| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.536231884057971, | |
| "eval_steps": 100, | |
| "global_step": 700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09057971014492754, | |
| "grad_norm": 3.993109941482544, | |
| "learning_rate": 4.8e-05, | |
| "loss": 5.8262, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18115942028985507, | |
| "grad_norm": 2.505798578262329, | |
| "learning_rate": 9.8e-05, | |
| "loss": 2.6903, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2717391304347826, | |
| "grad_norm": 3.59139084815979, | |
| "learning_rate": 9.680000000000001e-05, | |
| "loss": 1.526, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.36231884057971014, | |
| "grad_norm": 2.7294201850891113, | |
| "learning_rate": 9.346666666666667e-05, | |
| "loss": 1.2288, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4528985507246377, | |
| "grad_norm": 2.487971544265747, | |
| "learning_rate": 9.013333333333333e-05, | |
| "loss": 0.8614, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5434782608695652, | |
| "grad_norm": 2.39106822013855, | |
| "learning_rate": 8.680000000000001e-05, | |
| "loss": 0.6725, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6340579710144928, | |
| "grad_norm": 2.840284585952759, | |
| "learning_rate": 8.346666666666667e-05, | |
| "loss": 0.5635, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7246376811594203, | |
| "grad_norm": 2.5364346504211426, | |
| "learning_rate": 8.013333333333333e-05, | |
| "loss": 0.5359, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8152173913043478, | |
| "grad_norm": 2.3286707401275635, | |
| "learning_rate": 7.680000000000001e-05, | |
| "loss": 0.5415, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9057971014492754, | |
| "grad_norm": 2.4210703372955322, | |
| "learning_rate": 7.346666666666667e-05, | |
| "loss": 0.5255, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9963768115942029, | |
| "grad_norm": 2.7162601947784424, | |
| "learning_rate": 7.013333333333333e-05, | |
| "loss": 0.4809, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.0869565217391304, | |
| "grad_norm": 2.497736930847168, | |
| "learning_rate": 6.680000000000001e-05, | |
| "loss": 0.4163, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.177536231884058, | |
| "grad_norm": 2.3104195594787598, | |
| "learning_rate": 6.346666666666667e-05, | |
| "loss": 0.4313, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.2681159420289856, | |
| "grad_norm": 3.0482141971588135, | |
| "learning_rate": 6.013333333333334e-05, | |
| "loss": 0.3828, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.358695652173913, | |
| "grad_norm": 2.6846301555633545, | |
| "learning_rate": 5.68e-05, | |
| "loss": 0.3395, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.4492753623188406, | |
| "grad_norm": 3.353747606277466, | |
| "learning_rate": 5.346666666666667e-05, | |
| "loss": 0.3996, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.539855072463768, | |
| "grad_norm": 2.4080731868743896, | |
| "learning_rate": 5.013333333333333e-05, | |
| "loss": 0.3945, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.6304347826086958, | |
| "grad_norm": 2.7295942306518555, | |
| "learning_rate": 4.6800000000000006e-05, | |
| "loss": 0.3837, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.721014492753623, | |
| "grad_norm": 2.7674131393432617, | |
| "learning_rate": 4.346666666666667e-05, | |
| "loss": 0.3638, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.8115942028985508, | |
| "grad_norm": 2.684192419052124, | |
| "learning_rate": 4.013333333333333e-05, | |
| "loss": 0.3827, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9021739130434783, | |
| "grad_norm": 3.137209415435791, | |
| "learning_rate": 3.68e-05, | |
| "loss": 0.3838, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.9927536231884058, | |
| "grad_norm": 2.1572911739349365, | |
| "learning_rate": 3.346666666666667e-05, | |
| "loss": 0.3147, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.0833333333333335, | |
| "grad_norm": 1.9337104558944702, | |
| "learning_rate": 3.0133333333333335e-05, | |
| "loss": 0.266, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "grad_norm": 2.549443006515503, | |
| "learning_rate": 2.6800000000000004e-05, | |
| "loss": 0.275, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.2644927536231885, | |
| "grad_norm": 1.7999855279922485, | |
| "learning_rate": 2.3466666666666667e-05, | |
| "loss": 0.303, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.355072463768116, | |
| "grad_norm": 2.274960994720459, | |
| "learning_rate": 2.0133333333333336e-05, | |
| "loss": 0.2807, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.4456521739130435, | |
| "grad_norm": 2.8870270252227783, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.2969, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.536231884057971, | |
| "grad_norm": 2.63912034034729, | |
| "learning_rate": 1.3466666666666666e-05, | |
| "loss": 0.298, | |
| "step": 700 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3338166976512e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |