| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 12500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.992727272727273e-05, | |
| "loss": 1.1069, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9854545454545456e-05, | |
| "loss": 1.1657, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9781818181818184e-05, | |
| "loss": 1.1288, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.970909090909091e-05, | |
| "loss": 1.1395, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.963636363636364e-05, | |
| "loss": 1.1613, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.9563636363636366e-05, | |
| "loss": 1.149, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.9490909090909093e-05, | |
| "loss": 1.1539, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.941818181818182e-05, | |
| "loss": 1.1561, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.9345454545454548e-05, | |
| "loss": 1.1793, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.9272727272727275e-05, | |
| "loss": 1.1544, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 1.1414, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.912727272727273e-05, | |
| "loss": 1.1439, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.9054545454545457e-05, | |
| "loss": 1.1691, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.8981818181818185e-05, | |
| "loss": 1.1362, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.8909090909090912e-05, | |
| "loss": 1.1434, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8836363636363636e-05, | |
| "loss": 1.1652, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.8763636363636367e-05, | |
| "loss": 1.1717, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8690909090909094e-05, | |
| "loss": 1.135, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.861818181818182e-05, | |
| "loss": 1.1031, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.8545454545454545e-05, | |
| "loss": 1.1322, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.8472727272727273e-05, | |
| "loss": 1.1726, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 1.1472, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.832727272727273e-05, | |
| "loss": 1.1489, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.8254545454545455e-05, | |
| "loss": 1.1528, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 1.1203, | |
| "step": 12500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 137500, | |
| "num_train_epochs": 11, | |
| "save_steps": 500, | |
| "total_flos": 8443388560158720.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |