| { |
| "best_metric": 0.20379750430583954, |
| "best_model_checkpoint": "sequence_classification/checkpoint-618", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1030, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.2364644855260849, |
| "eval_pearson": 0.9376906914778141, |
| "eval_runtime": 33.6935, |
| "eval_samples_per_second": 27.661, |
| "eval_steps_per_second": 3.472, |
| "step": 206 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.21361978352069855, |
| "eval_pearson": 0.9652459511637033, |
| "eval_runtime": 33.666, |
| "eval_samples_per_second": 27.684, |
| "eval_steps_per_second": 3.475, |
| "step": 412 |
| }, |
| { |
| "epoch": 2.4271844660194173, |
| "grad_norm": 0.9426701664924622, |
| "learning_rate": 5.145631067961165e-05, |
| "loss": 0.3209, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.20379750430583954, |
| "eval_pearson": 0.9631027995287645, |
| "eval_runtime": 33.7681, |
| "eval_samples_per_second": 27.6, |
| "eval_steps_per_second": 3.465, |
| "step": 618 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.23791250586509705, |
| "eval_pearson": 0.9668452710020821, |
| "eval_runtime": 48.3963, |
| "eval_samples_per_second": 19.258, |
| "eval_steps_per_second": 2.418, |
| "step": 824 |
| }, |
| { |
| "epoch": 4.854368932038835, |
| "grad_norm": 0.053257785737514496, |
| "learning_rate": 2.912621359223301e-06, |
| "loss": 0.0314, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.23692642152309418, |
| "eval_pearson": 0.9678178837521502, |
| "eval_runtime": 48.5841, |
| "eval_samples_per_second": 19.183, |
| "eval_steps_per_second": 2.408, |
| "step": 1030 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 1030, |
| "total_flos": 5.610584124311962e+16, |
| "train_loss": 0.17107450719741943, |
| "train_runtime": 2510.3029, |
| "train_samples_per_second": 13.076, |
| "train_steps_per_second": 0.41 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1030, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.610584124311962e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
