| { |
| "best_metric": 0.5070422535211268, |
| "best_model_checkpoint": "roberta-Suggestions-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-423", |
| "epoch": 9.0, |
| "eval_steps": 500, |
| "global_step": 423, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.497709274291992, |
| "learning_rate": 9.437100067448849e-06, |
| "loss": 0.1893, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9589216944801027, |
| "eval_f1": 0.0, |
| "eval_loss": 0.026493968442082405, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 5.6135, |
| "eval_samples_per_second": 138.772, |
| "eval_steps_per_second": 8.729, |
| "step": 47 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.9029781818389893, |
| "learning_rate": 8.388533393287865e-06, |
| "loss": 0.1602, |
| "step": 94 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9589216944801027, |
| "eval_f1": 0.0, |
| "eval_loss": 0.07899215817451477, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 6.0685, |
| "eval_samples_per_second": 128.367, |
| "eval_steps_per_second": 8.074, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.2197129726409912, |
| "learning_rate": 7.339966719126881e-06, |
| "loss": 0.1275, |
| "step": 141 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9589216944801027, |
| "eval_f1": 0.0, |
| "eval_loss": 0.02892177551984787, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 5.6576, |
| "eval_samples_per_second": 137.69, |
| "eval_steps_per_second": 8.661, |
| "step": 141 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 5.551578044891357, |
| "learning_rate": 6.291400044965899e-06, |
| "loss": 0.1118, |
| "step": 188 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9614890885750963, |
| "eval_f1": 0.11764705882352941, |
| "eval_loss": 0.04150189831852913, |
| "eval_precision": 1.0, |
| "eval_recall": 0.0625, |
| "eval_runtime": 5.84, |
| "eval_samples_per_second": 133.391, |
| "eval_steps_per_second": 8.39, |
| "step": 188 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.566047430038452, |
| "learning_rate": 5.242833370804916e-06, |
| "loss": 0.0969, |
| "step": 235 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9602053915275995, |
| "eval_f1": 0.06060606060606061, |
| "eval_loss": 0.02676660381257534, |
| "eval_precision": 1.0, |
| "eval_recall": 0.03125, |
| "eval_runtime": 5.7945, |
| "eval_samples_per_second": 134.439, |
| "eval_steps_per_second": 8.456, |
| "step": 235 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 11.057209968566895, |
| "learning_rate": 4.194266696643932e-06, |
| "loss": 0.0889, |
| "step": 282 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9563543003851092, |
| "eval_f1": 0.2608695652173913, |
| "eval_loss": 0.02810371294617653, |
| "eval_precision": 0.42857142857142855, |
| "eval_recall": 0.1875, |
| "eval_runtime": 5.5694, |
| "eval_samples_per_second": 139.872, |
| "eval_steps_per_second": 8.798, |
| "step": 282 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 21.280832290649414, |
| "learning_rate": 3.1457000224829495e-06, |
| "loss": 0.1033, |
| "step": 329 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9589216944801027, |
| "eval_f1": 0.23809523809523808, |
| "eval_loss": 0.023050550371408463, |
| "eval_precision": 0.5, |
| "eval_recall": 0.15625, |
| "eval_runtime": 5.7361, |
| "eval_samples_per_second": 135.806, |
| "eval_steps_per_second": 8.542, |
| "step": 329 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 12.596846580505371, |
| "learning_rate": 2.097133348321966e-06, |
| "loss": 0.0846, |
| "step": 376 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9563543003851092, |
| "eval_f1": 0.48484848484848486, |
| "eval_loss": 0.06229134276509285, |
| "eval_precision": 0.47058823529411764, |
| "eval_recall": 0.5, |
| "eval_runtime": 5.9283, |
| "eval_samples_per_second": 131.404, |
| "eval_steps_per_second": 8.265, |
| "step": 376 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 10.026678085327148, |
| "learning_rate": 1.048566674160983e-06, |
| "loss": 0.0636, |
| "step": 423 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9550706033376123, |
| "eval_f1": 0.5070422535211268, |
| "eval_loss": 0.07518932968378067, |
| "eval_precision": 0.46153846153846156, |
| "eval_recall": 0.5625, |
| "eval_runtime": 5.4962, |
| "eval_samples_per_second": 141.734, |
| "eval_steps_per_second": 8.915, |
| "step": 423 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 470, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4003551654358872.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
