| { |
| "best_global_step": 36, |
| "best_metric": 0.4666666666666667, |
| "best_model_checkpoint": "./cheese-text-classifier/checkpoint-36", |
| "epoch": 8.0, |
| "eval_steps": 500, |
| "global_step": 72, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 2.245687246322632, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 1.3897, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.26666666666666666, |
| "eval_loss": 1.3788894414901733, |
| "eval_runtime": 15.3581, |
| "eval_samples_per_second": 0.977, |
| "eval_steps_per_second": 0.13, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 3.2673349380493164, |
| "learning_rate": 1.8e-05, |
| "loss": 1.3742, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 2.7203733921051025, |
| "learning_rate": 1.9e-05, |
| "loss": 1.376, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.26666666666666666, |
| "eval_loss": 1.3665523529052734, |
| "eval_runtime": 11.7383, |
| "eval_samples_per_second": 1.278, |
| "eval_steps_per_second": 0.17, |
| "step": 18 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 2.6290931701660156, |
| "learning_rate": 1.775e-05, |
| "loss": 1.3642, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.7777777777777777, |
| "grad_norm": 2.063326358795166, |
| "learning_rate": 1.65e-05, |
| "loss": 1.3545, |
| "step": 25 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.4, |
| "eval_loss": 1.3509334325790405, |
| "eval_runtime": 11.9563, |
| "eval_samples_per_second": 1.255, |
| "eval_steps_per_second": 0.167, |
| "step": 27 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 4.2415618896484375, |
| "learning_rate": 1.525e-05, |
| "loss": 1.3202, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.888888888888889, |
| "grad_norm": 2.6389851570129395, |
| "learning_rate": 1.4e-05, |
| "loss": 1.2773, |
| "step": 35 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.4666666666666667, |
| "eval_loss": 1.3365625143051147, |
| "eval_runtime": 16.0326, |
| "eval_samples_per_second": 0.936, |
| "eval_steps_per_second": 0.125, |
| "step": 36 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 4.96947717666626, |
| "learning_rate": 1.275e-05, |
| "loss": 1.2581, |
| "step": 40 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 4.3252763748168945, |
| "learning_rate": 1.15e-05, |
| "loss": 1.2385, |
| "step": 45 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.4, |
| "eval_loss": 1.3152297735214233, |
| "eval_runtime": 11.4967, |
| "eval_samples_per_second": 1.305, |
| "eval_steps_per_second": 0.174, |
| "step": 45 |
| }, |
| { |
| "epoch": 5.555555555555555, |
| "grad_norm": 3.6944730281829834, |
| "learning_rate": 1.025e-05, |
| "loss": 1.1673, |
| "step": 50 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.4666666666666667, |
| "eval_loss": 1.3012595176696777, |
| "eval_runtime": 11.6907, |
| "eval_samples_per_second": 1.283, |
| "eval_steps_per_second": 0.171, |
| "step": 54 |
| }, |
| { |
| "epoch": 6.111111111111111, |
| "grad_norm": 3.9506728649139404, |
| "learning_rate": 9e-06, |
| "loss": 1.1801, |
| "step": 55 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 3.8581199645996094, |
| "learning_rate": 7.75e-06, |
| "loss": 1.1062, |
| "step": 60 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.4, |
| "eval_loss": 1.2912942171096802, |
| "eval_runtime": 11.6514, |
| "eval_samples_per_second": 1.287, |
| "eval_steps_per_second": 0.172, |
| "step": 63 |
| }, |
| { |
| "epoch": 7.222222222222222, |
| "grad_norm": 3.7704031467437744, |
| "learning_rate": 6.5000000000000004e-06, |
| "loss": 1.1034, |
| "step": 65 |
| }, |
| { |
| "epoch": 7.777777777777778, |
| "grad_norm": 5.039752006530762, |
| "learning_rate": 5.2500000000000006e-06, |
| "loss": 1.0084, |
| "step": 70 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.4666666666666667, |
| "eval_loss": 1.2895780801773071, |
| "eval_runtime": 11.7247, |
| "eval_samples_per_second": 1.279, |
| "eval_steps_per_second": 0.171, |
| "step": 72 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 90, |
| "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": 74184389099520.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
