| { | |
| "best_metric": 10.99184799194336, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.12254901960784313, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024509803921568627, | |
| "grad_norm": 4.0515851974487305, | |
| "learning_rate": 5e-05, | |
| "loss": 177.8721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024509803921568627, | |
| "eval_loss": 11.109299659729004, | |
| "eval_runtime": 1.5305, | |
| "eval_samples_per_second": 32.669, | |
| "eval_steps_per_second": 8.494, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004901960784313725, | |
| "grad_norm": 3.821880340576172, | |
| "learning_rate": 0.0001, | |
| "loss": 177.838, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007352941176470588, | |
| "grad_norm": 3.804079532623291, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 177.8183, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00980392156862745, | |
| "grad_norm": 3.8125574588775635, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 177.7364, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012254901960784314, | |
| "grad_norm": 3.800719738006592, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 177.7654, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014705882352941176, | |
| "grad_norm": 4.122642993927002, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 177.6549, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01715686274509804, | |
| "grad_norm": 4.160602569580078, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 177.5693, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0196078431372549, | |
| "grad_norm": 4.247185230255127, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 177.5286, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022058823529411766, | |
| "grad_norm": 4.147463798522949, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 177.4949, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024509803921568627, | |
| "grad_norm": 4.242199420928955, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 177.5084, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02696078431372549, | |
| "grad_norm": 4.2388997077941895, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 177.3841, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029411764705882353, | |
| "grad_norm": 4.235126972198486, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 177.3785, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.031862745098039214, | |
| "grad_norm": 4.486023902893066, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 207.6706, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03431372549019608, | |
| "grad_norm": 4.396958827972412, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 177.2645, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03676470588235294, | |
| "grad_norm": 4.435211658477783, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 177.1757, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 4.590920925140381, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 177.0775, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.041666666666666664, | |
| "grad_norm": 4.719762325286865, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 177.0392, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04411764705882353, | |
| "grad_norm": 4.68377161026001, | |
| "learning_rate": 7.75e-05, | |
| "loss": 176.948, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04656862745098039, | |
| "grad_norm": 4.848801136016846, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 176.8581, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.049019607843137254, | |
| "grad_norm": 4.791360378265381, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 176.8594, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.051470588235294115, | |
| "grad_norm": 5.023166656494141, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 176.7801, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05392156862745098, | |
| "grad_norm": 4.994268894195557, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 176.7937, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.056372549019607844, | |
| "grad_norm": 5.045278072357178, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 176.6768, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 5.076049327850342, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 176.8229, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.061274509803921566, | |
| "grad_norm": 6.176201820373535, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 176.7589, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.061274509803921566, | |
| "eval_loss": 11.0306396484375, | |
| "eval_runtime": 0.0923, | |
| "eval_samples_per_second": 541.767, | |
| "eval_steps_per_second": 140.859, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06372549019607843, | |
| "grad_norm": 5.44142484664917, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 187.5009, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0661764705882353, | |
| "grad_norm": 4.920271873474121, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 176.5958, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06862745098039216, | |
| "grad_norm": 5.284728050231934, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 176.5206, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07107843137254902, | |
| "grad_norm": 5.332001686096191, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 176.4909, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07352941176470588, | |
| "grad_norm": 5.19172477722168, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 176.4136, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07598039215686274, | |
| "grad_norm": 5.826201438903809, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 176.1769, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 5.31245756149292, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 176.325, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08088235294117647, | |
| "grad_norm": 5.744202136993408, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 176.1636, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 5.508240222930908, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 176.1452, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0857843137254902, | |
| "grad_norm": 5.379641532897949, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 176.256, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08823529411764706, | |
| "grad_norm": 5.405764579772949, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 176.2521, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09068627450980392, | |
| "grad_norm": 5.883171558380127, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 176.2494, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09313725490196079, | |
| "grad_norm": 5.785599231719971, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 176.2912, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09558823529411764, | |
| "grad_norm": 5.51578426361084, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 176.0724, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09803921568627451, | |
| "grad_norm": 5.5537285804748535, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 176.0884, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10049019607843138, | |
| "grad_norm": 5.462303161621094, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 176.0427, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10294117647058823, | |
| "grad_norm": 5.737156867980957, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 175.98, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1053921568627451, | |
| "grad_norm": 5.694828987121582, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 175.9308, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10784313725490197, | |
| "grad_norm": 6.074409484863281, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 175.8056, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11029411764705882, | |
| "grad_norm": 5.782948970794678, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 175.8875, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11274509803921569, | |
| "grad_norm": 6.181939125061035, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 175.8657, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11519607843137254, | |
| "grad_norm": 5.735159873962402, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 175.8872, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 5.784780025482178, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 175.9216, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12009803921568628, | |
| "grad_norm": 5.5713701248168945, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 176.1538, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12254901960784313, | |
| "grad_norm": 6.3290205001831055, | |
| "learning_rate": 1e-05, | |
| "loss": 176.2121, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12254901960784313, | |
| "eval_loss": 10.99184799194336, | |
| "eval_runtime": 0.0933, | |
| "eval_samples_per_second": 535.863, | |
| "eval_steps_per_second": 139.324, | |
| "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": 38992443604992.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |