| { |
| "best_metric": 0.4501543343067169, |
| "best_model_checkpoint": "autotrain-qkfvr-4yrwe/checkpoint-100", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "grad_norm": 3.2349209785461426, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.6925, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 3.42258358001709, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.6949, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 1.1544133424758911, |
| "learning_rate": 2.5e-05, |
| "loss": 0.7045, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 4.767457962036133, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.6916, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 1.978225588798523, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.6937, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 4.386098384857178, |
| "learning_rate": 5e-05, |
| "loss": 0.6817, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 2.616386651992798, |
| "learning_rate": 4.9074074074074075e-05, |
| "loss": 0.6589, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 6.577281951904297, |
| "learning_rate": 4.814814814814815e-05, |
| "loss": 0.6352, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 5.725684642791748, |
| "learning_rate": 4.722222222222222e-05, |
| "loss": 0.6231, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 14.771023750305176, |
| "learning_rate": 4.62962962962963e-05, |
| "loss": 0.6771, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 6.239844799041748, |
| "learning_rate": 4.5370370370370374e-05, |
| "loss": 0.6031, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 5.879209995269775, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.3533, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 6.339338779449463, |
| "learning_rate": 4.351851851851852e-05, |
| "loss": 0.5966, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 16.186792373657227, |
| "learning_rate": 4.259259259259259e-05, |
| "loss": 0.6782, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 9.90497875213623, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.6433, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 4.704445838928223, |
| "learning_rate": 4.074074074074074e-05, |
| "loss": 0.4488, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 17.884246826171875, |
| "learning_rate": 3.981481481481482e-05, |
| "loss": 0.618, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 8.23388957977295, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.5853, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 8.233333587646484, |
| "learning_rate": 3.7962962962962964e-05, |
| "loss": 0.4419, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 6.261537075042725, |
| "learning_rate": 3.7037037037037037e-05, |
| "loss": 0.4245, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.805, |
| "eval_auc": 0.9066000000000001, |
| "eval_f1": 0.8251121076233184, |
| "eval_loss": 0.4501543343067169, |
| "eval_precision": 0.7479674796747967, |
| "eval_recall": 0.92, |
| "eval_runtime": 29.3558, |
| "eval_samples_per_second": 6.813, |
| "eval_steps_per_second": 0.443, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 300, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 52623154790400.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
