| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 12.173913043478262, |
| "global_step": 1400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.74, |
| "learning_rate": 1.891891891891892e-05, |
| "loss": 0.5364, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.74, |
| "eval_accuracy": 0.8382352941176471, |
| "eval_combined_score": 0.8622210953346856, |
| "eval_f1": 0.8862068965517241, |
| "eval_loss": 0.35622578859329224, |
| "eval_runtime": 3.0414, |
| "eval_samples_per_second": 134.148, |
| "eval_steps_per_second": 4.274, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 1.711711711711712e-05, |
| "loss": 0.3136, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.48, |
| "eval_accuracy": 0.8259803921568627, |
| "eval_combined_score": 0.8546979136482178, |
| "eval_f1": 0.883415435139573, |
| "eval_loss": 0.480543851852417, |
| "eval_runtime": 1.4071, |
| "eval_samples_per_second": 289.952, |
| "eval_steps_per_second": 9.239, |
| "step": 400 |
| }, |
| { |
| "epoch": 5.22, |
| "learning_rate": 1.5315315315315316e-05, |
| "loss": 0.1818, |
| "step": 600 |
| }, |
| { |
| "epoch": 5.22, |
| "eval_accuracy": 0.8627450980392157, |
| "eval_combined_score": 0.8808310327741204, |
| "eval_f1": 0.8989169675090252, |
| "eval_loss": 0.4389028251171112, |
| "eval_runtime": 1.4446, |
| "eval_samples_per_second": 282.425, |
| "eval_steps_per_second": 8.999, |
| "step": 600 |
| }, |
| { |
| "epoch": 6.96, |
| "learning_rate": 1.3513513513513515e-05, |
| "loss": 0.1187, |
| "step": 800 |
| }, |
| { |
| "epoch": 6.96, |
| "eval_accuracy": 0.8627450980392157, |
| "eval_combined_score": 0.8824215000685589, |
| "eval_f1": 0.9020979020979022, |
| "eval_loss": 0.46325385570526123, |
| "eval_runtime": 1.4574, |
| "eval_samples_per_second": 279.945, |
| "eval_steps_per_second": 8.92, |
| "step": 800 |
| }, |
| { |
| "epoch": 8.7, |
| "learning_rate": 1.1711711711711713e-05, |
| "loss": 0.0622, |
| "step": 1000 |
| }, |
| { |
| "epoch": 8.7, |
| "eval_accuracy": 0.8725490196078431, |
| "eval_combined_score": 0.8919059091213277, |
| "eval_f1": 0.9112627986348123, |
| "eval_loss": 0.8588500618934631, |
| "eval_runtime": 1.4112, |
| "eval_samples_per_second": 289.113, |
| "eval_steps_per_second": 9.212, |
| "step": 1000 |
| }, |
| { |
| "epoch": 10.43, |
| "learning_rate": 9.90990990990991e-06, |
| "loss": 0.0524, |
| "step": 1200 |
| }, |
| { |
| "epoch": 10.43, |
| "eval_accuracy": 0.8774509803921569, |
| "eval_combined_score": 0.8945558788886578, |
| "eval_f1": 0.9116607773851589, |
| "eval_loss": 0.6909387111663818, |
| "eval_runtime": 1.4612, |
| "eval_samples_per_second": 279.229, |
| "eval_steps_per_second": 8.897, |
| "step": 1200 |
| }, |
| { |
| "epoch": 12.17, |
| "learning_rate": 8.108108108108109e-06, |
| "loss": 0.043, |
| "step": 1400 |
| }, |
| { |
| "epoch": 12.17, |
| "eval_accuracy": 0.875, |
| "eval_combined_score": 0.8943527918781726, |
| "eval_f1": 0.9137055837563453, |
| "eval_loss": 0.876980185508728, |
| "eval_runtime": 1.4427, |
| "eval_samples_per_second": 282.811, |
| "eval_steps_per_second": 9.011, |
| "step": 1400 |
| } |
| ], |
| "max_steps": 2300, |
| "num_train_epochs": 20, |
| "total_flos": 3423856486686720.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
