{ "best_metric": 0.4269143342971802, "best_model_checkpoint": "/content/model/checkpoint-189", "epoch": 10.0, "eval_steps": 500, "global_step": 210, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "learning_rate": 9e-06, "loss": 0.6051, "step": 21 }, { "epoch": 1.0, "eval_f1": 0.6981023576768258, "eval_loss": 0.5369009375572205, "eval_runtime": 4.7612, "eval_samples_per_second": 476.145, "eval_steps_per_second": 59.649, "step": 21 }, { "epoch": 2.0, "learning_rate": 8.000000000000001e-06, "loss": 0.5209, "step": 42 }, { "epoch": 2.0, "eval_f1": 0.7298787210584344, "eval_loss": 0.4820566773414612, "eval_runtime": 1.7994, "eval_samples_per_second": 1259.862, "eval_steps_per_second": 157.83, "step": 42 }, { "epoch": 3.0, "learning_rate": 7e-06, "loss": 0.4766, "step": 63 }, { "epoch": 3.0, "eval_f1": 0.7651715039577837, "eval_loss": 0.45511141419410706, "eval_runtime": 1.453, "eval_samples_per_second": 1560.216, "eval_steps_per_second": 195.457, "step": 63 }, { "epoch": 4.0, "learning_rate": 6e-06, "loss": 0.4452, "step": 84 }, { "epoch": 4.0, "eval_f1": 0.7676130389064143, "eval_loss": 0.44256114959716797, "eval_runtime": 1.4814, "eval_samples_per_second": 1530.311, "eval_steps_per_second": 191.711, "step": 84 }, { "epoch": 5.0, "learning_rate": 5e-06, "loss": 0.4268, "step": 105 }, { "epoch": 5.0, "eval_f1": 0.7724583109198493, "eval_loss": 0.4344449043273926, "eval_runtime": 1.4719, "eval_samples_per_second": 1540.196, "eval_steps_per_second": 192.949, "step": 105 }, { "epoch": 6.0, "learning_rate": 4.000000000000001e-06, "loss": 0.4157, "step": 126 }, { "epoch": 6.0, "eval_f1": 0.7705263157894737, "eval_loss": 0.432775616645813, "eval_runtime": 1.5111, "eval_samples_per_second": 1500.278, "eval_steps_per_second": 187.948, "step": 126 }, { "epoch": 7.0, "learning_rate": 3e-06, "loss": 0.4091, "step": 147 }, { "epoch": 7.0, "eval_f1": 0.7769940314704288, "eval_loss": 0.42807161808013916, "eval_runtime": 1.9692, "eval_samples_per_second": 1151.231, "eval_steps_per_second": 144.221, "step": 147 }, { "epoch": 8.0, "learning_rate": 2.0000000000000003e-06, "loss": 0.4049, "step": 168 }, { "epoch": 8.0, "eval_f1": 0.7738853503184713, "eval_loss": 0.42762625217437744, "eval_runtime": 1.4553, "eval_samples_per_second": 1557.748, "eval_steps_per_second": 195.148, "step": 168 }, { "epoch": 9.0, "learning_rate": 1.0000000000000002e-06, "loss": 0.3984, "step": 189 }, { "epoch": 9.0, "eval_f1": 0.7751855779427359, "eval_loss": 0.4269143342971802, "eval_runtime": 1.4517, "eval_samples_per_second": 1561.613, "eval_steps_per_second": 195.632, "step": 189 }, { "epoch": 10.0, "learning_rate": 0.0, "loss": 0.3974, "step": 210 }, { "epoch": 10.0, "eval_f1": 0.7723919915700739, "eval_loss": 0.42761725187301636, "eval_runtime": 1.4549, "eval_samples_per_second": 1558.188, "eval_steps_per_second": 195.203, "step": 210 }, { "epoch": 10.0, "step": 210, "total_flos": 163389580070400.0, "train_loss": 0.45001178923107327, "train_runtime": 86.5922, "train_samples_per_second": 610.678, "train_steps_per_second": 2.425 } ], "logging_steps": 500, "max_steps": 210, "num_train_epochs": 10, "save_steps": 500, "total_flos": 163389580070400.0, "trial_name": null, "trial_params": null }