| { | |
| "best_metric": 0.976475715637207, | |
| "best_model_checkpoint": "microsoft-swin-base-patch4-window7-224_bert-base-multilingual-cased_bert-base-multilingual-cased/checkpoint-3864", | |
| "epoch": 6.0, | |
| "global_step": 3864, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.923136645962734e-05, | |
| "loss": 2.2925, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6365079879760742, | |
| "eval_runtime": 232.7485, | |
| "eval_samples_per_second": 11.068, | |
| "eval_steps_per_second": 0.692, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3.845496894409938e-05, | |
| "loss": 1.4969, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.3718241453170776, | |
| "eval_runtime": 40.4125, | |
| "eval_samples_per_second": 63.743, | |
| "eval_steps_per_second": 3.984, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 3.7678571428571433e-05, | |
| "loss": 1.2926, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.1062968969345093, | |
| "eval_runtime": 40.4904, | |
| "eval_samples_per_second": 63.62, | |
| "eval_steps_per_second": 3.976, | |
| "step": 1932 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.690217391304348e-05, | |
| "loss": 1.1515, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 3.612577639751553e-05, | |
| "loss": 1.0376, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0416237115859985, | |
| "eval_runtime": 40.3883, | |
| "eval_samples_per_second": 63.781, | |
| "eval_steps_per_second": 3.986, | |
| "step": 2576 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 3.534937888198758e-05, | |
| "loss": 0.9386, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.0240283012390137, | |
| "eval_runtime": 40.487, | |
| "eval_samples_per_second": 63.625, | |
| "eval_steps_per_second": 3.977, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 3.4572981366459633e-05, | |
| "loss": 0.867, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.976475715637207, | |
| "eval_runtime": 40.4063, | |
| "eval_samples_per_second": 63.752, | |
| "eval_steps_per_second": 3.985, | |
| "step": 3864 | |
| } | |
| ], | |
| "max_steps": 25760, | |
| "num_train_epochs": 40, | |
| "total_flos": 1.1256086855275315e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |