| { |
| "best_metric": 0.14741940796375275, |
| "best_model_checkpoint": "./trained_models/twitter-emotion-deberta-v3-base/checkpoint-500", |
| "epoch": 6.0, |
| "global_step": 1200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5, |
| "eval_accuracy": 0.8405, |
| "eval_loss": 0.5359936952590942, |
| "eval_runtime": 4.1757, |
| "eval_samples_per_second": 478.965, |
| "eval_steps_per_second": 5.987, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.915, |
| "eval_loss": 0.28240880370140076, |
| "eval_runtime": 4.2049, |
| "eval_samples_per_second": 475.638, |
| "eval_steps_per_second": 5.945, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.5, |
| "eval_accuracy": 0.93, |
| "eval_loss": 0.19999809563159943, |
| "eval_runtime": 4.2283, |
| "eval_samples_per_second": 473.002, |
| "eval_steps_per_second": 5.913, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.936, |
| "eval_loss": 0.13397051393985748, |
| "eval_runtime": 4.2488, |
| "eval_samples_per_second": 470.716, |
| "eval_steps_per_second": 5.884, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 2.916666666666667e-05, |
| "loss": 0.4142, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.5, |
| "eval_accuracy": 0.937, |
| "eval_loss": 0.14741940796375275, |
| "eval_runtime": 4.2278, |
| "eval_samples_per_second": 473.054, |
| "eval_steps_per_second": 5.913, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.936, |
| "eval_loss": 0.15366272628307343, |
| "eval_runtime": 4.2318, |
| "eval_samples_per_second": 472.612, |
| "eval_steps_per_second": 5.908, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.5, |
| "eval_accuracy": 0.939, |
| "eval_loss": 0.13712549209594727, |
| "eval_runtime": 4.2434, |
| "eval_samples_per_second": 471.315, |
| "eval_steps_per_second": 5.891, |
| "step": 700 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.941, |
| "eval_loss": 0.13440823554992676, |
| "eval_runtime": 4.2389, |
| "eval_samples_per_second": 471.816, |
| "eval_steps_per_second": 5.898, |
| "step": 800 |
| }, |
| { |
| "epoch": 4.5, |
| "eval_accuracy": 0.939, |
| "eval_loss": 0.13154806196689606, |
| "eval_runtime": 4.244, |
| "eval_samples_per_second": 471.257, |
| "eval_steps_per_second": 5.891, |
| "step": 900 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.1013, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.936, |
| "eval_loss": 0.15716207027435303, |
| "eval_runtime": 4.2453, |
| "eval_samples_per_second": 471.109, |
| "eval_steps_per_second": 5.889, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.5, |
| "eval_accuracy": 0.938, |
| "eval_loss": 0.15671509504318237, |
| "eval_runtime": 4.2362, |
| "eval_samples_per_second": 472.124, |
| "eval_steps_per_second": 5.902, |
| "step": 1100 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.939, |
| "eval_loss": 0.15347838401794434, |
| "eval_runtime": 4.2428, |
| "eval_samples_per_second": 471.385, |
| "eval_steps_per_second": 5.892, |
| "step": 1200 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 1200, |
| "total_flos": 6907037114880000.0, |
| "train_loss": 0.2273927664756775, |
| "train_runtime": 627.7316, |
| "train_samples_per_second": 152.932, |
| "train_steps_per_second": 1.912 |
| } |
| ], |
| "max_steps": 1200, |
| "num_train_epochs": 6, |
| "total_flos": 6907037114880000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
