| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.999954063117277, | |
| "global_step": 10884, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002908122013965454, | |
| "loss": 0.65, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002816244027930907, | |
| "loss": 0.4102, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002724366041896361, | |
| "loss": 0.3675, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00026324880558618153, | |
| "loss": 0.3386, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00025406100698272693, | |
| "loss": 0.3203, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00024487320837927233, | |
| "loss": 0.3104, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023568540977581768, | |
| "loss": 0.3027, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00022649761117236308, | |
| "loss": 0.289, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00021730981256890848, | |
| "loss": 0.2876, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00020812201396545386, | |
| "loss": 0.2807, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00019893421536199926, | |
| "loss": 0.2665, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00018974641675854466, | |
| "loss": 0.2423, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018055861815509, | |
| "loss": 0.2402, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001713708195516354, | |
| "loss": 0.2449, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0001621830209481808, | |
| "loss": 0.2354, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0001529952223447262, | |
| "loss": 0.2298, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014380742374127156, | |
| "loss": 0.2361, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013461962513781697, | |
| "loss": 0.2329, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00012543182653436237, | |
| "loss": 0.2274, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011624402793090774, | |
| "loss": 0.2213, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010705622932745312, | |
| "loss": 0.2306, | |
| "step": 10500 | |
| } | |
| ], | |
| "max_steps": 16326, | |
| "num_train_epochs": 3, | |
| "total_flos": 3.200004777443328e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |