| { | |
| "best_metric": 0.40812382102012634, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08584612082841507, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017169224165683014, | |
| "grad_norm": 1.2387948036193848, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6481, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017169224165683014, | |
| "eval_loss": 0.9035757184028625, | |
| "eval_runtime": 0.831, | |
| "eval_samples_per_second": 60.166, | |
| "eval_steps_per_second": 15.643, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003433844833136603, | |
| "grad_norm": 1.3572694063186646, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7447, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005150767249704904, | |
| "grad_norm": 1.1221895217895508, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.7121, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006867689666273206, | |
| "grad_norm": 0.7851347923278809, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.5931, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008584612082841506, | |
| "grad_norm": 0.6702699661254883, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6026, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010301534499409808, | |
| "grad_norm": 0.6956961750984192, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.5553, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01201845691597811, | |
| "grad_norm": 0.5245652198791504, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.5045, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013735379332546411, | |
| "grad_norm": 0.506264328956604, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.5315, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015452301749114711, | |
| "grad_norm": 0.5087101459503174, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.5457, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017169224165683013, | |
| "grad_norm": 0.5110356211662292, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.4977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018886146582251316, | |
| "grad_norm": 0.4791967570781708, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5322, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020603068998819616, | |
| "grad_norm": 0.4328009784221649, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.4964, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022319991415387916, | |
| "grad_norm": 0.32185426354408264, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.3866, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02403691383195622, | |
| "grad_norm": 0.2920650839805603, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3992, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02575383624852452, | |
| "grad_norm": 0.2996692657470703, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.4367, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027470758665092822, | |
| "grad_norm": 0.2852506637573242, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4233, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.029187681081661122, | |
| "grad_norm": 0.3162078857421875, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4704, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030904603498229422, | |
| "grad_norm": 0.2991979122161865, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.4363, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03262152591479772, | |
| "grad_norm": 0.2970002591609955, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.4265, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.034338448331366025, | |
| "grad_norm": 0.302399218082428, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.4395, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03605537074793433, | |
| "grad_norm": 0.3205581605434418, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4759, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03777229316450263, | |
| "grad_norm": 0.34469857811927795, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.4782, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03948921558107093, | |
| "grad_norm": 0.32635343074798584, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4121, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04120613799763923, | |
| "grad_norm": 0.3795582056045532, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4489, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042923060414207535, | |
| "grad_norm": 0.4399312734603882, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.4482, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042923060414207535, | |
| "eval_loss": 0.42468079924583435, | |
| "eval_runtime": 0.8655, | |
| "eval_samples_per_second": 57.773, | |
| "eval_steps_per_second": 15.021, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04463998283077583, | |
| "grad_norm": 0.21563903987407684, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.332, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.046356905247344135, | |
| "grad_norm": 0.24940654635429382, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4055, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04807382766391244, | |
| "grad_norm": 0.25732117891311646, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4137, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.049790750080480735, | |
| "grad_norm": 0.2807253897190094, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4411, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05150767249704904, | |
| "grad_norm": 0.2723471224308014, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.4307, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05322459491361734, | |
| "grad_norm": 0.27555128931999207, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4244, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.054941517330185645, | |
| "grad_norm": 0.28199151158332825, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.4497, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05665843974675394, | |
| "grad_norm": 0.2908327579498291, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4427, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.058375362163322245, | |
| "grad_norm": 0.3176117241382599, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4469, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06009228457989055, | |
| "grad_norm": 0.31177636981010437, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4536, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061809206996458844, | |
| "grad_norm": 0.3403571844100952, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4703, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06352612941302715, | |
| "grad_norm": 0.3851555585861206, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.4157, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06524305182959544, | |
| "grad_norm": 0.21249587833881378, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3325, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06695997424616375, | |
| "grad_norm": 0.2026110589504242, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.3721, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06867689666273205, | |
| "grad_norm": 0.22161202132701874, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4041, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07039381907930035, | |
| "grad_norm": 0.22970175743103027, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.3862, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07211074149586866, | |
| "grad_norm": 0.24665836989879608, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4327, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07382766391243696, | |
| "grad_norm": 0.2487974464893341, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4008, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07554458632900526, | |
| "grad_norm": 0.2714938819408417, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4436, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07726150874557355, | |
| "grad_norm": 0.27039292454719543, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4286, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07897843116214186, | |
| "grad_norm": 0.280936598777771, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4681, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08069535357871016, | |
| "grad_norm": 0.2817816138267517, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.4288, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08241227599527846, | |
| "grad_norm": 0.3105645775794983, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.4546, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08412919841184677, | |
| "grad_norm": 0.34473907947540283, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4575, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08584612082841507, | |
| "grad_norm": 0.4184184968471527, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4269, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08584612082841507, | |
| "eval_loss": 0.40812382102012634, | |
| "eval_runtime": 0.8579, | |
| "eval_samples_per_second": 58.279, | |
| "eval_steps_per_second": 15.153, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5899604877626573e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |