| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3364012086270969, | |
| "global_step": 29058, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9999768462241983e-05, | |
| "loss": 1.7563, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9884694196506097e-05, | |
| "loss": 1.6983, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9768925317496153e-05, | |
| "loss": 1.6678, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9537387559476264e-05, | |
| "loss": 1.6488, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9306081339214394e-05, | |
| "loss": 1.6092, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9074775118952524e-05, | |
| "loss": 1.6189, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8843237360932635e-05, | |
| "loss": 1.603, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8611699602912747e-05, | |
| "loss": 1.5877, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8380161844892858e-05, | |
| "loss": 1.5702, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8148855624630988e-05, | |
| "loss": 1.5832, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7917549404369118e-05, | |
| "loss": 1.5646, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.768624318410725e-05, | |
| "loss": 1.5727, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7454705426087362e-05, | |
| "loss": 1.552, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.722316766806747e-05, | |
| "loss": 1.5383, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.699162991004758e-05, | |
| "loss": 1.5534, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6760092152027693e-05, | |
| "loss": 1.5457, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6528554394007805e-05, | |
| "loss": 1.5495, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6297248173745934e-05, | |
| "loss": 1.5386, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6065710415726046e-05, | |
| "loss": 1.5368, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5834172657706157e-05, | |
| "loss": 1.535, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5602866437444287e-05, | |
| "loss": 1.5247, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5371560217182417e-05, | |
| "loss": 1.5199, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.514002245916253e-05, | |
| "loss": 1.5341, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.4908484701142641e-05, | |
| "loss": 1.519, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.467741001863879e-05, | |
| "loss": 1.5243, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.44458722606189e-05, | |
| "loss": 1.5164, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4214334502599012e-05, | |
| "loss": 1.5095, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.3982796744579123e-05, | |
| "loss": 1.5007, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.3751490524317255e-05, | |
| "loss": 1.5128, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3519952766297365e-05, | |
| "loss": 1.5231, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3288415008277476e-05, | |
| "loss": 1.5052, | |
| "step": 29000 | |
| } | |
| ], | |
| "max_steps": 86379, | |
| "num_train_epochs": 1, | |
| "total_flos": 5.411313875209421e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |