| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9947704822777454, |
| "eval_steps": 1000, |
| "global_step": 107, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.09296920395119117, |
| "grad_norm": 0.7048821800444566, |
| "learning_rate": 9.978246739845095e-06, |
| "loss": 0.8236, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.18593840790238234, |
| "grad_norm": 0.4150380996837911, |
| "learning_rate": 9.596765194911182e-06, |
| "loss": 0.5002, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2789076118535735, |
| "grad_norm": 0.3590804657677201, |
| "learning_rate": 8.774114695766286e-06, |
| "loss": 0.4698, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.37187681580476467, |
| "grad_norm": 0.3203064886912417, |
| "learning_rate": 7.589248124491627e-06, |
| "loss": 0.4408, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.46484601975595585, |
| "grad_norm": 0.319927362444108, |
| "learning_rate": 6.15588161057485e-06, |
| "loss": 0.4316, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.557815223707147, |
| "grad_norm": 0.3063736106799291, |
| "learning_rate": 4.611580763554969e-06, |
| "loss": 0.439, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.6507844276583382, |
| "grad_norm": 0.3055856222140526, |
| "learning_rate": 3.104557980798104e-06, |
| "loss": 0.4321, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.7437536316095293, |
| "grad_norm": 0.3197809936930162, |
| "learning_rate": 1.7794479427480115e-06, |
| "loss": 0.4268, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.8367228355607205, |
| "grad_norm": 0.3159717120836253, |
| "learning_rate": 7.634264752111131e-07, |
| "loss": 0.421, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.9296920395119117, |
| "grad_norm": 0.3098749060038542, |
| "learning_rate": 1.540050040016694e-07, |
| "loss": 0.435, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.9947704822777454, |
| "step": 107, |
| "total_flos": 145069794394112.0, |
| "train_loss": 0.4802975632319941, |
| "train_runtime": 3035.4853, |
| "train_samples_per_second": 4.534, |
| "train_steps_per_second": 0.035 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 107, |
| "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": 145069794394112.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
