| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.903225806451612, |
| "eval_steps": 50, |
| "global_step": 70, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.774193548387097, |
| "grad_norm": 1.1368188858032227, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 1.2228, |
| "num_input_tokens_seen": 176768, |
| "step": 20 |
| }, |
| { |
| "epoch": 5.645161290322581, |
| "grad_norm": 0.8997830152511597, |
| "learning_rate": 5e-05, |
| "loss": 0.6911, |
| "num_input_tokens_seen": 359616, |
| "step": 40 |
| }, |
| { |
| "epoch": 7.129032258064516, |
| "eval_loss": 1.2629692554473877, |
| "eval_runtime": 0.6074, |
| "eval_samples_per_second": 23.048, |
| "eval_steps_per_second": 3.293, |
| "num_input_tokens_seen": 451904, |
| "step": 50 |
| }, |
| { |
| "epoch": 8.516129032258064, |
| "grad_norm": 0.7021396160125732, |
| "learning_rate": 6.698729810778065e-06, |
| "loss": 0.4192, |
| "num_input_tokens_seen": 542624, |
| "step": 60 |
| }, |
| { |
| "epoch": 9.903225806451612, |
| "num_input_tokens_seen": 630048, |
| "step": 70, |
| "total_flos": 1.455329346748416e+16, |
| "train_loss": 0.715225853238787, |
| "train_runtime": 178.896, |
| "train_samples_per_second": 6.82, |
| "train_steps_per_second": 0.391 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 70, |
| "num_input_tokens_seen": 630048, |
| "num_train_epochs": 10, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.455329346748416e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
