| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9880715705765408, | |
| "eval_steps": 250, | |
| "global_step": 750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.349799732977303e-05, | |
| "loss": 1.7061, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.182910547396529e-05, | |
| "loss": 1.641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0160213618157546e-05, | |
| "loss": 1.6228, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.84913217623498e-05, | |
| "loss": 1.6018, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.6822429906542056e-05, | |
| "loss": 1.5884, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.6648187637329102, | |
| "eval_runtime": 17.075, | |
| "eval_samples_per_second": 11.713, | |
| "eval_steps_per_second": 1.464, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.5153538050734314e-05, | |
| "loss": 1.5793, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.348464619492657e-05, | |
| "loss": 1.5768, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.1815754339118826e-05, | |
| "loss": 1.57, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.0146862483311081e-05, | |
| "loss": 1.5642, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 8.477970627503338e-06, | |
| "loss": 1.5607, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.6562799215316772, | |
| "eval_runtime": 17.0881, | |
| "eval_samples_per_second": 11.704, | |
| "eval_steps_per_second": 1.463, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 6.809078771695594e-06, | |
| "loss": 1.5598, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5.14018691588785e-06, | |
| "loss": 1.5577, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.471295060080107e-06, | |
| "loss": 1.5612, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.8024032042723633e-06, | |
| "loss": 1.5609, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.335113484646195e-07, | |
| "loss": 1.5528, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 1.653220772743225, | |
| "eval_runtime": 17.0774, | |
| "eval_samples_per_second": 11.711, | |
| "eval_steps_per_second": 1.464, | |
| "step": 750 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 754, | |
| "num_train_epochs": 2, | |
| "save_steps": 250, | |
| "total_flos": 2.6288263099853046e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |