| { | |
| "best_metric": 0.4549524486064911, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0392156862745098, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000784313725490196, | |
| "grad_norm": 12.951228141784668, | |
| "learning_rate": 9e-06, | |
| "loss": 4.2676, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000784313725490196, | |
| "eval_loss": 1.2241708040237427, | |
| "eval_runtime": 170.1958, | |
| "eval_samples_per_second": 12.621, | |
| "eval_steps_per_second": 3.155, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001568627450980392, | |
| "grad_norm": 15.065213203430176, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.7549, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002352941176470588, | |
| "grad_norm": 13.755888938903809, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 2.7658, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003137254901960784, | |
| "grad_norm": 11.931817054748535, | |
| "learning_rate": 3.6e-05, | |
| "loss": 2.2277, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00392156862745098, | |
| "grad_norm": 8.542208671569824, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.8974, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004705882352941176, | |
| "grad_norm": 7.989168643951416, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 2.0913, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005490196078431373, | |
| "grad_norm": 6.630977630615234, | |
| "learning_rate": 6.3e-05, | |
| "loss": 1.6821, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006274509803921568, | |
| "grad_norm": 6.496756553649902, | |
| "learning_rate": 7.2e-05, | |
| "loss": 1.6665, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007058823529411765, | |
| "grad_norm": 7.982497215270996, | |
| "learning_rate": 8.1e-05, | |
| "loss": 2.0694, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00784313725490196, | |
| "grad_norm": 6.226460933685303, | |
| "learning_rate": 9e-05, | |
| "loss": 1.6821, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008627450980392156, | |
| "grad_norm": 6.819662570953369, | |
| "learning_rate": 8.999384872466111e-05, | |
| "loss": 1.73, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009411764705882352, | |
| "grad_norm": 8.317466735839844, | |
| "learning_rate": 8.997539658034168e-05, | |
| "loss": 1.7702, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01019607843137255, | |
| "grad_norm": 7.111891269683838, | |
| "learning_rate": 8.994464861167372e-05, | |
| "loss": 1.6366, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010980392156862745, | |
| "grad_norm": 7.476611614227295, | |
| "learning_rate": 8.990161322484486e-05, | |
| "loss": 1.6355, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011764705882352941, | |
| "grad_norm": 6.031744480133057, | |
| "learning_rate": 8.984630218530015e-05, | |
| "loss": 1.4807, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012549019607843137, | |
| "grad_norm": 6.812473773956299, | |
| "learning_rate": 8.977873061452552e-05, | |
| "loss": 1.6878, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013333333333333334, | |
| "grad_norm": 8.05068588256836, | |
| "learning_rate": 8.969891698591372e-05, | |
| "loss": 1.828, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01411764705882353, | |
| "grad_norm": 12.39442253112793, | |
| "learning_rate": 8.96068831197139e-05, | |
| "loss": 1.5053, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014901960784313726, | |
| "grad_norm": 10.175419807434082, | |
| "learning_rate": 8.950265417706609e-05, | |
| "loss": 1.7489, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01568627450980392, | |
| "grad_norm": 8.073866844177246, | |
| "learning_rate": 8.938625865312251e-05, | |
| "loss": 1.9391, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01647058823529412, | |
| "grad_norm": 7.202723026275635, | |
| "learning_rate": 8.925772836925722e-05, | |
| "loss": 1.3958, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017254901960784313, | |
| "grad_norm": 8.959539413452148, | |
| "learning_rate": 8.911709846436643e-05, | |
| "loss": 1.6471, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01803921568627451, | |
| "grad_norm": 9.780714988708496, | |
| "learning_rate": 8.896440738526198e-05, | |
| "loss": 1.3311, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018823529411764704, | |
| "grad_norm": 9.363273620605469, | |
| "learning_rate": 8.879969687616027e-05, | |
| "loss": 1.5693, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0196078431372549, | |
| "grad_norm": 11.106522560119629, | |
| "learning_rate": 8.862301196726988e-05, | |
| "loss": 1.3139, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0203921568627451, | |
