| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.134471718249733, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.929420135183209e-05, | |
| "loss": 2.2013, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.8582710779082177e-05, | |
| "loss": 1.8974, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.7872643187477766e-05, | |
| "loss": 1.8466, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.7162575595873356e-05, | |
| "loss": 1.7943, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.6458199928850945e-05, | |
| "loss": 1.7609, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 14.754002134471719, | |
| "eval_loss": 1.6032053232192993, | |
| "eval_rouge1": 0.48488710871167534, | |
| "eval_rouge2": 0.22785571055312542, | |
| "eval_rougeL": 0.43701890815900213, | |
| "eval_rougeLsum": 0.4373720227877942, | |
| "eval_runtime": 718.1564, | |
| "eval_samples_per_second": 5.219, | |
| "eval_steps_per_second": 1.305, | |
| "step": 2811 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.5749555318392034e-05, | |
| "loss": 1.697, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.5040910707933121e-05, | |
| "loss": 1.6457, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.433226609747421e-05, | |
| "loss": 1.6618, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.3620775524724299e-05, | |
| "loss": 1.663, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.2910707933119888e-05, | |
| "loss": 1.6142, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.2202063322660976e-05, | |
| "loss": 1.6299, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 14.741728922091783, | |
| "eval_loss": 1.5628483295440674, | |
| "eval_rouge1": 0.49155599715708637, | |
| "eval_rouge2": 0.23584657180255802, | |
| "eval_rougeL": 0.44583750748943135, | |
| "eval_rougeLsum": 0.44613129652159983, | |
| "eval_runtime": 721.9589, | |
| "eval_samples_per_second": 5.191, | |
| "eval_steps_per_second": 1.298, | |
| "step": 5622 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.1491995731056565e-05, | |
| "loss": 1.5961, | |
| "step": 6000 | |
| } | |
| ], | |
| "max_steps": 14055, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.361090782518272e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |