| { | |
| "best_metric": 0.35333333333333333, | |
| "best_model_checkpoint": "nli_results/10k_test3/models/canine_s/checkpoint-625", | |
| "epoch": 2.9952, | |
| "global_step": 936, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.99465811965812e-05, | |
| "loss": 1.2375, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.465811965811966e-05, | |
| "loss": 1.1012, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.931623931623932e-05, | |
| "loss": 1.1001, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.397435897435898e-05, | |
| "loss": 1.1006, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.32466666666666666, | |
| "eval_f1_weighted": 0.15914712296594533, | |
| "eval_loss": 1.1008782386779785, | |
| "eval_precision_weighted": 0.10540844444444444, | |
| "eval_recall_weighted": 0.32466666666666666, | |
| "eval_runtime": 5.5832, | |
| "eval_samples_per_second": 268.662, | |
| "eval_steps_per_second": 67.165, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.863247863247863e-05, | |
| "loss": 1.0986, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.3290598290598293e-05, | |
| "loss": 1.0995, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.794871794871795e-05, | |
| "loss": 1.1002, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.35333333333333333, | |
| "eval_f1_weighted": 0.1844991789819376, | |
| "eval_loss": 1.098054051399231, | |
| "eval_precision_weighted": 0.12484444444444445, | |
| "eval_recall_weighted": 0.35333333333333333, | |
| "eval_runtime": 5.4579, | |
| "eval_samples_per_second": 274.833, | |
| "eval_steps_per_second": 68.708, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.2606837606837608e-05, | |
| "loss": 1.0994, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.264957264957266e-06, | |
| "loss": 1.099, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.9230769230769234e-06, | |
| "loss": 1.0988, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.32466666666666666, | |
| "eval_f1_weighted": 0.15914712296594533, | |
| "eval_loss": 1.0987415313720703, | |
| "eval_precision_weighted": 0.10540844444444444, | |
| "eval_recall_weighted": 0.32466666666666666, | |
| "eval_runtime": 5.312, | |
| "eval_samples_per_second": 282.382, | |
| "eval_steps_per_second": 70.595, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 936, | |
| "total_flos": 5792280106446720.0, | |
| "train_loss": 1.099813917763213, | |
| "train_runtime": 452.5487, | |
| "train_samples_per_second": 66.291, | |
| "train_steps_per_second": 2.068 | |
| } | |
| ], | |
| "max_steps": 936, | |
| "num_train_epochs": 3, | |
| "total_flos": 5792280106446720.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |