| { | |
| "best_metric": 11.762595176696777, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7259528130671506, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014519056261343012, | |
| "grad_norm": 0.029154645279049873, | |
| "learning_rate": 5e-05, | |
| "loss": 11.766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014519056261343012, | |
| "eval_loss": 11.767232894897461, | |
| "eval_runtime": 0.1606, | |
| "eval_samples_per_second": 311.383, | |
| "eval_steps_per_second": 80.96, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029038112522686024, | |
| "grad_norm": 0.02247803285717964, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7657, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.043557168784029036, | |
| "grad_norm": 0.02242513746023178, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.7655, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05807622504537205, | |
| "grad_norm": 0.026150308549404144, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.7669, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "grad_norm": 0.02264326624572277, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.7657, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08711433756805807, | |
| "grad_norm": 0.024662349373102188, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.7653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10163339382940109, | |
| "grad_norm": 0.026005947962403297, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.7658, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1161524500907441, | |
| "grad_norm": 0.02762726880609989, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.7645, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1306715063520871, | |
| "grad_norm": 0.028195101767778397, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.7659, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14519056261343014, | |
| "grad_norm": 0.029820987954735756, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.7654, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15970961887477314, | |
| "grad_norm": 0.029102293774485588, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.766, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17422867513611615, | |
| "grad_norm": 0.029941972345113754, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.7655, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18874773139745918, | |
| "grad_norm": 0.02638484351336956, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.7642, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20326678765880218, | |
| "grad_norm": 0.026509391143918037, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.7642, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2177858439201452, | |
| "grad_norm": 0.025683650746941566, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.7638, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2323049001814882, | |
| "grad_norm": 0.02455858327448368, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.7649, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24682395644283123, | |
| "grad_norm": 0.029889853671193123, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.7635, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2613430127041742, | |
| "grad_norm": 0.030321016907691956, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.7642, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 0.029456747695803642, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.7638, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.29038112522686027, | |
| "grad_norm": 0.035611592233181, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.7654, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.30490018148820325, | |
| "grad_norm": 0.03753160312771797, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.7639, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3194192377495463, | |
| "grad_norm": 0.03716311976313591, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.7646, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3339382940108893, | |
| "grad_norm": 0.0360814593732357, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.7642, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3484573502722323, | |
| "grad_norm": 0.04132644459605217, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.764, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3629764065335753, | |
| "grad_norm": 0.042830027639865875, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.7649, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3629764065335753, | |
| "eval_loss": 11.764338493347168, | |
| "eval_runtime": 0.1544, | |
| "eval_samples_per_second": 323.82, | |
| "eval_steps_per_second": 84.193, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.37749546279491836, | |
| "grad_norm": 0.03273957595229149, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.7629, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.39201451905626133, | |
| "grad_norm": 0.03591519221663475, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.7638, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.40653357531760437, | |
| "grad_norm": 0.03769417852163315, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.7638, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.03959864750504494, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.7632, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4355716878402904, | |
| "grad_norm": 0.0384114570915699, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.7634, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4500907441016334, | |
| "grad_norm": 0.043950121849775314, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.7624, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4646098003629764, | |
| "grad_norm": 0.0419909842312336, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.763, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4791288566243194, | |
| "grad_norm": 0.049478158354759216, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.7621, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.49364791288566245, | |
| "grad_norm": 0.05043622851371765, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.7621, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5081669691470054, | |
| "grad_norm": 0.054947227239608765, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.7627, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5226860254083484, | |
| "grad_norm": 0.04828513413667679, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.7625, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5372050816696915, | |
| "grad_norm": 0.053075019270181656, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.763, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 0.039661288261413574, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.7631, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5662431941923775, | |
| "grad_norm": 0.0446428544819355, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.7629, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5807622504537205, | |
| "grad_norm": 0.04789067059755325, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.762, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5952813067150635, | |
| "grad_norm": 0.044995371252298355, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.7621, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6098003629764065, | |
| "grad_norm": 0.048021722584962845, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.7626, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6243194192377496, | |
| "grad_norm": 0.04975919798016548, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.7628, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6388384754990926, | |
| "grad_norm": 0.05071737989783287, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.7614, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6533575317604355, | |
| "grad_norm": 0.05162530392408371, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.7615, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6678765880217786, | |
| "grad_norm": 0.05929640680551529, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.7618, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6823956442831216, | |
| "grad_norm": 0.0559273362159729, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.7615, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6969147005444646, | |
| "grad_norm": 0.06553119421005249, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.7608, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7114337568058077, | |
| "grad_norm": 0.06088912487030029, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.7609, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7259528130671506, | |
| "grad_norm": 0.056244444102048874, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7624, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7259528130671506, | |
| "eval_loss": 11.762595176696777, | |
| "eval_runtime": 0.1679, | |
| "eval_samples_per_second": 297.873, | |
| "eval_steps_per_second": 77.447, | |
| "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": 171619514318848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |