| { |
| "best_metric": 0.43876591324806213, |
| "best_model_checkpoint": "output_pipe/0/origin/checkpoint-400", |
| "epoch": 4.0, |
| "eval_steps": 200, |
| "global_step": 408, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9803921568627451, |
| "grad_norm": 4.340454578399658, |
| "learning_rate": 2.6061452513966484e-05, |
| "loss": 0.6743, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.9607843137254903, |
| "grad_norm": 4.347059726715088, |
| "learning_rate": 1.7681564245810057e-05, |
| "loss": 0.4757, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.9607843137254903, |
| "eval_accuracy": 0.8098765432098766, |
| "eval_f1": 0.8095002474022761, |
| "eval_loss": 0.45168113708496094, |
| "eval_matthews_correlation": 0.626803554022576, |
| "eval_precision": 0.8153468923901698, |
| "eval_recall": 0.8114686594479182, |
| "eval_runtime": 0.1311, |
| "eval_samples_per_second": 6180.527, |
| "eval_steps_per_second": 99.194, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.9411764705882355, |
| "grad_norm": 6.6639485359191895, |
| "learning_rate": 9.301675977653631e-06, |
| "loss": 0.3291, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.9215686274509802, |
| "grad_norm": 6.7193684577941895, |
| "learning_rate": 9.217877094972066e-07, |
| "loss": 0.2513, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.9215686274509802, |
| "eval_accuracy": 0.8333333333333334, |
| "eval_f1": 0.8333025904792685, |
| "eval_loss": 0.43876591324806213, |
| "eval_matthews_correlation": 0.669050678827637, |
| "eval_precision": 0.8348738262910798, |
| "eval_recall": 0.8341772151898734, |
| "eval_runtime": 0.1238, |
| "eval_samples_per_second": 6544.22, |
| "eval_steps_per_second": 105.031, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 408, |
| "total_flos": 531354250802880.0, |
| "train_loss": 0.4285174494280535, |
| "train_runtime": 23.4588, |
| "train_samples_per_second": 1104.575, |
| "train_steps_per_second": 17.392 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 408, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 531354250802880.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
