| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 64, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15625, |
| "grad_norm": 1.826694622432399, |
| "learning_rate": 4.844380330367701e-06, |
| "loss": 1.1143, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3125, |
| "grad_norm": 1.2388035729378144, |
| "learning_rate": 4.128431206805556e-06, |
| "loss": 0.6823, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.46875, |
| "grad_norm": 1.0426568030156709, |
| "learning_rate": 3.0032463002216504e-06, |
| "loss": 0.5937, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 0.9268168058904268, |
| "learning_rate": 1.7515921925666053e-06, |
| "loss": 0.5559, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.78125, |
| "grad_norm": 0.7842462004958339, |
| "learning_rate": 6.880180319272006e-07, |
| "loss": 0.5367, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9375, |
| "grad_norm": 0.7996537272057895, |
| "learning_rate": 7.980720283448957e-08, |
| "loss": 0.5385, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 64, |
| "total_flos": 10038179987456.0, |
| "train_loss": 0.6609018817543983, |
| "train_runtime": 326.674, |
| "train_samples_per_second": 6.239, |
| "train_steps_per_second": 0.196 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 64, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 10038179987456.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
