| { | |
| "best_metric": 1.85786771774292, | |
| "best_model_checkpoint": "output/agata-christie/checkpoint-29", | |
| "epoch": 1.0, | |
| "global_step": 29, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001273804022850966, | |
| "loss": 2.2408, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00010073281903200561, | |
| "loss": 2.1303, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.488607087104036e-05, | |
| "loss": 1.9387, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.0102567316140575e-05, | |
| "loss": 1.9719, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.340326210572357e-06, | |
| "loss": 1.7591, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.85786771774292, | |
| "eval_runtime": 1.8785, | |
| "eval_samples_per_second": 22.891, | |
| "eval_steps_per_second": 3.194, | |
| "step": 29 | |
| } | |
| ], | |
| "max_steps": 29, | |
| "num_train_epochs": 1, | |
| "total_flos": 30048583680000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |