| { | |
| "best_metric": 0.4081031084060669, | |
| "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": 1.2596246004104614, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017169224165683014, | |
| "eval_loss": 0.9036669731140137, | |
| "eval_runtime": 1.4326, | |
| "eval_samples_per_second": 34.903, | |
| "eval_steps_per_second": 9.075, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003433844833136603, | |
| "grad_norm": 1.3791555166244507, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005150767249704904, | |
| "grad_norm": 1.1667404174804688, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.7132, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006867689666273206, | |
| "grad_norm": 0.8153201341629028, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.5947, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008584612082841506, | |
| "grad_norm": 0.692710280418396, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6038, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010301534499409808, | |
| "grad_norm": 0.6953746676445007, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.5551, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01201845691597811, | |
| "grad_norm": 0.5362421274185181, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.5038, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013735379332546411, | |
| "grad_norm": 0.5057839155197144, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.5306, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015452301749114711, | |
| "grad_norm": 0.5087113380432129, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.5439, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017169224165683013, | |
| "grad_norm": 0.5152668356895447, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.4963, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018886146582251316, | |
| "grad_norm": 0.4857848584651947, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5318, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020603068998819616, | |
| "grad_norm": 0.4353604316711426, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.4958, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022319991415387916, | |
| "grad_norm": 0.32499048113822937, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.3869, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02403691383195622, | |
| "grad_norm": 0.29568466544151306, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3995, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02575383624852452, | |
| "grad_norm": 0.30388227105140686, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.4368, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027470758665092822, | |
| "grad_norm": 0.28955161571502686, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4231, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.029187681081661122, | |
| "grad_norm": 0.31605711579322815, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4697, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030904603498229422, | |
| "grad_norm": 0.29648900032043457, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.4358, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03262152591479772, | |
| "grad_norm": 0.2937246263027191, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.4259, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.034338448331366025, | |
| "grad_norm": 0.303239643573761, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.439, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03605537074793433, | |
| "grad_norm": 0.3211648464202881, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4753, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03777229316450263, | |
| "grad_norm": 0.3482668697834015, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.4777, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03948921558107093, | |
| "grad_norm": 0.3265639841556549, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4112, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04120613799763923, | |
| "grad_norm": 0.3768616318702698, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4484, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042923060414207535, | |
| "grad_norm": 0.44284531474113464, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.448, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042923060414207535, | |
| "eval_loss": 0.4245308041572571, | |
| "eval_runtime": 1.4666, | |
| "eval_samples_per_second": 34.093, | |
| "eval_steps_per_second": 8.864, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04463998283077583, | |
| "grad_norm": 0.21593862771987915, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.3316, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.046356905247344135, | |
| "grad_norm": 0.24882915616035461, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4051, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04807382766391244, | |
| "grad_norm": 0.25821322202682495, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4135, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.049790750080480735, | |
| "grad_norm": 0.2826606333255768, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4407, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05150767249704904, | |
| "grad_norm": 0.2720731198787689, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.4301, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05322459491361734, | |
| "grad_norm": 0.27546319365501404, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4239, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.054941517330185645, | |
| "grad_norm": 0.28127309679985046, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.449, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05665843974675394, | |
| "grad_norm": 0.29469725489616394, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4422, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.058375362163322245, | |
| "grad_norm": 0.32133859395980835, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4467, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06009228457989055, | |
| "grad_norm": 0.31768831610679626, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4535, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061809206996458844, | |
| "grad_norm": 0.3453242778778076, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4698, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06352612941302715, | |
| "grad_norm": 0.388174831867218, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.4149, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06524305182959544, | |
| "grad_norm": 0.2139841616153717, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3314, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06695997424616375, | |
| "grad_norm": 0.2043762505054474, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.372, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06867689666273205, | |
| "grad_norm": 0.22525262832641602, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4039, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07039381907930035, | |
| "grad_norm": 0.23101642727851868, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.3862, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07211074149586866, | |
| "grad_norm": 0.2495206594467163, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4331, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07382766391243696, | |
| "grad_norm": 0.24867644906044006, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4008, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07554458632900526, | |
| "grad_norm": 0.2708423435688019, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4429, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07726150874557355, | |
| "grad_norm": 0.27113476395606995, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4277, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07897843116214186, | |
| "grad_norm": 0.27955588698387146, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4675, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08069535357871016, | |
| "grad_norm": 0.28158727288246155, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.4287, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08241227599527846, | |
| "grad_norm": 0.3091404438018799, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.4544, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08412919841184677, | |
| "grad_norm": 0.3447839319705963, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4569, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08584612082841507, | |
| "grad_norm": 0.4188736081123352, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4265, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08584612082841507, | |
| "eval_loss": 0.4081031084060669, | |
| "eval_runtime": 1.4601, | |
| "eval_samples_per_second": 34.245, | |
| "eval_steps_per_second": 8.904, | |
| "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 | |
| } | |