| "grad_norm": 9.613574028015137, | |
| "learning_rate": 8.84344009624807e-05, | |
| "loss": 1.0847, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.021176470588235293, | |
| "grad_norm": 9.658738136291504, | |
| "learning_rate": 8.823391542615818e-05, | |
| "loss": 1.432, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02196078431372549, | |
| "grad_norm": 7.206670761108398, | |
| "learning_rate": 8.80216101690461e-05, | |
| "loss": 1.0293, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.022745098039215685, | |
| "grad_norm": 11.575990676879883, | |
| "learning_rate": 8.779754323328193e-05, | |
| "loss": 1.3784, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.023529411764705882, | |
| "grad_norm": 9.105690956115723, | |
| "learning_rate": 8.756177587652856e-05, | |
| "loss": 0.9299, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02431372549019608, | |
| "grad_norm": 11.146190643310547, | |
| "learning_rate": 8.731437255522727e-05, | |
| "loss": 1.127, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.025098039215686273, | |
| "grad_norm": 13.225046157836914, | |
| "learning_rate": 8.705540090697575e-05, | |
| "loss": 1.3228, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02588235294117647, | |
| "grad_norm": 12.464346885681152, | |
| "learning_rate": 8.678493173203682e-05, | |
| "loss": 1.9641, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02666666666666667, | |
| "grad_norm": 10.996861457824707, | |
| "learning_rate": 8.650303897398232e-05, | |
| "loss": 1.6458, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.027450980392156862, | |
| "grad_norm": 11.745558738708496, | |
| "learning_rate": 8.620979969947759e-05, | |
| "loss": 1.6805, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02823529411764706, | |
| "grad_norm": 10.623291015625, | |
| "learning_rate": 8.590529407721231e-05, | |
| "loss": 1.594, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.029019607843137254, | |
| "grad_norm": 9.937420845031738, | |
| "learning_rate": 8.558960535598317e-05, | |
| "loss": 1.4287, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02980392156862745, | |
| "grad_norm": 12.139042854309082, | |
| "learning_rate": 8.526281984193436e-05, | |
| "loss": 1.7026, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03058823529411765, | |
| "grad_norm": 12.166768074035645, | |
| "learning_rate": 8.492502687496253e-05, | |
| "loss": 2.1068, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03137254901960784, | |
| "grad_norm": 12.726622581481934, | |
| "learning_rate": 8.4576318804292e-05, | |
| "loss": 1.583, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03215686274509804, | |
| "grad_norm": 21.52069854736328, | |
| "learning_rate": 8.421679096322747e-05, | |
| "loss": 1.7145, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03294117647058824, | |
| "grad_norm": 13.835341453552246, | |
| "learning_rate": 8.384654164309084e-05, | |
| "loss": 2.445, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03372549019607843, | |
| "grad_norm": 16.390380859375, | |
| "learning_rate": 8.346567206634926e-05, | |
| "loss": 1.6284, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.034509803921568626, | |
| "grad_norm": 19.605005264282227, | |
| "learning_rate": 8.307428635894209e-05, | |
| "loss": 2.1787, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03529411764705882, | |
| "grad_norm": 12.839860916137695, | |
| "learning_rate": 8.26724915218138e-05, | |
| "loss": 1.6432, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03607843137254902, | |
| "grad_norm": 17.19524383544922, | |
| "learning_rate": 8.226039740166091e-05, | |
| "loss": 2.6786, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03686274509803922, | |
| "grad_norm": 22.435400009155273, | |
| "learning_rate": 8.183811666090117e-05, | |
| "loss": 2.043, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03764705882352941, | |
| "grad_norm": 52.507537841796875, | |
| "learning_rate": 8.140576474687264e-05, | |
| "loss": 2.563, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.038431372549019606, | |
| "grad_norm": 33.50967025756836, | |
| "learning_rate": 8.096345986027161e-05, | |
| "loss": 2.8917, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 47.0520133972168, | |
| "learning_rate": 8.051132292283772e-05, | |
| "loss": 3.6867, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "eval_loss": 0.4549524486064911, | |
| "eval_runtime": 171.8457, | |
| "eval_samples_per_second": 12.5, | |
| "eval_steps_per_second": 3.125, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 4, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.548522993392026e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |