| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.944110060189166, |
| "global_step": 23000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11, |
| "learning_rate": 9.787188306104902e-05, |
| "loss": 1.1754, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 9.572226999140155e-05, |
| "loss": 0.5467, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 9.357265692175409e-05, |
| "loss": 0.5189, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 9.142304385210663e-05, |
| "loss": 0.5128, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 8.927343078245917e-05, |
| "loss": 0.5021, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 8.71238177128117e-05, |
| "loss": 0.5089, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 8.497420464316423e-05, |
| "loss": 0.4957, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 8.282459157351677e-05, |
| "loss": 0.4943, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 8.06749785038693e-05, |
| "loss": 0.4853, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_gen_len": 23.4555, |
| "eval_loss": 0.4496892988681793, |
| "eval_rouge1": 73.323, |
| "eval_rouge2": 54.7538, |
| "eval_rougeL": 68.0299, |
| "eval_rougeLsum": 68.0246, |
| "eval_runtime": 375.6913, |
| "eval_samples_per_second": 0.508, |
| "eval_steps_per_second": 0.016, |
| "step": 4652 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 7.852536543422185e-05, |
| "loss": 0.4764, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 7.637575236457438e-05, |
| "loss": 0.4661, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 7.422613929492692e-05, |
| "loss": 0.4562, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 7.207652622527945e-05, |
| "loss": 0.4591, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 6.9926913155632e-05, |
| "loss": 0.46, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 6.777730008598453e-05, |
| "loss": 0.462, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 6.562768701633706e-05, |
| "loss": 0.457, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 6.34780739466896e-05, |
| "loss": 0.4473, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 6.132846087704214e-05, |
| "loss": 0.4536, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_gen_len": 23.089, |
| "eval_loss": 0.4476110339164734, |
| "eval_rouge1": 73.0167, |
| "eval_rouge2": 54.5451, |
| "eval_rougeL": 67.782, |
| "eval_rougeLsum": 67.7971, |
| "eval_runtime": 375.2197, |
| "eval_samples_per_second": 0.509, |
| "eval_steps_per_second": 0.016, |
| "step": 9304 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 5.917884780739468e-05, |
| "loss": 0.4484, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 5.7029234737747204e-05, |
| "loss": 0.4335, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 5.4879621668099744e-05, |
| "loss": 0.4341, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 5.2730008598452284e-05, |
| "loss": 0.4347, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 5.0584694754944115e-05, |
| "loss": 0.4268, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 4.843508168529665e-05, |
| "loss": 0.4283, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.69, |
| "learning_rate": 4.628976784178848e-05, |
| "loss": 0.4353, |
| "step": 12500 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 4.414015477214102e-05, |
| "loss": 0.4291, |
| "step": 13000 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 4.1990541702493554e-05, |
| "loss": 0.4333, |
| "step": 13500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_gen_len": 22.9686, |
| "eval_loss": 0.44937288761138916, |
| "eval_rouge1": 73.1917, |
| "eval_rouge2": 54.579, |
| "eval_rougeL": 67.9593, |
| "eval_rougeLsum": 67.9681, |
| "eval_runtime": 375.7125, |
| "eval_samples_per_second": 0.508, |
| "eval_steps_per_second": 0.016, |
| "step": 13956 |
| }, |
| { |
| "epoch": 3.01, |
| "learning_rate": 3.9840928632846094e-05, |
| "loss": 0.429, |
| "step": 14000 |
| }, |
| { |
| "epoch": 3.12, |
| "learning_rate": 3.769561478933792e-05, |
| "loss": 0.4158, |
| "step": 14500 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 3.554600171969046e-05, |
| "loss": 0.4113, |
| "step": 15000 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 3.339638865004299e-05, |
| "loss": 0.4131, |
| "step": 15500 |
| }, |
| { |
| "epoch": 3.44, |
| "learning_rate": 3.124677558039553e-05, |
| "loss": 0.4176, |
| "step": 16000 |
| }, |
| { |
| "epoch": 3.55, |
| "learning_rate": 2.9097162510748066e-05, |
| "loss": 0.4179, |
| "step": 16500 |
| }, |
| { |
| "epoch": 3.65, |
| "learning_rate": 2.6947549441100606e-05, |
| "loss": 0.4136, |
| "step": 17000 |
| }, |
| { |
| "epoch": 3.76, |
| "learning_rate": 2.479793637145314e-05, |
| "loss": 0.4158, |
| "step": 17500 |
| }, |
| { |
| "epoch": 3.87, |
| "learning_rate": 2.2648323301805677e-05, |
| "loss": 0.4146, |
| "step": 18000 |
| }, |
| { |
| "epoch": 3.98, |
| "learning_rate": 2.0498710232158214e-05, |
| "loss": 0.4142, |
| "step": 18500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_gen_len": 22.9162, |
| "eval_loss": 0.4507947266101837, |
| "eval_rouge1": 72.7951, |
| "eval_rouge2": 54.1782, |
| "eval_rougeL": 67.7093, |
| "eval_rougeLsum": 67.7632, |
| "eval_runtime": 376.0977, |
| "eval_samples_per_second": 0.508, |
| "eval_steps_per_second": 0.016, |
| "step": 18608 |
| }, |
| { |
| "epoch": 4.08, |
| "learning_rate": 1.8349097162510747e-05, |
| "loss": 0.4057, |
| "step": 19000 |
| }, |
| { |
| "epoch": 4.19, |
| "learning_rate": 1.6199484092863284e-05, |
| "loss": 0.4059, |
| "step": 19500 |
| }, |
| { |
| "epoch": 4.3, |
| "learning_rate": 1.4054170249355117e-05, |
| "loss": 0.4055, |
| "step": 20000 |
| }, |
| { |
| "epoch": 4.41, |
| "learning_rate": 1.1904557179707654e-05, |
| "loss": 0.4022, |
| "step": 20500 |
| }, |
| { |
| "epoch": 4.51, |
| "learning_rate": 9.754944110060189e-06, |
| "loss": 0.4105, |
| "step": 21000 |
| }, |
| { |
| "epoch": 4.62, |
| "learning_rate": 7.605331040412726e-06, |
| "loss": 0.405, |
| "step": 21500 |
| }, |
| { |
| "epoch": 4.73, |
| "learning_rate": 5.455717970765263e-06, |
| "loss": 0.4007, |
| "step": 22000 |
| }, |
| { |
| "epoch": 4.84, |
| "learning_rate": 3.3061049011177993e-06, |
| "loss": 0.4093, |
| "step": 22500 |
| }, |
| { |
| "epoch": 4.94, |
| "learning_rate": 1.1564918314703356e-06, |
| "loss": 0.4011, |
| "step": 23000 |
| } |
| ], |
| "max_steps": 23260, |
| "num_train_epochs": 5, |
| "total_flos": 7.011060475428864e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
