{ "best_metric": null, "best_model_checkpoint": null, "epoch": 76.92307692307692, "eval_steps": 500, "global_step": 5000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.5384615384615383, "grad_norm": 134.7136688232422, "learning_rate": 9.981600000000001e-06, "loss": 5.6198, "step": 100 }, { "epoch": 3.076923076923077, "grad_norm": 115.98611450195312, "learning_rate": 9.961600000000001e-06, "loss": 3.5959, "step": 200 }, { "epoch": 4.615384615384615, "grad_norm": 114.23514556884766, "learning_rate": 9.941600000000002e-06, "loss": 3.3845, "step": 300 }, { "epoch": 6.153846153846154, "grad_norm": 140.5648193359375, "learning_rate": 9.921600000000002e-06, "loss": 3.1494, "step": 400 }, { "epoch": 7.6923076923076925, "grad_norm": 117.4485855102539, "learning_rate": 9.901600000000002e-06, "loss": 3.0773, "step": 500 }, { "epoch": 9.23076923076923, "grad_norm": 389.71490478515625, "learning_rate": 9.8816e-06, "loss": 3.2116, "step": 600 }, { "epoch": 10.76923076923077, "grad_norm": 107.11251831054688, "learning_rate": 9.8616e-06, "loss": 3.0471, "step": 700 }, { "epoch": 12.307692307692308, "grad_norm": 85.49571228027344, "learning_rate": 9.8416e-06, "loss": 3.0201, "step": 800 }, { "epoch": 13.846153846153847, "grad_norm": 121.62274932861328, "learning_rate": 9.821600000000001e-06, "loss": 2.9355, "step": 900 }, { "epoch": 15.384615384615385, "grad_norm": 64.66451263427734, "learning_rate": 9.801600000000001e-06, "loss": 2.9637, "step": 1000 }, { "epoch": 16.923076923076923, "grad_norm": 182.4657440185547, "learning_rate": 9.781600000000001e-06, "loss": 2.9819, "step": 1100 }, { "epoch": 18.46153846153846, "grad_norm": 97.80529022216797, "learning_rate": 9.761600000000002e-06, "loss": 2.9486, "step": 1200 }, { "epoch": 20.0, "grad_norm": 220.0562744140625, "learning_rate": 9.741600000000002e-06, "loss": 2.8608, "step": 1300 }, { "epoch": 21.53846153846154, "grad_norm": 95.53397369384766, "learning_rate": 9.7216e-06, "loss": 2.8322, "step": 1400 }, { "epoch": 23.076923076923077, "grad_norm": 67.54853057861328, "learning_rate": 9.7016e-06, "loss": 2.9429, "step": 1500 }, { "epoch": 24.615384615384617, "grad_norm": 214.53131103515625, "learning_rate": 9.6816e-06, "loss": 2.7927, "step": 1600 }, { "epoch": 26.153846153846153, "grad_norm": 293.3318786621094, "learning_rate": 9.6616e-06, "loss": 2.7665, "step": 1700 }, { "epoch": 27.692307692307693, "grad_norm": 216.3682861328125, "learning_rate": 9.641600000000001e-06, "loss": 2.8309, "step": 1800 }, { "epoch": 29.23076923076923, "grad_norm": 168.0605010986328, "learning_rate": 9.621600000000001e-06, "loss": 2.8433, "step": 1900 }, { "epoch": 30.76923076923077, "grad_norm": 103.49143981933594, "learning_rate": 9.601600000000001e-06, "loss": 2.7606, "step": 2000 }, { "epoch": 32.30769230769231, "grad_norm": 116.6761474609375, "learning_rate": 9.581600000000002e-06, "loss": 2.6595, "step": 2100 }, { "epoch": 33.84615384615385, "grad_norm": 176.0087432861328, "learning_rate": 9.5616e-06, "loss": 2.632, "step": 2200 }, { "epoch": 35.38461538461539, "grad_norm": 120.39679718017578, "learning_rate": 9.5416e-06, "loss": 2.5941, "step": 2300 }, { "epoch": 36.92307692307692, "grad_norm": 100.69256591796875, "learning_rate": 9.5216e-06, "loss": 2.6007, "step": 2400 }, { "epoch": 38.46153846153846, "grad_norm": 254.54440307617188, "learning_rate": 9.5016e-06, "loss": 2.5548, "step": 2500 }, { "epoch": 40.0, "grad_norm": 113.618896484375, "learning_rate": 9.4816e-06, "loss": 2.5157, "step": 2600 }, { "epoch": 41.53846153846154, "grad_norm": 825.5616455078125, "learning_rate": 9.461600000000001e-06, "loss": 2.4832, "step": 2700 }, { "epoch": 43.07692307692308, "grad_norm": 58.83940505981445, "learning_rate": 9.441600000000001e-06, "loss": 2.4393, "step": 2800 }, { "epoch": 44.61538461538461, "grad_norm": 89.66182708740234, "learning_rate": 9.421600000000001e-06, "loss": 2.4381, "step": 2900 }, { "epoch": 46.15384615384615, "grad_norm": 242.81410217285156, "learning_rate": 9.4016e-06, "loss": 2.3978, "step": 3000 }, { "epoch": 47.69230769230769, "grad_norm": 70.43364715576172, "learning_rate": 9.3816e-06, "loss": 2.3782, "step": 3100 }, { "epoch": 49.23076923076923, "grad_norm": 244.31356811523438, "learning_rate": 9.3616e-06, "loss": 2.3319, "step": 3200 }, { "epoch": 50.76923076923077, "grad_norm": 59.848697662353516, "learning_rate": 9.3416e-06, "loss": 2.3205, "step": 3300 }, { "epoch": 52.30769230769231, "grad_norm": 109.26374053955078, "learning_rate": 9.3216e-06, "loss": 2.2943, "step": 3400 }, { "epoch": 53.84615384615385, "grad_norm": 307.2849426269531, "learning_rate": 9.301600000000001e-06, "loss": 2.2913, "step": 3500 }, { "epoch": 55.38461538461539, "grad_norm": 69.93729400634766, "learning_rate": 9.281600000000001e-06, "loss": 2.2166, "step": 3600 }, { "epoch": 56.92307692307692, "grad_norm": 83.3631591796875, "learning_rate": 9.261600000000001e-06, "loss": 2.2718, "step": 3700 }, { "epoch": 58.46153846153846, "grad_norm": 48.52922821044922, "learning_rate": 9.2416e-06, "loss": 2.2645, "step": 3800 }, { "epoch": 60.0, "grad_norm": 51.951324462890625, "learning_rate": 9.2218e-06, "loss": 2.2416, "step": 3900 }, { "epoch": 61.53846153846154, "grad_norm": 254.99429321289062, "learning_rate": 9.2018e-06, "loss": 2.2104, "step": 4000 }, { "epoch": 63.07692307692308, "grad_norm": 109.68157958984375, "learning_rate": 9.1818e-06, "loss": 2.1574, "step": 4100 }, { "epoch": 64.61538461538461, "grad_norm": 85.5855941772461, "learning_rate": 9.161800000000001e-06, "loss": 2.1513, "step": 4200 }, { "epoch": 66.15384615384616, "grad_norm": 63.89781951904297, "learning_rate": 9.141800000000001e-06, "loss": 2.1331, "step": 4300 }, { "epoch": 67.6923076923077, "grad_norm": 184.29612731933594, "learning_rate": 9.121800000000001e-06, "loss": 2.1866, "step": 4400 }, { "epoch": 69.23076923076923, "grad_norm": 108.59600830078125, "learning_rate": 9.1018e-06, "loss": 2.1453, "step": 4500 }, { "epoch": 70.76923076923077, "grad_norm": 80.51258087158203, "learning_rate": 9.0818e-06, "loss": 2.1125, "step": 4600 }, { "epoch": 72.3076923076923, "grad_norm": 172.7328643798828, "learning_rate": 9.0618e-06, "loss": 2.141, "step": 4700 }, { "epoch": 73.84615384615384, "grad_norm": 58.20785903930664, "learning_rate": 9.0418e-06, "loss": 2.0786, "step": 4800 }, { "epoch": 75.38461538461539, "grad_norm": 72.46143341064453, "learning_rate": 9.0218e-06, "loss": 2.0914, "step": 4900 }, { "epoch": 76.92307692307692, "grad_norm": 48.18838119506836, "learning_rate": 9.0018e-06, "loss": 2.0439, "step": 5000 } ], "logging_steps": 100, "max_steps": 50000, "num_input_tokens_seen": 0, "num_train_epochs": 770, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.91121583104e+19, "train_batch_size": 8, "trial_name": null, "trial_params": null }