| { | |
| "best_metric": 2.623548425617628e-06, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1215159109895952, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002430318219791904, | |
| "grad_norm": 22.831417083740234, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2244, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002430318219791904, | |
| "eval_loss": 4.146914005279541, | |
| "eval_runtime": 1.4756, | |
| "eval_samples_per_second": 33.885, | |
| "eval_steps_per_second": 8.81, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004860636439583808, | |
| "grad_norm": 23.100126266479492, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2233, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007290954659375712, | |
| "grad_norm": 19.852075576782227, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.2369, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009721272879167617, | |
| "grad_norm": 15.922313690185547, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.7262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01215159109895952, | |
| "grad_norm": 16.65655517578125, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.728, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014581909318751423, | |
| "grad_norm": 6.661933898925781, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.2899, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01701222753854333, | |
| "grad_norm": 2.946009874343872, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.062, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019442545758335233, | |
| "grad_norm": 0.16026008129119873, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0014, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021872863978127138, | |
| "grad_norm": 0.05047684162855148, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0002, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02430318219791904, | |
| "grad_norm": 0.007031927350908518, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026733500417710943, | |
| "grad_norm": 0.0027359570376574993, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029163818637502847, | |
| "grad_norm": 0.0011876067146658897, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03159413685729475, | |
| "grad_norm": 0.0007614659261889756, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03402445507708666, | |
| "grad_norm": 0.0006199803901836276, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03645477329687856, | |
| "grad_norm": 0.0007788946386426687, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03888509151667047, | |
| "grad_norm": 0.000807474716566503, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04131540973646237, | |
| "grad_norm": 0.000674623588565737, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.043745727956254275, | |
| "grad_norm": 0.0008040957036428154, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.046176046176046176, | |
| "grad_norm": 0.0016823202604427934, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04860636439583808, | |
| "grad_norm": 0.0009950436651706696, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.051036682615629984, | |
| "grad_norm": 0.0008805769612081349, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.053467000835421885, | |
| "grad_norm": 0.0005429453449323773, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05589731905521379, | |
| "grad_norm": 0.0005001699319109321, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05832763727500569, | |
| "grad_norm": 0.0005343256052583456, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0607579554947976, | |
| "grad_norm": 0.0005651435349136591, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0607579554947976, | |
| "eval_loss": 3.9596316128154285e-06, | |
| "eval_runtime": 1.4796, | |
| "eval_samples_per_second": 33.793, | |
| "eval_steps_per_second": 8.786, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0631882737145895, | |
| "grad_norm": 0.00042510413913987577, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06561859193438141, | |
| "grad_norm": 0.00035989907337352633, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06804891015417332, | |
| "grad_norm": 0.00035917776403948665, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07047922837396521, | |
| "grad_norm": 0.0003286278515588492, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07290954659375712, | |
| "grad_norm": 0.00031797558767721057, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07533986481354903, | |
| "grad_norm": 0.00030757233616895974, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07777018303334093, | |
| "grad_norm": 0.00030923346639610827, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08020050125313283, | |
| "grad_norm": 0.00029912899481132627, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08263081947292474, | |
| "grad_norm": 0.0002802808303385973, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08506113769271664, | |
| "grad_norm": 0.0002648854861035943, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08749145591250855, | |
| "grad_norm": 0.00025963204097934067, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08992177413230044, | |
| "grad_norm": 0.00027164211496710777, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09235209235209235, | |
| "grad_norm": 0.0002490248007234186, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09478241057188426, | |
| "grad_norm": 0.00024242346989922225, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09721272879167615, | |
| "grad_norm": 0.00022952283325139433, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09964304701146806, | |
| "grad_norm": 0.0002252504782518372, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10207336523125997, | |
| "grad_norm": 0.00022119212371762842, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10450368345105188, | |
| "grad_norm": 0.00021124388149473816, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10693400167084377, | |
| "grad_norm": 0.00021805534197483212, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10936431989063568, | |
| "grad_norm": 0.00021745653066318482, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11179463811042759, | |
| "grad_norm": 0.0002112941292580217, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1142249563302195, | |
| "grad_norm": 0.00020633387612178922, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11665527455001139, | |
| "grad_norm": 0.00020409161515999585, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1190855927698033, | |
| "grad_norm": 0.00021153417765162885, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1215159109895952, | |
| "grad_norm": 0.00021407307940535247, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1215159109895952, | |
| "eval_loss": 2.623548425617628e-06, | |
| "eval_runtime": 1.4808, | |
| "eval_samples_per_second": 33.766, | |
| "eval_steps_per_second": 8.779, | |
| "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": 2.953470533435392e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |