| { |
| "best_metric": 0.6624430418014526, |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_cola_128/checkpoint-1669", |
| "epoch": 6.0, |
| "global_step": 10014, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 4.9e-05, |
| "loss": 0.5456, |
| "step": 1669 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.6624430418014526, |
| "eval_matthews_correlation": 0.06184591421174734, |
| "eval_runtime": 1.5166, |
| "eval_samples_per_second": 687.706, |
| "eval_steps_per_second": 5.934, |
| "step": 1669 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.8e-05, |
| "loss": 0.4572, |
| "step": 3338 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.777407169342041, |
| "eval_matthews_correlation": 0.051399018194061875, |
| "eval_runtime": 1.5185, |
| "eval_samples_per_second": 686.884, |
| "eval_steps_per_second": 5.927, |
| "step": 3338 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.7e-05, |
| "loss": 0.419, |
| "step": 5007 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.8468864560127258, |
| "eval_matthews_correlation": 0.09306306856112183, |
| "eval_runtime": 1.5273, |
| "eval_samples_per_second": 682.882, |
| "eval_steps_per_second": 5.893, |
| "step": 5007 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.3649, |
| "step": 6676 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.8748074769973755, |
| "eval_matthews_correlation": 0.10111280260891091, |
| "eval_runtime": 1.7031, |
| "eval_samples_per_second": 612.425, |
| "eval_steps_per_second": 5.285, |
| "step": 6676 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.5e-05, |
| "loss": 0.3117, |
| "step": 8345 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 1.0731576681137085, |
| "eval_matthews_correlation": 0.08244224996771606, |
| "eval_runtime": 1.5249, |
| "eval_samples_per_second": 683.964, |
| "eval_steps_per_second": 5.902, |
| "step": 8345 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.2698, |
| "step": 10014 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 1.2173097133636475, |
| "eval_matthews_correlation": 0.0618342291155662, |
| "eval_runtime": 1.5181, |
| "eval_samples_per_second": 687.026, |
| "eval_steps_per_second": 5.928, |
| "step": 10014 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 10014, |
| "total_flos": 3.054770256347136e+16, |
| "train_loss": 0.39469508008612164, |
| "train_runtime": 6179.6216, |
| "train_samples_per_second": 1728.334, |
| "train_steps_per_second": 13.504 |
| } |
| ], |
| "max_steps": 83450, |
| "num_train_epochs": 50, |
| "total_flos": 3.054770256347136e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
