| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.959422903516682, |
| "global_step": 11000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.23, |
| "learning_rate": 1.909828674481515e-05, |
| "loss": 2.3025, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 1.81965734896303e-05, |
| "loss": 1.9624, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 1.729486023444545e-05, |
| "loss": 1.8381, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 1.6393146979260597e-05, |
| "loss": 1.7487, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.6010558605194092, |
| "eval_runtime": 7.739, |
| "eval_samples_per_second": 1142.27, |
| "eval_steps_per_second": 142.784, |
| "step": 2218 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 1.5491433724075746e-05, |
| "loss": 1.699, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 1.4589720468890894e-05, |
| "loss": 1.657, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 1.3688007213706042e-05, |
| "loss": 1.6196, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 1.2786293958521191e-05, |
| "loss": 1.5819, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.468666672706604, |
| "eval_runtime": 8.211, |
| "eval_samples_per_second": 1076.611, |
| "eval_steps_per_second": 134.576, |
| "step": 4436 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 1.1884580703336339e-05, |
| "loss": 1.562, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 1.098286744815149e-05, |
| "loss": 1.54, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 1.0081154192966638e-05, |
| "loss": 1.5266, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.71, |
| "learning_rate": 9.179440937781785e-06, |
| "loss": 1.5093, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 8.277727682596934e-06, |
| "loss": 1.4967, |
| "step": 6500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.411802887916565, |
| "eval_runtime": 8.223, |
| "eval_samples_per_second": 1075.038, |
| "eval_steps_per_second": 134.38, |
| "step": 6654 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 7.376014427412083e-06, |
| "loss": 1.4714, |
| "step": 7000 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 6.474301172227232e-06, |
| "loss": 1.4786, |
| "step": 7500 |
| }, |
| { |
| "epoch": 3.61, |
| "learning_rate": 5.572587917042381e-06, |
| "loss": 1.4602, |
| "step": 8000 |
| }, |
| { |
| "epoch": 3.83, |
| "learning_rate": 4.670874661857529e-06, |
| "loss": 1.4769, |
| "step": 8500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 1.383550763130188, |
| "eval_runtime": 8.2365, |
| "eval_samples_per_second": 1073.27, |
| "eval_steps_per_second": 134.159, |
| "step": 8872 |
| }, |
| { |
| "epoch": 4.06, |
| "learning_rate": 3.7691614066726782e-06, |
| "loss": 1.441, |
| "step": 9000 |
| }, |
| { |
| "epoch": 4.28, |
| "learning_rate": 2.867448151487827e-06, |
| "loss": 1.4561, |
| "step": 9500 |
| }, |
| { |
| "epoch": 4.51, |
| "learning_rate": 1.9657348963029757e-06, |
| "loss": 1.4494, |
| "step": 10000 |
| }, |
| { |
| "epoch": 4.73, |
| "learning_rate": 1.0640216411181244e-06, |
| "loss": 1.4381, |
| "step": 10500 |
| }, |
| { |
| "epoch": 4.96, |
| "learning_rate": 1.6230838593327323e-07, |
| "loss": 1.4314, |
| "step": 11000 |
| } |
| ], |
| "max_steps": 11090, |
| "num_train_epochs": 5, |
| "total_flos": 561354220339200.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
