| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 1800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.33, |
| "learning_rate": 7.11111111111111e-05, |
| "loss": 4.4138, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 6.222222222222223e-05, |
| "loss": 1.8202, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 5.333333333333333e-05, |
| "loss": 1.3066, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_gen_len": 16.380792618997692, |
| "eval_loss": 0.43468213081359863, |
| "eval_rouge1": 59.0002, |
| "eval_rouge2": 54.7692, |
| "eval_rougeL": 58.7112, |
| "eval_rougeLsum": 58.7856, |
| "eval_runtime": 66.5448, |
| "eval_samples_per_second": 286.664, |
| "eval_steps_per_second": 1.127, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 4.444444444444445e-05, |
| "loss": 1.0562, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 3.555555555555555e-05, |
| "loss": 0.9014, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 2.6666666666666667e-05, |
| "loss": 0.8192, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_gen_len": 16.515778989305936, |
| "eval_loss": 0.31542888283729553, |
| "eval_rouge1": 62.4672, |
| "eval_rouge2": 59.0199, |
| "eval_rougeL": 62.4096, |
| "eval_rougeLsum": 62.3667, |
| "eval_runtime": 67.0, |
| "eval_samples_per_second": 284.716, |
| "eval_steps_per_second": 1.119, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 1.7777777777777777e-05, |
| "loss": 0.7586, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 8.888888888888888e-06, |
| "loss": 0.7397, |
| "step": 1600 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0, |
| "loss": 0.7208, |
| "step": 1800 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_gen_len": 16.547127280352274, |
| "eval_loss": 0.30499330163002014, |
| "eval_rouge1": 62.701, |
| "eval_rouge2": 59.3201, |
| "eval_rougeL": 62.6739, |
| "eval_rougeLsum": 62.6165, |
| "eval_runtime": 66.9041, |
| "eval_samples_per_second": 285.124, |
| "eval_steps_per_second": 1.121, |
| "step": 1800 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 1800, |
| "total_flos": 4211322991681536.0, |
| "train_loss": 1.392938749525282, |
| "train_runtime": 543.7445, |
| "train_samples_per_second": 423.486, |
| "train_steps_per_second": 3.31 |
| } |
| ], |
| "max_steps": 1800, |
| "num_train_epochs": 3, |
| "total_flos": 4211322991681536.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
