| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08060226008737285, | |
| "global_step": 45000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.955220966618126e-05, | |
| "loss": 2.3776, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.910441933236253e-05, | |
| "loss": 0.2443, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.865662899854379e-05, | |
| "loss": 0.2738, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8208838664725045e-05, | |
| "loss": 0.1848, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.776104833090631e-05, | |
| "loss": 0.1507, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.11242648959159851, | |
| "eval_runtime": 3430.1226, | |
| "eval_samples_per_second": 18.085, | |
| "eval_steps_per_second": 9.043, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7313257997087574e-05, | |
| "loss": 0.1358, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.6865467663268834e-05, | |
| "loss": 0.1323, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.64176773294501e-05, | |
| "loss": 0.1193, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.596988699563136e-05, | |
| "loss": 0.1129, | |
| "step": 45000 | |
| } | |
| ], | |
| "max_steps": 558297, | |
| "num_train_epochs": 1, | |
| "total_flos": 4.439552157522432e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |