| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 51, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.19900497512437812, |
| "grad_norm": 1.2696179151535034, |
| "learning_rate": 9.890738003669029e-06, |
| "loss": 0.6594, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.39800995024875624, |
| "grad_norm": 1.0009506940841675, |
| "learning_rate": 8.078307376628292e-06, |
| "loss": 0.2957, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5970149253731343, |
| "grad_norm": 0.816304624080658, |
| "learning_rate": 4.825502516487497e-06, |
| "loss": 0.2682, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7960199004975125, |
| "grad_norm": 0.7167808413505554, |
| "learning_rate": 1.6543469682057105e-06, |
| "loss": 0.2472, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9950248756218906, |
| "grad_norm": 0.7434136271476746, |
| "learning_rate": 4.865965629214819e-08, |
| "loss": 0.257, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 51, |
| "total_flos": 71987160678400.0, |
| "train_loss": 0.33997809361009035, |
| "train_runtime": 8691.2958, |
| "train_samples_per_second": 0.739, |
| "train_steps_per_second": 0.006 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 51, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 71987160678400.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
