| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "global_step": 39375, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.902023616171372e-05, | |
| "loss": 2.3606, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 108.1064, | |
| "eval_loss": 2.050605297088623, | |
| "eval_rouge1": 43.1144, | |
| "eval_rouge2": 19.9792, | |
| "eval_rougeL": 29.3193, | |
| "eval_rougeLsum": 29.3219, | |
| "eval_runtime": 6630.4724, | |
| "eval_samples_per_second": 3.016, | |
| "eval_steps_per_second": 3.016, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.914534041525834e-05, | |
| "loss": 2.0883, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 111.923, | |
| "eval_loss": 1.9714523553848267, | |
| "eval_rouge1": 43.2087, | |
| "eval_rouge2": 20.0241, | |
| "eval_rougeL": 29.2716, | |
| "eval_rougeLsum": 29.2729, | |
| "eval_runtime": 6876.0309, | |
| "eval_samples_per_second": 2.909, | |
| "eval_steps_per_second": 2.909, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5.9272200517975506e-05, | |
| "loss": 1.9401, | |
| "step": 16875 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 110.7088, | |
| "eval_loss": 1.9192545413970947, | |
| "eval_rouge1": 43.7675, | |
| "eval_rouge2": 20.4219, | |
| "eval_rougeL": 29.736, | |
| "eval_rougeLsum": 29.736, | |
| "eval_runtime": 6792.0963, | |
| "eval_samples_per_second": 2.945, | |
| "eval_steps_per_second": 2.945, | |
| "step": 16875 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.9397304771520136e-05, | |
| "loss": 1.8413, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 114.6206, | |
| "eval_loss": 1.9106097221374512, | |
| "eval_rouge1": 43.9857, | |
| "eval_rouge2": 20.6259, | |
| "eval_rougeL": 29.863, | |
| "eval_rougeLsum": 29.8645, | |
| "eval_runtime": 7084.2274, | |
| "eval_samples_per_second": 2.823, | |
| "eval_steps_per_second": 2.823, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.952240902506475e-05, | |
| "loss": 1.7632, | |
| "step": 28125 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 116.4429, | |
| "eval_loss": 1.9056074619293213, | |
| "eval_rouge1": 44.0791, | |
| "eval_rouge2": 20.7132, | |
| "eval_rougeL": 29.9243, | |
| "eval_rougeLsum": 29.9263, | |
| "eval_runtime": 7223.7263, | |
| "eval_samples_per_second": 2.769, | |
| "eval_steps_per_second": 2.769, | |
| "step": 28125 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 2.9649269127781926e-05, | |
| "loss": 1.6991, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_gen_len": 116.3214, | |
| "eval_loss": 1.9034677743911743, | |
| "eval_rouge1": 44.0398, | |
| "eval_rouge2": 20.6289, | |
| "eval_rougeL": 29.862, | |
| "eval_rougeLsum": 29.8651, | |
| "eval_runtime": 7200.6944, | |
| "eval_samples_per_second": 2.778, | |
| "eval_steps_per_second": 2.778, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 1.9777885079671656e-05, | |
| "loss": 1.6457, | |
| "step": 39375 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_gen_len": 113.2878, | |
| "eval_loss": 1.9000203609466553, | |
| "eval_rouge1": 43.9966, | |
| "eval_rouge2": 20.5908, | |
| "eval_rougeL": 29.9303, | |
| "eval_rougeLsum": 29.93, | |
| "eval_runtime": 7006.6993, | |
| "eval_samples_per_second": 2.854, | |
| "eval_steps_per_second": 2.854, | |
| "step": 39375 | |
| } | |
| ], | |
| "max_steps": 50625, | |
| "num_train_epochs": 9, | |
| "total_flos": 3.353631721258291e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |