| { |
| "best_global_step": 410, |
| "best_metric": 0.6417577862739563, |
| "best_model_checkpoint": "distilbert_rand_10_v1_qnli/checkpoint-410", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 2460, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.7041937112808228, |
| "learning_rate": 4.9e-05, |
| "loss": 0.6652, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6221856123009335, |
| "eval_loss": 0.6417577862739563, |
| "eval_runtime": 2.397, |
| "eval_samples_per_second": 2279.084, |
| "eval_steps_per_second": 9.178, |
| "step": 410 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.7172274589538574, |
| "learning_rate": 4.8e-05, |
| "loss": 0.6296, |
| "step": 820 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6262127036426872, |
| "eval_loss": 0.6434317231178284, |
| "eval_runtime": 2.2158, |
| "eval_samples_per_second": 2465.421, |
| "eval_steps_per_second": 9.928, |
| "step": 820 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 3.370169162750244, |
| "learning_rate": 4.7e-05, |
| "loss": 0.5657, |
| "step": 1230 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.6324363902617609, |
| "eval_loss": 0.6625856757164001, |
| "eval_runtime": 2.2095, |
| "eval_samples_per_second": 2472.561, |
| "eval_steps_per_second": 9.957, |
| "step": 1230 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 4.301219940185547, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.4602, |
| "step": 1640 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.6296906461651107, |
| "eval_loss": 0.7295259833335876, |
| "eval_runtime": 2.2128, |
| "eval_samples_per_second": 2468.847, |
| "eval_steps_per_second": 9.942, |
| "step": 1640 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 4.016913890838623, |
| "learning_rate": 4.5e-05, |
| "loss": 0.344, |
| "step": 2050 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6214534138751602, |
| "eval_loss": 0.8669584393501282, |
| "eval_runtime": 2.2217, |
| "eval_samples_per_second": 2458.943, |
| "eval_steps_per_second": 9.902, |
| "step": 2050 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 7.9369893074035645, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.2451, |
| "step": 2460 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.6176093721398499, |
| "eval_loss": 1.0550340414047241, |
| "eval_runtime": 2.2096, |
| "eval_samples_per_second": 2472.442, |
| "eval_steps_per_second": 9.957, |
| "step": 2460 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 2460, |
| "total_flos": 4.162509821227622e+16, |
| "train_loss": 0.48498512516176795, |
| "train_runtime": 591.672, |
| "train_samples_per_second": 8851.441, |
| "train_steps_per_second": 34.648 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 20500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 5 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.162509821227622e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
