| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1129, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.0792332887649536, | |
| "learning_rate": 6.637168141592921e-06, | |
| "loss": 2.8189, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.3077887296676636, | |
| "learning_rate": 1.3274336283185841e-05, | |
| "loss": 2.6588, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 1.2354748249053955, | |
| "learning_rate": 1.991150442477876e-05, | |
| "loss": 2.4479, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.6841175556182861, | |
| "learning_rate": 2.6548672566371683e-05, | |
| "loss": 2.2587, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.5395749807357788, | |
| "learning_rate": 2.9645669291338583e-05, | |
| "loss": 1.9755, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.49534282088279724, | |
| "learning_rate": 2.890748031496063e-05, | |
| "loss": 1.8501, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.40641939640045166, | |
| "learning_rate": 2.8169291338582678e-05, | |
| "loss": 1.8908, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.39455121755599976, | |
| "learning_rate": 2.7431102362204727e-05, | |
| "loss": 1.7573, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.48203709721565247, | |
| "learning_rate": 2.6722440944881888e-05, | |
| "loss": 1.6421, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.6426458358764648, | |
| "learning_rate": 2.5984251968503937e-05, | |
| "loss": 1.738, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.446591854095459, | |
| "learning_rate": 2.5246062992125983e-05, | |
| "loss": 1.6237, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.43455299735069275, | |
| "learning_rate": 2.450787401574803e-05, | |
| "loss": 1.6079, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.4745838940143585, | |
| "learning_rate": 2.376968503937008e-05, | |
| "loss": 1.4791, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.4581379294395447, | |
| "learning_rate": 2.3031496062992126e-05, | |
| "loss": 1.6389, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.4056738018989563, | |
| "learning_rate": 2.2293307086614175e-05, | |
| "loss": 1.5783, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.48176687955856323, | |
| "learning_rate": 2.155511811023622e-05, | |
| "loss": 1.5243, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.548370361328125, | |
| "learning_rate": 2.0816929133858267e-05, | |
| "loss": 1.4877, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.5029275417327881, | |
| "learning_rate": 2.0078740157480316e-05, | |
| "loss": 1.5826, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.5703559517860413, | |
| "learning_rate": 1.934055118110236e-05, | |
| "loss": 1.5118, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.4942224323749542, | |
| "learning_rate": 1.860236220472441e-05, | |
| "loss": 1.5043, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.5140496492385864, | |
| "learning_rate": 1.786417322834646e-05, | |
| "loss": 1.53, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.5072318911552429, | |
| "learning_rate": 1.7125984251968505e-05, | |
| "loss": 1.4875, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.5855621695518494, | |
| "learning_rate": 1.6387795275590554e-05, | |
| "loss": 1.4771, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.47852256894111633, | |
| "learning_rate": 1.5649606299212596e-05, | |
| "loss": 1.3911, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.4826895594596863, | |
| "learning_rate": 1.4911417322834647e-05, | |
| "loss": 1.3855, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.5134251117706299, | |
| "learning_rate": 1.4173228346456692e-05, | |
| "loss": 1.4103, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.4681044816970825, | |
| "learning_rate": 1.343503937007874e-05, | |
| "loss": 1.4102, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.5529048442840576, | |
| "learning_rate": 1.2696850393700789e-05, | |
| "loss": 1.4231, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.5898122787475586, | |
| "learning_rate": 1.1958661417322836e-05, | |
| "loss": 1.3718, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.766099214553833, | |
| "learning_rate": 1.1220472440944882e-05, | |
| "loss": 1.3482, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.5822522044181824, | |
| "learning_rate": 1.0482283464566929e-05, | |
| "loss": 1.2873, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.49051281809806824, | |
| "learning_rate": 9.744094488188976e-06, | |
| "loss": 1.3268, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.5041054487228394, | |
| "learning_rate": 9.005905511811024e-06, | |
| "loss": 1.3923, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.5318450331687927, | |
| "learning_rate": 8.267716535433071e-06, | |
| "loss": 1.3487, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.5623608827590942, | |
| "learning_rate": 7.529527559055118e-06, | |
| "loss": 1.4091, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.5455105900764465, | |
| "learning_rate": 6.791338582677165e-06, | |
| "loss": 1.3664, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.5180054903030396, | |
| "learning_rate": 6.053149606299213e-06, | |
| "loss": 1.3277, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.641249418258667, | |
| "learning_rate": 5.3149606299212595e-06, | |
| "loss": 1.4015, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.4672348201274872, | |
| "learning_rate": 4.576771653543308e-06, | |
| "loss": 1.3587, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.468883752822876, | |
| "learning_rate": 3.838582677165354e-06, | |
| "loss": 1.4637, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.5818473100662231, | |
| "learning_rate": 3.1003937007874014e-06, | |
| "loss": 1.3372, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.6030290126800537, | |
| "learning_rate": 2.3622047244094487e-06, | |
| "loss": 1.4148, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.5191698670387268, | |
| "learning_rate": 1.624015748031496e-06, | |
| "loss": 1.3975, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.48896682262420654, | |
| "learning_rate": 8.858267716535433e-07, | |
| "loss": 1.4067, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.46865954995155334, | |
| "learning_rate": 1.4763779527559055e-07, | |
| "loss": 1.3374, | |
| "step": 1125 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1129, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 2425451377065984.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |