| "grad_norm": 0.09447915107011795, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 10.3723, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025157232704402517, | |
| "grad_norm": 0.09398620575666428, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 10.3687, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026415094339622643, | |
| "grad_norm": 0.10066643357276917, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 10.3696, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027672955974842768, | |
| "grad_norm": 0.10919738560914993, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 10.3668, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.028930817610062894, | |
| "grad_norm": 0.12229104340076447, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 10.3678, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03018867924528302, | |
| "grad_norm": 0.11512572318315506, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 10.3675, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031446540880503145, | |
| "grad_norm": 0.1288090944290161, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 10.3658, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03270440251572327, | |
| "grad_norm": 0.1288468837738037, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 10.3638, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.033962264150943396, | |
| "grad_norm": 0.15287871658802032, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 10.3627, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03522012578616352, | |
| "grad_norm": 0.14995208382606506, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 10.3658, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03647798742138365, | |
| "grad_norm": 0.16352064907550812, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.363, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03773584905660377, | |
| "grad_norm": 0.1616298109292984, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 10.362, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0389937106918239, | |
| "grad_norm": 0.18207941949367523, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 10.3582, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04025157232704402, | |
| "grad_norm": 0.17258626222610474, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 10.3591, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04150943396226415, | |
| "grad_norm": 0.1723157912492752, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 10.3575, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.042767295597484274, | |
| "grad_norm": 0.1635301411151886, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 10.3578, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0440251572327044, | |
| "grad_norm": 0.18812069296836853, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 10.3569, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.045283018867924525, | |
| "grad_norm": 0.17699386179447174, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 10.3525, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04654088050314465, | |
| "grad_norm": 0.17810064554214478, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 10.3524, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04779874213836478, | |
| "grad_norm": 0.1659187227487564, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 10.3481, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04905660377358491, | |
| "grad_norm": 0.15193907916545868, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 10.3503, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.050314465408805034, | |
| "grad_norm": 0.16581708192825317, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 10.3489, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05157232704402516, | |
| "grad_norm": 0.14731748402118683, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 10.3484, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.052830188679245285, | |
| "grad_norm": 0.12889303267002106, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 10.3448, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05408805031446541, | |
| "grad_norm": 0.14560353755950928, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 10.3448, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.055345911949685536, | |
| "grad_norm": 0.12265373766422272, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 10.3433, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05660377358490566, | |
| "grad_norm": 0.13917139172554016, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 10.34, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05786163522012579, | |
| "grad_norm": 0.10753589868545532, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 10.3415, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05911949685534591, | |
| "grad_norm": 0.0811968594789505, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 10.3417, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06037735849056604, | |
| "grad_norm": 0.11372454464435577, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3455, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.061635220125786164, | |
| "grad_norm": 0.1224861592054367, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 10.3371, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06289308176100629, | |
| "grad_norm": 0.15765050053596497, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 10.3347, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06289308176100629, | |
| "eval_loss": 10.346579551696777, | |
| "eval_runtime": 2.8076, | |
| "eval_samples_per_second": 476.923, | |
| "eval_steps_per_second": 119.32, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 5605420695552.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |