| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.797101449275362, |
| "eval_steps": 500, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.29, |
| "learning_rate": 6e-06, |
| "loss": 10.813, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 1.2e-05, |
| "loss": 9.0619, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 1.8e-05, |
| "loss": 6.7725, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 1.9227799227799228e-05, |
| "loss": 5.6929, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 1.806949806949807e-05, |
| "loss": 5.2432, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 1.6911196911196913e-05, |
| "loss": 5.0545, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 1.5752895752895755e-05, |
| "loss": 4.9437, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 1.4594594594594596e-05, |
| "loss": 4.8686, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 1.3436293436293437e-05, |
| "loss": 4.8206, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 1.227799227799228e-05, |
| "loss": 4.7745, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 1.111969111969112e-05, |
| "loss": 4.7536, |
| "step": 330 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 9.961389961389962e-06, |
| "loss": 4.7134, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.77, |
| "learning_rate": 8.803088803088804e-06, |
| "loss": 4.6985, |
| "step": 390 |
| }, |
| { |
| "epoch": 4.06, |
| "learning_rate": 7.644787644787645e-06, |
| "loss": 4.6877, |
| "step": 420 |
| }, |
| { |
| "epoch": 4.35, |
| "learning_rate": 6.486486486486487e-06, |
| "loss": 4.6685, |
| "step": 450 |
| }, |
| { |
| "epoch": 4.64, |
| "learning_rate": 5.328185328185329e-06, |
| "loss": 4.6536, |
| "step": 480 |
| }, |
| { |
| "epoch": 4.93, |
| "learning_rate": 4.16988416988417e-06, |
| "loss": 4.6641, |
| "step": 510 |
| }, |
| { |
| "epoch": 5.22, |
| "learning_rate": 3.011583011583012e-06, |
| "loss": 4.6487, |
| "step": 540 |
| }, |
| { |
| "epoch": 5.51, |
| "learning_rate": 1.8532818532818534e-06, |
| "loss": 4.6403, |
| "step": 570 |
| }, |
| { |
| "epoch": 5.8, |
| "learning_rate": 6.94980694980695e-07, |
| "loss": 4.6346, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 30, |
| "max_steps": 618, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 30, |
| "total_flos": 3.141346947760128e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
