| { | |
| "best_metric": 71.7689855624189, | |
| "best_model_checkpoint": "/home/jcanete/ft-data/all_results/mlqa/roberta_base_bne/epochs_3_bs_64_lr_5e-5/checkpoint-2100", | |
| "epoch": 3.0, | |
| "global_step": 3849, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23, | |
| "eval_exact_match": 42.8, | |
| "eval_f1": 66.07691845266821, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.3517796830345545e-05, | |
| "loss": 2.2125, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_exact_match": 42.4, | |
| "eval_f1": 67.60252707997819, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_exact_match": 44.2, | |
| "eval_f1": 68.22127636863422, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.7022603273577556e-05, | |
| "loss": 1.8138, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_exact_match": 45.0, | |
| "eval_f1": 70.7168308464295, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.052740971680956e-05, | |
| "loss": 1.5408, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_exact_match": 44.2, | |
| "eval_f1": 69.58175791833233, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_exact_match": 43.6, | |
| "eval_f1": 69.82509104561767, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.403221616004157e-05, | |
| "loss": 1.2868, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_exact_match": 47.0, | |
| "eval_f1": 71.7689855624189, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_exact_match": 44.2, | |
| "eval_f1": 69.13446111576798, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.7537022603273577e-05, | |
| "loss": 1.2713, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_exact_match": 42.0, | |
| "eval_f1": 68.23957701346676, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.1041829046505586e-05, | |
| "loss": 0.9214, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_exact_match": 43.2, | |
| "eval_f1": 70.51423374645961, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_exact_match": 43.0, | |
| "eval_f1": 69.77814728542101, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.546635489737595e-06, | |
| "loss": 0.8332, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_exact_match": 42.0, | |
| "eval_f1": 68.99822059948373, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 3849, | |
| "total_flos": 5.458154461745472e+16, | |
| "train_loss": 1.3586923545228875, | |
| "train_runtime": 1361.6722, | |
| "train_samples_per_second": 180.792, | |
| "train_steps_per_second": 2.827 | |
| } | |
| ], | |
| "max_steps": 3849, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.458154461745472e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |