| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1362654536202431, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003406636340506077, | |
| "grad_norm": 0.8387678265571594, | |
| "learning_rate": 5.4421768707483e-06, | |
| "loss": 0.8629, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006813272681012154, | |
| "grad_norm": 0.5580975413322449, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.8351, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010219909021518231, | |
| "grad_norm": 0.4770251214504242, | |
| "learning_rate": 1.6780045351473924e-05, | |
| "loss": 0.8023, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.013626545362024308, | |
| "grad_norm": 0.35437077283859253, | |
| "learning_rate": 2.2448979591836737e-05, | |
| "loss": 0.7808, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.017033181702530386, | |
| "grad_norm": 0.37850669026374817, | |
| "learning_rate": 2.811791383219955e-05, | |
| "loss": 0.7554, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.020439818043036462, | |
| "grad_norm": 0.40117064118385315, | |
| "learning_rate": 3.378684807256236e-05, | |
| "loss": 0.7419, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02384645438354254, | |
| "grad_norm": 0.4868236780166626, | |
| "learning_rate": 3.945578231292517e-05, | |
| "loss": 0.751, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.027253090724048617, | |
| "grad_norm": 0.3966948390007019, | |
| "learning_rate": 4.512471655328798e-05, | |
| "loss": 0.7251, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.030659727064554693, | |
| "grad_norm": 0.3908109664916992, | |
| "learning_rate": 5.0793650793650794e-05, | |
| "loss": 0.7088, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.03406636340506077, | |
| "grad_norm": 0.3687989115715027, | |
| "learning_rate": 5.646258503401361e-05, | |
| "loss": 0.7115, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.03747299974556685, | |
| "grad_norm": 0.3919059634208679, | |
| "learning_rate": 6.213151927437642e-05, | |
| "loss": 0.7026, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.040879636086072924, | |
| "grad_norm": 0.42019009590148926, | |
| "learning_rate": 6.780045351473924e-05, | |
| "loss": 0.6967, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.044286272426579, | |
| "grad_norm": 0.4229620695114136, | |
| "learning_rate": 7.346938775510205e-05, | |
| "loss": 0.7148, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.04769290876708508, | |
| "grad_norm": 0.39575278759002686, | |
| "learning_rate": 7.913832199546486e-05, | |
| "loss": 0.744, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.051099545107591154, | |
| "grad_norm": 0.45732468366622925, | |
| "learning_rate": 8.480725623582767e-05, | |
| "loss": 0.7216, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.054506181448097234, | |
| "grad_norm": 0.3956912159919739, | |
| "learning_rate": 9.047619047619048e-05, | |
| "loss": 0.6953, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05791281778860331, | |
| "grad_norm": 0.3948104679584503, | |
| "learning_rate": 9.61451247165533e-05, | |
| "loss": 0.7235, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.061319454129109385, | |
| "grad_norm": 0.3913336396217346, | |
| "learning_rate": 9.99438004917457e-05, | |
| "loss": 0.6676, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.06472609046961547, | |
| "grad_norm": 0.3908584713935852, | |
| "learning_rate": 9.9768177028451e-05, | |
| "loss": 0.7158, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.06813272681012154, | |
| "grad_norm": 0.4225063920021057, | |
| "learning_rate": 9.959255356515631e-05, | |
| "loss": 0.7129, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07153936315062762, | |
| "grad_norm": 2.2388832569122314, | |
| "learning_rate": 9.941693010186162e-05, | |
| "loss": 0.7199, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.0749459994911337, | |
| "grad_norm": 0.39503997564315796, | |
| "learning_rate": 9.924130663856692e-05, | |
| "loss": 0.7298, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.07835263583163977, | |
| "grad_norm": 2.1647109985351562, | |
| "learning_rate": 9.906568317527221e-05, | |
| "loss": 0.7499, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.08175927217214585, | |
| "grad_norm": 0.36966434121131897, | |
| "learning_rate": 9.889005971197752e-05, | |
| "loss": 0.7212, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.08516590851265193, | |
| "grad_norm": 0.36990946531295776, | |
| "learning_rate": 9.871443624868283e-05, | |
| "loss": 0.7214, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.088572544853158, | |
| "grad_norm": 0.4158572852611542, | |
| "learning_rate": 9.853881278538813e-05, | |
| "loss": 0.6942, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.09197918119366408, | |
| "grad_norm": 0.3846476972103119, | |
| "learning_rate": 9.836318932209344e-05, | |
| "loss": 0.7218, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.09538581753417016, | |
| "grad_norm": 0.33537471294403076, | |
| "learning_rate": 9.818756585879874e-05, | |
| "loss": 0.7115, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.09879245387467624, | |
| "grad_norm": 0.3672342896461487, | |
| "learning_rate": 9.801194239550405e-05, | |
| "loss": 0.7225, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.10219909021518231, | |
| "grad_norm": 0.3498263955116272, | |
| "learning_rate": 9.783631893220935e-05, | |
| "loss": 0.7124, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.1056057265556884, | |
| "grad_norm": 0.3860284388065338, | |
| "learning_rate": 9.766069546891466e-05, | |
| "loss": 0.7018, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.10901236289619447, | |
| "grad_norm": 0.33633533120155334, | |
| "learning_rate": 9.748507200561996e-05, | |
| "loss": 0.6962, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.11241899923670054, | |
| "grad_norm": 0.3424709439277649, | |
| "learning_rate": 9.730944854232526e-05, | |
| "loss": 0.7068, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.11582563557720663, | |
| "grad_norm": 0.3627208173274994, | |
| "learning_rate": 9.713382507903056e-05, | |
| "loss": 0.6738, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.1192322719177127, | |
| "grad_norm": 0.3304712176322937, | |
| "learning_rate": 9.695820161573587e-05, | |
| "loss": 0.7004, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.12263890825821877, | |
| "grad_norm": 0.37575623393058777, | |
| "learning_rate": 9.678257815244117e-05, | |
| "loss": 0.711, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.12604554459872486, | |
| "grad_norm": 0.37238940596580505, | |
| "learning_rate": 9.660695468914648e-05, | |
| "loss": 0.7172, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.12945218093923094, | |
| "grad_norm": 0.39354655146598816, | |
| "learning_rate": 9.643133122585177e-05, | |
| "loss": 0.6949, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.132858817279737, | |
| "grad_norm": 0.34536346793174744, | |
| "learning_rate": 9.625570776255708e-05, | |
| "loss": 0.6871, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.1362654536202431, | |
| "grad_norm": 0.3518439829349518, | |
| "learning_rate": 9.608008429926238e-05, | |
| "loss": 0.7168, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 14676, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.2600066061911e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |