| { |
| "best_metric": 1.2630633115768433, |
| "epoch": 4.0, |
| "global_step": 12460, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 3.08, |
| "learning_rate": 9.866238630283575e-06, |
| "loss": 1.04, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 9.73247726056715e-06, |
| "loss": 1.0455, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.24, |
| "learning_rate": 9.598715890850723e-06, |
| "loss": 1.0043, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.32, |
| "learning_rate": 9.464954521134298e-06, |
| "loss": 1.0157, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.4, |
| "learning_rate": 9.331193151417872e-06, |
| "loss": 0.9964, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 9.197431781701446e-06, |
| "loss": 1.0175, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.56, |
| "learning_rate": 9.06367041198502e-06, |
| "loss": 1.0155, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.64, |
| "learning_rate": 8.929909042268593e-06, |
| "loss": 0.9954, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.72, |
| "learning_rate": 8.796147672552167e-06, |
| "loss": 0.9904, |
| "step": 4500 |
| }, |
| { |
| "epoch": 3.8, |
| "learning_rate": 8.662386302835741e-06, |
| "loss": 0.9646, |
| "step": 5000 |
| }, |
| { |
| "epoch": 3.88, |
| "learning_rate": 8.528624933119315e-06, |
| "loss": 1.002, |
| "step": 5500 |
| }, |
| { |
| "epoch": 3.96, |
| "learning_rate": 8.39486356340289e-06, |
| "loss": 0.9811, |
| "step": 6000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_gen_len": 18.808, |
| "eval_loss": 1.2630633115768433, |
| "eval_rouge1": 39.3771, |
| "eval_rouge2": 15.0611, |
| "eval_rougeL": 33.1013, |
| "eval_rougeLsum": 34.9745, |
| "eval_runtime": 715.4312, |
| "eval_samples_per_second": 2.097, |
| "eval_steps_per_second": 1.048, |
| "step": 6230 |
| } |
| ], |
| "max_steps": 37380, |
| "num_train_epochs": 6, |
| "total_flos": 2.96391223296e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
