| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 6246, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.24, |
| "learning_rate": 4.599743836055075e-05, |
| "loss": 0.0731, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 4.1994876721101504e-05, |
| "loss": 0.0345, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 3.7992315081652255e-05, |
| "loss": 0.0299, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 3.398975344220301e-05, |
| "loss": 0.027, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 2.998719180275376e-05, |
| "loss": 0.0199, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 2.5984630163304517e-05, |
| "loss": 0.0183, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 2.1982068523855268e-05, |
| "loss": 0.018, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 1.797950688440602e-05, |
| "loss": 0.0175, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 1.3976945244956775e-05, |
| "loss": 0.0132, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 9.974383605507526e-06, |
| "loss": 0.0114, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.64, |
| "learning_rate": 5.971821966058277e-06, |
| "loss": 0.0108, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 1.96926032660903e-06, |
| "loss": 0.0105, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 6246, |
| "total_flos": 6623681170117440.0, |
| "train_loss": 0.02315408722391657, |
| "train_runtime": 2017.0522, |
| "train_samples_per_second": 49.534, |
| "train_steps_per_second": 3.097 |
| } |
| ], |
| "max_steps": 6246, |
| "num_train_epochs": 3, |
| "total_flos": 6623681170117440.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
