| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.1964e-05, | |
| "loss": 1.6251, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.3952e-05, | |
| "loss": 1.0682, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.9991929541758342e-05, | |
| "loss": 0.8531, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.9926636060938516e-05, | |
| "loss": 0.8384, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.9796072198520905e-05, | |
| "loss": 0.8226, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.96010361969696e-05, | |
| "loss": 0.8162, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.9342281162131742e-05, | |
| "loss": 0.802, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.902058372494256e-05, | |
| "loss": 0.8099, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.8637577842487164e-05, | |
| "loss": 0.8511, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.8194938302038455e-05, | |
| "loss": 0.8355, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.8438622275145564, | |
| "eval_loss": 0.6963315010070801, | |
| "eval_runtime": 212.1584, | |
| "eval_samples_per_second": 23.567, | |
| "eval_steps_per_second": 0.589, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 50000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 3.156662550528e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |