| { | |
| "best_metric": 1.1560208797454834, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1658181818181819, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02327272727272727, | |
| "grad_norm": 1.7745463848114014, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5999, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02327272727272727, | |
| "eval_loss": 1.773289442062378, | |
| "eval_runtime": 3.9571, | |
| "eval_samples_per_second": 12.635, | |
| "eval_steps_per_second": 3.285, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04654545454545454, | |
| "grad_norm": 1.9175318479537964, | |
| "learning_rate": 0.0001, | |
| "loss": 1.773, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06981818181818182, | |
| "grad_norm": 1.262076735496521, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.6515, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09309090909090909, | |
| "grad_norm": 0.9791045188903809, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4618, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 0.8115462064743042, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.4479, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13963636363636364, | |
| "grad_norm": 0.7214769721031189, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3714, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16290909090909092, | |
| "grad_norm": 0.5080850720405579, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.328, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18618181818181817, | |
| "grad_norm": 0.8564537167549133, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.346, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20945454545454545, | |
| "grad_norm": 0.5081934928894043, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.3867, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": 0.5730867981910706, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.4286, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.6481610536575317, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3303, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2792727272727273, | |
| "grad_norm": 0.5679121017456055, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.363, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.30254545454545456, | |
| "grad_norm": 0.4099390208721161, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.3366, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.32581818181818184, | |
| "grad_norm": 0.3924468159675598, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2421, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3490909090909091, | |
| "grad_norm": 0.42564189434051514, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2091, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.37236363636363634, | |
| "grad_norm": 0.39355647563934326, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.1623, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3956363636363636, | |
| "grad_norm": 0.36167147755622864, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1963, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4189090909090909, | |
| "grad_norm": 0.3511923849582672, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.1963, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4421818181818182, | |
| "grad_norm": 0.37287771701812744, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2414, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.46545454545454545, | |
| "grad_norm": 0.3826206922531128, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.3273, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48872727272727273, | |
| "grad_norm": 0.5573943853378296, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4127, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.5266674160957336, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.2144, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5352727272727272, | |
| "grad_norm": 0.48996224999427795, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2944, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5585454545454546, | |
| "grad_norm": 0.41946741938591003, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2175, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.3697955310344696, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1384, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "eval_loss": 1.2017804384231567, | |
| "eval_runtime": 4.0484, | |
| "eval_samples_per_second": 12.351, | |
| "eval_steps_per_second": 3.211, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6050909090909091, | |
| "grad_norm": 0.36338701844215393, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1141, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6283636363636363, | |
| "grad_norm": 0.367141991853714, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.1142, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6516363636363637, | |
| "grad_norm": 0.3999696373939514, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.1136, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6749090909090909, | |
| "grad_norm": 0.39164677262306213, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.1816, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6981818181818182, | |
| "grad_norm": 0.45403310656547546, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2989, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7214545454545455, | |
| "grad_norm": 0.5455201864242554, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.3082, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7447272727272727, | |
| "grad_norm": 0.3580777645111084, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2199, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.38596412539482117, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.2403, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7912727272727272, | |
| "grad_norm": 0.3120631277561188, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.1839, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8145454545454546, | |
| "grad_norm": 0.3093988001346588, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.1151, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8378181818181818, | |
| "grad_norm": 0.2600014805793762, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.1773, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8610909090909091, | |
| "grad_norm": 0.27386701107025146, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.0633, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8843636363636364, | |
| "grad_norm": 0.2746947407722473, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.0732, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9076363636363637, | |
| "grad_norm": 0.28902333974838257, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.117, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9309090909090909, | |
| "grad_norm": 0.3158881962299347, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.2144, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9541818181818181, | |
| "grad_norm": 0.3764362931251526, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.3209, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9774545454545455, | |
| "grad_norm": 0.5556831359863281, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3623, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.002909090909091, | |
| "grad_norm": 0.31221914291381836, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2963, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.026181818181818, | |
| "grad_norm": 0.35975971817970276, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.1284, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0494545454545454, | |
| "grad_norm": 0.28899094462394714, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.1973, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0727272727272728, | |
| "grad_norm": 0.25856634974479675, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.1399, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.096, | |
| "grad_norm": 0.248923197388649, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0896, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1192727272727272, | |
| "grad_norm": 0.25821453332901, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.0757, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1425454545454545, | |
| "grad_norm": 0.26640933752059937, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0786, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1658181818181819, | |
| "grad_norm": 0.30744296312332153, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1057, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1658181818181819, | |
| "eval_loss": 1.1560208797454834, | |
| "eval_runtime": 3.9511, | |
| "eval_samples_per_second": 12.655, | |
| "eval_steps_per_second": 3.29, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 3.24961789018112e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |