| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "global_step": 5690, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.88, |
| "learning_rate": 1.8263620386643236e-05, |
| "loss": 0.693, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_runtime": 7.7102, |
| "eval_samples_per_second": 65.368, |
| "eval_steps_per_second": 8.171, |
| "step": 569 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 1.650615114235501e-05, |
| "loss": 0.4198, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_runtime": 7.6907, |
| "eval_samples_per_second": 65.533, |
| "eval_steps_per_second": 8.192, |
| "step": 1138 |
| }, |
| { |
| "epoch": 2.64, |
| "learning_rate": 1.4748681898066785e-05, |
| "loss": 0.3079, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_runtime": 7.8146, |
| "eval_samples_per_second": 64.494, |
| "eval_steps_per_second": 8.062, |
| "step": 1707 |
| }, |
| { |
| "epoch": 3.51, |
| "learning_rate": 1.299121265377856e-05, |
| "loss": 0.2031, |
| "step": 2000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_runtime": 7.6687, |
| "eval_samples_per_second": 65.721, |
| "eval_steps_per_second": 8.215, |
| "step": 2276 |
| }, |
| { |
| "epoch": 4.39, |
| "learning_rate": 1.1237258347978912e-05, |
| "loss": 0.1858, |
| "step": 2500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_runtime": 7.7223, |
| "eval_samples_per_second": 65.266, |
| "eval_steps_per_second": 8.158, |
| "step": 2845 |
| }, |
| { |
| "epoch": 5.27, |
| "learning_rate": 9.479789103690687e-06, |
| "loss": 0.1088, |
| "step": 3000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_runtime": 7.6837, |
| "eval_samples_per_second": 65.594, |
| "eval_steps_per_second": 8.199, |
| "step": 3414 |
| }, |
| { |
| "epoch": 6.15, |
| "learning_rate": 7.72231985940246e-06, |
| "loss": 0.086, |
| "step": 3500 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_runtime": 7.6991, |
| "eval_samples_per_second": 65.462, |
| "eval_steps_per_second": 8.183, |
| "step": 3983 |
| }, |
| { |
| "epoch": 7.03, |
| "learning_rate": 5.968365553602813e-06, |
| "loss": 0.0536, |
| "step": 4000 |
| }, |
| { |
| "epoch": 7.91, |
| "learning_rate": 4.214411247803164e-06, |
| "loss": 0.0433, |
| "step": 4500 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_runtime": 7.691, |
| "eval_samples_per_second": 65.531, |
| "eval_steps_per_second": 8.191, |
| "step": 4552 |
| }, |
| { |
| "epoch": 8.79, |
| "learning_rate": 2.4569420035149386e-06, |
| "loss": 0.0224, |
| "step": 5000 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_runtime": 7.6949, |
| "eval_samples_per_second": 65.498, |
| "eval_steps_per_second": 8.187, |
| "step": 5121 |
| }, |
| { |
| "epoch": 9.67, |
| "learning_rate": 6.994727592267137e-07, |
| "loss": 0.0135, |
| "step": 5500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_runtime": 7.6822, |
| "eval_samples_per_second": 65.607, |
| "eval_steps_per_second": 8.201, |
| "step": 5690 |
| } |
| ], |
| "max_steps": 5690, |
| "num_train_epochs": 10, |
| "total_flos": 2.111879700099072e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
