| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3, | |
| "eval_steps": 10, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.4549098196392788e-05, | |
| "loss": 1.5765, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.4641923904418945, | |
| "eval_runtime": 221.9956, | |
| "eval_samples_per_second": 0.901, | |
| "eval_steps_per_second": 0.113, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.404809619238477e-05, | |
| "loss": 1.5681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.4410793781280518, | |
| "eval_runtime": 221.7333, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.3547094188376757e-05, | |
| "loss": 1.2801, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.4293081760406494, | |
| "eval_runtime": 221.7604, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.304609218436874e-05, | |
| "loss": 1.5474, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.430722951889038, | |
| "eval_runtime": 221.7555, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.2545090180360722e-05, | |
| "loss": 1.3972, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.4295932054519653, | |
| "eval_runtime": 221.7379, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.2044088176352705e-05, | |
| "loss": 1.578, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.425429344177246, | |
| "eval_runtime": 221.7329, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.1543086172344688e-05, | |
| "loss": 1.3322, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.4246026277542114, | |
| "eval_runtime": 221.7499, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.1042084168336674e-05, | |
| "loss": 1.4031, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.4232592582702637, | |
| "eval_runtime": 221.7409, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.054108216432866e-05, | |
| "loss": 1.454, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.4188882112503052, | |
| "eval_runtime": 221.7396, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.0040080160320643e-05, | |
| "loss": 1.4341, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.416797161102295, | |
| "eval_runtime": 221.7427, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.9539078156312626e-05, | |
| "loss": 1.4684, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.4176369905471802, | |
| "eval_runtime": 221.7309, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.903807615230461e-05, | |
| "loss": 1.2462, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.4165884256362915, | |
| "eval_runtime": 221.7346, | |
| "eval_samples_per_second": 0.902, | |
| "eval_steps_per_second": 0.113, | |
| "step": 120 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "total_flos": 2.072361959424e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |