| { | |
| "best_metric": 1.1465318202972412, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.22857142857142856, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004571428571428572, | |
| "grad_norm": 0.12384573370218277, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7389, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004571428571428572, | |
| "eval_loss": 1.362682580947876, | |
| "eval_runtime": 40.2981, | |
| "eval_samples_per_second": 9.157, | |
| "eval_steps_per_second": 2.308, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009142857142857144, | |
| "grad_norm": 0.1931685507297516, | |
| "learning_rate": 2e-05, | |
| "loss": 1.263, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013714285714285714, | |
| "grad_norm": 0.24555817246437073, | |
| "learning_rate": 3e-05, | |
| "loss": 1.546, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018285714285714287, | |
| "grad_norm": 0.20846664905548096, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4432, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022857142857142857, | |
| "grad_norm": 0.21662656962871552, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4057, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027428571428571427, | |
| "grad_norm": 0.22502146661281586, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4752, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.2199072688817978, | |
| "learning_rate": 7e-05, | |
| "loss": 1.5484, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.036571428571428574, | |
| "grad_norm": 0.2088400423526764, | |
| "learning_rate": 8e-05, | |
| "loss": 1.376, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04114285714285714, | |
| "grad_norm": 0.1994723379611969, | |
| "learning_rate": 9e-05, | |
| "loss": 1.4309, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.045714285714285714, | |
| "grad_norm": 0.17029602825641632, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5372, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05028571428571429, | |
| "grad_norm": 0.17547327280044556, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.3906, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.054857142857142854, | |
| "grad_norm": 0.16624683141708374, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.3834, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05942857142857143, | |
| "grad_norm": 0.20969858765602112, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.4273, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 0.20921021699905396, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.4157, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06857142857142857, | |
| "grad_norm": 0.19582298398017883, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.388, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07314285714285715, | |
| "grad_norm": 0.2045115977525711, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.2916, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07771428571428571, | |
| "grad_norm": 0.17086480557918549, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.3656, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08228571428571428, | |
| "grad_norm": 0.15559332072734833, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.3276, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08685714285714285, | |
| "grad_norm": 0.14628355205059052, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.1483, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09142857142857143, | |
| "grad_norm": 0.14557524025440216, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.2162, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.1672665923833847, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.1963, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10057142857142858, | |
| "grad_norm": 0.13945060968399048, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.2472, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10514285714285715, | |
| "grad_norm": 0.13727137446403503, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.0866, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10971428571428571, | |
| "grad_norm": 0.1319202333688736, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.1846, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 0.13479618728160858, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.1505, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11885714285714286, | |
| "grad_norm": 0.12670767307281494, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.2476, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12342857142857143, | |
| "grad_norm": 0.15373919904232025, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.1967, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.15247727930545807, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.9893, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13257142857142856, | |
| "grad_norm": 0.1301872432231903, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.2281, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13714285714285715, | |
| "grad_norm": 0.12188567966222763, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.1287, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1417142857142857, | |
| "grad_norm": 0.1177821233868599, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.19, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1462857142857143, | |
| "grad_norm": 0.12030963599681854, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.2389, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.15085714285714286, | |
| "grad_norm": 0.12400416284799576, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.272, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15542857142857142, | |
| "grad_norm": 0.13301657140254974, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.2809, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.14115765690803528, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.2218, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16457142857142856, | |
| "grad_norm": 0.12093055248260498, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.115, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16914285714285715, | |
| "grad_norm": 0.12792570888996124, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.1204, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1737142857142857, | |
| "grad_norm": 0.1883489042520523, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.3103, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1782857142857143, | |
| "grad_norm": 0.14241398870944977, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.1938, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "grad_norm": 0.1636561155319214, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.1379, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18742857142857142, | |
| "grad_norm": 0.17105966806411743, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.1285, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.17147573828697205, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.09, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19657142857142856, | |
| "grad_norm": 0.18589459359645844, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.0317, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.20114285714285715, | |
| "grad_norm": 0.1729321926832199, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.8933, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2057142857142857, | |
| "grad_norm": 0.22401976585388184, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.8621, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2102857142857143, | |
| "grad_norm": 0.29440781474113464, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.8579, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21485714285714286, | |
| "grad_norm": 0.5384777188301086, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.6747, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21942857142857142, | |
| "grad_norm": 0.7473423480987549, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.5015, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.5895587801933289, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.4012, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.7679787278175354, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.4151, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "eval_loss": 1.1465318202972412, | |
| "eval_runtime": 41.0324, | |
| "eval_samples_per_second": 8.993, | |
| "eval_steps_per_second": 2.267, | |
| "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": 1.0213137333406925e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |