| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.6824395373291272, |
| "eval_steps": 100.0, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "learning_rate": 5e-06, |
| "loss": 4.1311, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 1e-05, |
| "loss": 4.0983, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 1.5e-05, |
| "loss": 3.9944, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 2e-05, |
| "loss": 3.8495, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 2.5e-05, |
| "loss": 3.5944, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 3e-05, |
| "loss": 3.1649, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 3.5e-05, |
| "loss": 3.0072, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 4e-05, |
| "loss": 2.9697, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 4.5e-05, |
| "loss": 2.8497, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 5e-05, |
| "loss": 2.8376, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 4.998942375205502e-05, |
| "loss": 2.8255, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 4.995770395678171e-05, |
| "loss": 2.7066, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 4.990486745229364e-05, |
| "loss": 2.6717, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 4.983095894354858e-05, |
| "loss": 2.6093, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 4.973604096452361e-05, |
| "loss": 2.588, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 4.962019382530521e-05, |
| "loss": 2.5881, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 4.948351554413879e-05, |
| "loss": 2.4645, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 4.9326121764495596e-05, |
| "loss": 2.4118, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 4.914814565722671e-05, |
| "loss": 2.5078, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 4.894973780788722e-05, |
| "loss": 2.3461, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1180, |
| "num_train_epochs": 10, |
| "save_steps": 100, |
| "total_flos": 1.733059225580667e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
