| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 19.46875, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 4.999999999999999e-07, | |
| "loss": 2.0668, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 6.611096473669595e-07, | |
| "loss": 2.0009, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 7.456808469171361e-07, | |
| "loss": 1.8945, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 8.116246451989502e-07, | |
| "loss": 1.8767, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 8.621379348003944e-07, | |
| "loss": 1.8832, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 8.996702747267907e-07, | |
| "loss": 1.8296, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 9.346158598654879e-07, | |
| "loss": 1.7937, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 9.647094628571462e-07, | |
| "loss": 1.7744, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 9.888618026444236e-07, | |
| "loss": 1.7569, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 19.47, | |
| "learning_rate": 9.875e-07, | |
| "loss": 1.7344, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 19.47, | |
| "eval_oa_private_accuracy": 0.6364534452951346, | |
| "eval_oa_private_loss": 1.6610597372055054, | |
| "eval_oa_private_runtime": 3.2247, | |
| "eval_oa_private_samples_per_second": 5.272, | |
| "eval_oa_private_steps_per_second": 0.62, | |
| "step": 100 | |
| } | |
| ], | |
| "max_steps": 500, | |
| "num_train_epochs": 50, | |
| "total_flos": 38105874169856.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |