| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5482456140350878, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03289473684210526, | |
| "grad_norm": 0.6724075675010681, | |
| "learning_rate": 1.9874388886763944e-05, | |
| "loss": 3.3606, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "grad_norm": 0.5784845352172852, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 2.93, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09868421052631579, | |
| "grad_norm": 0.43988049030303955, | |
| "learning_rate": 1.8579834132349773e-05, | |
| "loss": 2.4914, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 0.48597127199172974, | |
| "learning_rate": 1.745264449675755e-05, | |
| "loss": 2.1611, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.16447368421052633, | |
| "grad_norm": 0.48318102955818176, | |
| "learning_rate": 1.6056096871376667e-05, | |
| "loss": 1.8257, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "grad_norm": 0.5479584336280823, | |
| "learning_rate": 1.4440666126057743e-05, | |
| "loss": 1.5039, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.23026315789473684, | |
| "grad_norm": 0.445963054895401, | |
| "learning_rate": 1.266473813690035e-05, | |
| "loss": 1.2459, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 0.5397000908851624, | |
| "learning_rate": 1.0792499568567885e-05, | |
| "loss": 1.0866, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.29605263157894735, | |
| "grad_norm": 0.32380956411361694, | |
| "learning_rate": 8.89161800098989e-06, | |
| "loss": 0.9383, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "grad_norm": 0.2861121892929077, | |
| "learning_rate": 7.0307962467172555e-06, | |
| "loss": 0.8876, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3618421052631579, | |
| "grad_norm": 0.33690324425697327, | |
| "learning_rate": 5.277289252273175e-06, | |
| "loss": 0.8535, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 0.3120814859867096, | |
| "learning_rate": 3.6944733291547784e-06, | |
| "loss": 0.8281, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4276315789473684, | |
| "grad_norm": 0.2872855067253113, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.8277, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "grad_norm": 0.39285048842430115, | |
| "learning_rate": 1.2615062293021508e-06, | |
| "loss": 0.8036, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4934210526315789, | |
| "grad_norm": 0.3163042962551117, | |
| "learning_rate": 4.992888225905467e-07, | |
| "loss": 0.8061, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.29761916399002075, | |
| "learning_rate": 8.04518716920466e-08, | |
| "loss": 0.7961, | |
| "step": 480 | |
| } | |
| ], | |
| "logging_steps": 30, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "total_flos": 2.3224000778521805e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |