| { |
| "best_metric": 0.8314220183486238, |
| "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-1\\checkpoint-2108", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 2635, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 7.193342816186545e-05, |
| "loss": 1.1191, |
| "step": 527 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8061926605504587, |
| "eval_loss": 0.9445732831954956, |
| "eval_runtime": 1.8865, |
| "eval_samples_per_second": 462.238, |
| "eval_steps_per_second": 3.711, |
| "step": 527 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 5.994452346822122e-05, |
| "loss": 0.6346, |
| "step": 1054 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8279816513761468, |
| "eval_loss": 0.8901896476745605, |
| "eval_runtime": 1.7665, |
| "eval_samples_per_second": 493.618, |
| "eval_steps_per_second": 3.963, |
| "step": 1054 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.795561877457697e-05, |
| "loss": 0.4919, |
| "step": 1581 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8211009174311926, |
| "eval_loss": 0.9235907196998596, |
| "eval_runtime": 1.9102, |
| "eval_samples_per_second": 456.496, |
| "eval_steps_per_second": 3.665, |
| "step": 1581 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3.5966714080932725e-05, |
| "loss": 0.4192, |
| "step": 2108 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8314220183486238, |
| "eval_loss": 0.9573733806610107, |
| "eval_runtime": 1.9272, |
| "eval_samples_per_second": 452.465, |
| "eval_steps_per_second": 3.632, |
| "step": 2108 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 2.3977809387288486e-05, |
| "loss": 0.377, |
| "step": 2635 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8268348623853211, |
| "eval_loss": 0.9544126987457275, |
| "eval_runtime": 1.9749, |
| "eval_samples_per_second": 441.534, |
| "eval_steps_per_second": 3.544, |
| "step": 2635 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3689, |
| "num_train_epochs": 7, |
| "save_steps": 500, |
| "total_flos": 40452267650880.0, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.6227846651931359, |
| "learning_rate": 8.39223328555097e-05, |
| "num_train_epochs": 7, |
| "temperature": 4 |
| } |
| } |
|
|
