{ "best_metric": null, "best_model_checkpoint": null, "epoch": 12.0, "eval_steps": 500, "global_step": 2544, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "learning_rate": 9.95e-05, "loss": 6.3714, "step": 212 }, { "epoch": 1.0, "eval_loss": 5.850927352905273, "eval_runtime": 3.8282, "eval_samples_per_second": 176.584, "eval_steps_per_second": 22.204, "step": 212 }, { "epoch": 2.0, "learning_rate": 9.900000000000001e-05, "loss": 5.5438, "step": 424 }, { "epoch": 2.0, "eval_loss": 4.862037658691406, "eval_runtime": 3.7425, "eval_samples_per_second": 180.626, "eval_steps_per_second": 22.712, "step": 424 }, { "epoch": 3.0, "learning_rate": 9.850000000000001e-05, "loss": 4.6993, "step": 636 }, { "epoch": 3.0, "eval_loss": 4.018372058868408, "eval_runtime": 4.0424, "eval_samples_per_second": 167.229, "eval_steps_per_second": 21.027, "step": 636 }, { "epoch": 4.0, "learning_rate": 9.8e-05, "loss": 3.967, "step": 848 }, { "epoch": 4.0, "eval_loss": 3.290557384490967, "eval_runtime": 4.3933, "eval_samples_per_second": 153.872, "eval_steps_per_second": 19.348, "step": 848 }, { "epoch": 5.0, "learning_rate": 9.75e-05, "loss": 3.305, "step": 1060 }, { "epoch": 5.0, "eval_loss": 2.6497254371643066, "eval_runtime": 4.3562, "eval_samples_per_second": 155.182, "eval_steps_per_second": 19.513, "step": 1060 }, { "epoch": 6.0, "learning_rate": 9.7e-05, "loss": 2.7185, "step": 1272 }, { "epoch": 6.0, "eval_loss": 2.1158342361450195, "eval_runtime": 4.5634, "eval_samples_per_second": 148.135, "eval_steps_per_second": 18.626, "step": 1272 }, { "epoch": 7.0, "learning_rate": 9.65e-05, "loss": 2.2181, "step": 1484 }, { "epoch": 7.0, "eval_loss": 1.6882902383804321, "eval_runtime": 4.3232, "eval_samples_per_second": 156.367, "eval_steps_per_second": 19.662, "step": 1484 }, { "epoch": 8.0, "learning_rate": 9.6e-05, "loss": 1.8106, "step": 1696 }, { "epoch": 8.0, "eval_loss": 1.3730388879776, "eval_runtime": 4.3486, "eval_samples_per_second": 155.451, "eval_steps_per_second": 19.546, "step": 1696 }, { "epoch": 9.0, "learning_rate": 9.55e-05, "loss": 1.497, "step": 1908 }, { "epoch": 9.0, "eval_loss": 1.142008900642395, "eval_runtime": 4.2743, "eval_samples_per_second": 158.154, "eval_steps_per_second": 19.886, "step": 1908 }, { "epoch": 10.0, "learning_rate": 9.5e-05, "loss": 1.2526, "step": 2120 }, { "epoch": 10.0, "eval_loss": 0.9753935933113098, "eval_runtime": 4.2134, "eval_samples_per_second": 160.44, "eval_steps_per_second": 20.174, "step": 2120 }, { "epoch": 11.0, "learning_rate": 9.449999999999999e-05, "loss": 1.0576, "step": 2332 }, { "epoch": 11.0, "eval_loss": 0.8463678956031799, "eval_runtime": 4.432, "eval_samples_per_second": 152.527, "eval_steps_per_second": 19.179, "step": 2332 }, { "epoch": 12.0, "learning_rate": 9.4e-05, "loss": 0.8965, "step": 2544 }, { "epoch": 12.0, "eval_loss": 0.7349700927734375, "eval_runtime": 4.5659, "eval_samples_per_second": 148.054, "eval_steps_per_second": 18.616, "step": 2544 } ], "logging_steps": 500, "max_steps": 42400, "num_train_epochs": 200, "save_steps": 500, "total_flos": 3419356374609576.0, "trial_name": null, "trial_params": null }