| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23652537938252224, | |
| "eval_steps": 500, | |
| "global_step": 113, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9999783114048658e-05, | |
| "loss": 1.388, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9994578321597258e-05, | |
| "loss": 2.0465, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9978319165308373e-05, | |
| "loss": 1.4634, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9951240161516643e-05, | |
| "loss": 1.3214, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9913370672952074e-05, | |
| "loss": 1.2373, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.986475176285232e-05, | |
| "loss": 1.2045, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9805436150436352e-05, | |
| "loss": 1.179, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9735488153739128e-05, | |
| "loss": 1.1447, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9654983619869242e-05, | |
| "loss": 1.1215, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9564009842765225e-05, | |
| "loss": 1.1073, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9462665468539582e-05, | |
| "loss": 1.1227, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9351060388513304e-05, | |
| "loss": 1.1091, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9229315620056805e-05, | |
| "loss": 1.0856, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.909756317536643e-05, | |
| "loss": 1.0948, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.895594591831896e-05, | |
| "loss": 1.0504, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.88046174095592e-05, | |
| "loss": 1.0596, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.8643741739988672e-05, | |
| "loss": 1.0684, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.8473493352836032e-05, | |
| "loss": 1.0813, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.829405685450202e-05, | |
| "loss": 1.0411, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8105626814384173e-05, | |
| "loss": 1.0507, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.7908407553898282e-05, | |
| "loss": 1.0678, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.7702612924925377e-05, | |
| "loss": 1.0602, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.7488466077924525e-05, | |
| "loss": 1.0374, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.043993592262268, | |
| "eval_runtime": 13.2732, | |
| "eval_samples_per_second": 75.34, | |
| "eval_steps_per_second": 2.411, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "step": 113, | |
| "total_flos": 47529181839360.0, | |
| "train_loss": 1.1670819742489704, | |
| "train_runtime": 3085.7682, | |
| "train_samples_per_second": 19.812, | |
| "train_steps_per_second": 0.155 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 477, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 47529181839360.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |