| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 3, |
| "global_step": 14, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0001, |
| "loss": 4.5023, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 9.85470908713026e-05, |
| "loss": 4.2546, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 9.42728012826605e-05, |
| "loss": 3.8535, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.43, |
| "eval_loss": 3.6483154296875, |
| "eval_runtime": 3.3549, |
| "eval_samples_per_second": 12.519, |
| "eval_steps_per_second": 1.788, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 8.742553740855506e-05, |
| "loss": 3.4696, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 7.840323733655778e-05, |
| "loss": 3.277, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 6.773024435212678e-05, |
| "loss": 2.9668, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.86, |
| "eval_loss": 2.703300952911377, |
| "eval_runtime": 3.3559, |
| "eval_samples_per_second": 12.515, |
| "eval_steps_per_second": 1.788, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 5.602683401276615e-05, |
| "loss": 2.5299, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 4.397316598723385e-05, |
| "loss": 2.406, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 3.226975564787322e-05, |
| "loss": 2.0197, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.29, |
| "eval_loss": 2.36472749710083, |
| "eval_runtime": 3.3547, |
| "eval_samples_per_second": 12.52, |
| "eval_steps_per_second": 1.789, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 2.1596762663442218e-05, |
| "loss": 2.2506, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 1.257446259144494e-05, |
| "loss": 1.9917, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 5.727198717339511e-06, |
| "loss": 2.3299, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.71, |
| "eval_loss": 2.217278003692627, |
| "eval_runtime": 3.354, |
| "eval_samples_per_second": 12.522, |
| "eval_steps_per_second": 1.789, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 1.4529091286973995e-06, |
| "loss": 1.8462, |
| "step": 13 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.0, |
| "loss": 1.9122, |
| "step": 14 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 14, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 501453414371328.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
