| { |
| "best_metric": 2.9672200679779053, |
| "best_model_checkpoint": "output/till-lindemann/checkpoint-39", |
| "epoch": 1.0, |
| "global_step": 39, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00013171058983499535, |
| "loss": 3.3688, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00011612089065075853, |
| "loss": 3.4282, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 9.292589525111794e-05, |
| "loss": 3.1227, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 6.583775650849414e-05, |
| "loss": 2.8864, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 3.9191690287750474e-05, |
| "loss": 2.8641, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 1.725216267546246e-05, |
| "loss": 3.099, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 3.53040008242582e-06, |
| "loss": 2.8089, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.9672200679779053, |
| "eval_runtime": 2.6533, |
| "eval_samples_per_second": 21.483, |
| "eval_steps_per_second": 3.015, |
| "step": 39 |
| } |
| ], |
| "max_steps": 39, |
| "num_train_epochs": 1, |
| "total_flos": 40630910976000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
