| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 13038, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12, |
| "learning_rate": 4.808252799509128e-05, |
| "loss": 3.9076, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 4.6165055990182545e-05, |
| "loss": 3.6869, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 4.424758398527381e-05, |
| "loss": 3.6372, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 4.233011198036509e-05, |
| "loss": 3.612, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 4.041263997545636e-05, |
| "loss": 3.5812, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 3.849516797054763e-05, |
| "loss": 3.5516, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 3.6577695965638905e-05, |
| "loss": 3.5391, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 3.466022396073017e-05, |
| "loss": 3.5271, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 3.274275195582145e-05, |
| "loss": 3.4532, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 3.0825279950912716e-05, |
| "loss": 3.2922, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 2.890780794600399e-05, |
| "loss": 3.3032, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 2.6990335941095262e-05, |
| "loss": 3.3062, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 2.507286393618653e-05, |
| "loss": 3.319, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 2.3155391931277805e-05, |
| "loss": 3.2838, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.73, |
| "learning_rate": 2.1237919926369076e-05, |
| "loss": 3.2729, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 1.9320447921460347e-05, |
| "loss": 3.2908, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 1.740297591655162e-05, |
| "loss": 3.2716, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 1.548550391164289e-05, |
| "loss": 3.1832, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 1.3568031906734163e-05, |
| "loss": 3.13, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 1.1650559901825433e-05, |
| "loss": 3.1337, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 9.733087896916706e-06, |
| "loss": 3.1165, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 7.815615892007977e-06, |
| "loss": 3.1283, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 5.8981438870992485e-06, |
| "loss": 3.1381, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 3.980671882190521e-06, |
| "loss": 3.1443, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 2.0631998772817916e-06, |
| "loss": 3.1399, |
| "step": 12500 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 1.4572787237306336e-07, |
| "loss": 3.1344, |
| "step": 13000 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 13038, |
| "total_flos": 2.6925692092416e+16, |
| "train_runtime": 5223.9033, |
| "train_samples_per_second": 2.496 |
| } |
| ], |
| "max_steps": 13038, |
| "num_train_epochs": 3, |
| "total_flos": 2.6925692092416e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
