| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.21722012544462244, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0006992397089171283, | |
| "loss": 0.5664, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0006984794178342565, | |
| "loss": 0.5958, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006977191267513849, | |
| "loss": 0.599, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006969588356685131, | |
| "loss": 0.6111, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006961985445856413, | |
| "loss": 0.5763, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006954382535027696, | |
| "loss": 0.6012, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006946779624198979, | |
| "loss": 0.6054, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006939176713370262, | |
| "loss": 0.5922, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006931573802541545, | |
| "loss": 0.5865, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006923970891712827, | |
| "loss": 0.6263, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006916367980884109, | |
| "loss": 0.6332, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006908765070055393, | |
| "loss": 0.618, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006901162159226675, | |
| "loss": 0.6272, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006893559248397958, | |
| "loss": 0.6505, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006885956337569241, | |
| "loss": 0.6179, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006878353426740524, | |
| "loss": 0.6509, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006870750515911806, | |
| "loss": 0.6487, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0006863147605083089, | |
| "loss": 0.6341, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0006855544694254371, | |
| "loss": 0.6408, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0006847941783425654, | |
| "loss": 0.6413, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 92070, | |
| "num_train_epochs": 10, | |
| "total_flos": 4097763812966400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |