| { |
| "best_metric": 0.04441085457801819, |
| "best_model_checkpoint": "trainCMDBERT-sample/checkpoint-30", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "grad_norm": 7.945383071899414, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.6922, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 4.711484909057617, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.6868, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 7.974453926086426, |
| "learning_rate": 5e-05, |
| "loss": 0.6604, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 6.878942966461182, |
| "learning_rate": 4.814814814814815e-05, |
| "loss": 0.7292, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 6.609418869018555, |
| "learning_rate": 4.62962962962963e-05, |
| "loss": 0.6536, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 4.901663303375244, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.6743, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 4.790696620941162, |
| "learning_rate": 4.259259259259259e-05, |
| "loss": 0.595, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 5.129704475402832, |
| "learning_rate": 4.074074074074074e-05, |
| "loss": 0.5059, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 13.14133358001709, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.7147, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 8.443601608276367, |
| "learning_rate": 3.7037037037037037e-05, |
| "loss": 0.4751, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 1.0, |
| "eval_auc": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.3918549418449402, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 1.5522, |
| "eval_samples_per_second": 12.885, |
| "eval_steps_per_second": 1.289, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.1, |
| "grad_norm": 5.978346824645996, |
| "learning_rate": 3.518518518518519e-05, |
| "loss": 0.4208, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 10.853551864624023, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.5508, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.3, |
| "grad_norm": 3.4875123500823975, |
| "learning_rate": 3.148148148148148e-05, |
| "loss": 0.2284, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 5.512720108032227, |
| "learning_rate": 2.962962962962963e-05, |
| "loss": 0.3199, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 8.866156578063965, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.2572, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 13.71770191192627, |
| "learning_rate": 2.5925925925925925e-05, |
| "loss": 0.3133, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.7, |
| "grad_norm": 2.18959379196167, |
| "learning_rate": 2.4074074074074074e-05, |
| "loss": 0.1026, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 2.2819249629974365, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.063, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.9, |
| "grad_norm": 3.038083553314209, |
| "learning_rate": 2.037037037037037e-05, |
| "loss": 0.1096, |
| "step": 19 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 4.494248867034912, |
| "learning_rate": 1.8518518518518518e-05, |
| "loss": 0.0653, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.95, |
| "eval_auc": 1.0, |
| "eval_f1": 0.9523809523809523, |
| "eval_loss": 0.19424112141132355, |
| "eval_precision": 0.9090909090909091, |
| "eval_recall": 1.0, |
| "eval_runtime": 1.5099, |
| "eval_samples_per_second": 13.246, |
| "eval_steps_per_second": 1.325, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.1, |
| "grad_norm": 3.483051061630249, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.0604, |
| "step": 21 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 0.8026891350746155, |
| "learning_rate": 1.4814814814814815e-05, |
| "loss": 0.026, |
| "step": 22 |
| }, |
| { |
| "epoch": 2.3, |
| "grad_norm": 1.3247548341751099, |
| "learning_rate": 1.2962962962962962e-05, |
| "loss": 0.0319, |
| "step": 23 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.4032141864299774, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.0164, |
| "step": 24 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 1.0784159898757935, |
| "learning_rate": 9.259259259259259e-06, |
| "loss": 0.0222, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 0.32401901483535767, |
| "learning_rate": 7.4074074074074075e-06, |
| "loss": 0.0132, |
| "step": 26 |
| }, |
| { |
| "epoch": 2.7, |
| "grad_norm": 8.892071723937988, |
| "learning_rate": 5.555555555555556e-06, |
| "loss": 0.0401, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.20014284551143646, |
| "learning_rate": 3.7037037037037037e-06, |
| "loss": 0.009, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.9, |
| "grad_norm": 0.24240027368068695, |
| "learning_rate": 1.8518518518518519e-06, |
| "loss": 0.0093, |
| "step": 29 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.1646367609500885, |
| "learning_rate": 0.0, |
| "loss": 0.0074, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.95, |
| "eval_auc": 1.0, |
| "eval_f1": 0.9523809523809523, |
| "eval_loss": 0.04441085457801819, |
| "eval_precision": 0.9090909090909091, |
| "eval_recall": 1.0, |
| "eval_runtime": 1.4953, |
| "eval_samples_per_second": 13.375, |
| "eval_steps_per_second": 1.337, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.01 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 15786663321600.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
