| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.0606060606060606, |
| "global_step": 3000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 1.6203636363636364e-05, |
| "loss": 0.8991, |
| "step": 494 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7804532577903682, |
| "eval_f1": 0.7820792833566528, |
| "eval_loss": 0.6184162497520447, |
| "eval_runtime": 88.3049, |
| "eval_samples_per_second": 47.97, |
| "eval_steps_per_second": 2.401, |
| "step": 495 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 1.440727272727273e-05, |
| "loss": 0.5228, |
| "step": 988 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8182247403210576, |
| "eval_f1": 0.8195587712666443, |
| "eval_loss": 0.5347467660903931, |
| "eval_runtime": 88.3154, |
| "eval_samples_per_second": 47.964, |
| "eval_steps_per_second": 2.4, |
| "step": 990 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 1.2610909090909091e-05, |
| "loss": 0.3661, |
| "step": 1482 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8458451369216242, |
| "eval_f1": 0.8456365209622985, |
| "eval_loss": 0.47167500853538513, |
| "eval_runtime": 88.276, |
| "eval_samples_per_second": 47.986, |
| "eval_steps_per_second": 2.402, |
| "step": 1485 |
| }, |
| { |
| "epoch": 3.99, |
| "learning_rate": 1.0814545454545455e-05, |
| "loss": 0.2528, |
| "step": 1976 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8359301227573183, |
| "eval_f1": 0.8334971747863884, |
| "eval_loss": 0.5231624245643616, |
| "eval_runtime": 88.232, |
| "eval_samples_per_second": 48.01, |
| "eval_steps_per_second": 2.403, |
| "step": 1980 |
| }, |
| { |
| "epoch": 4.99, |
| "learning_rate": 9.018181818181818e-06, |
| "loss": 0.1714, |
| "step": 2470 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8621340887629839, |
| "eval_f1": 0.8597728023734812, |
| "eval_loss": 0.5139923095703125, |
| "eval_runtime": 88.2994, |
| "eval_samples_per_second": 47.973, |
| "eval_steps_per_second": 2.401, |
| "step": 2475 |
| }, |
| { |
| "epoch": 5.99, |
| "learning_rate": 7.221818181818181e-06, |
| "loss": 0.1313, |
| "step": 2964 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8611898016997167, |
| "eval_f1": 0.8589456922670535, |
| "eval_loss": 0.6027271747589111, |
| "eval_runtime": 88.3228, |
| "eval_samples_per_second": 47.96, |
| "eval_steps_per_second": 2.4, |
| "step": 2970 |
| } |
| ], |
| "max_steps": 4950, |
| "num_train_epochs": 10, |
| "total_flos": 5479149586954968.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
