| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00495785820525533, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016526194017517766, | |
| "eval_loss": 2.3399617671966553, | |
| "eval_runtime": 337.7926, | |
| "eval_samples_per_second": 7.543, | |
| "eval_steps_per_second": 3.772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004957858205255329, | |
| "grad_norm": 3.5715930461883545, | |
| "learning_rate": 3e-05, | |
| "loss": 10.4675, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009915716410510659, | |
| "grad_norm": 3.4245548248291016, | |
| "learning_rate": 6e-05, | |
| "loss": 10.0766, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013220955214014213, | |
| "eval_loss": 2.2484359741210938, | |
| "eval_runtime": 339.4909, | |
| "eval_samples_per_second": 7.505, | |
| "eval_steps_per_second": 3.753, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001487357461576599, | |
| "grad_norm": 4.232046604156494, | |
| "learning_rate": 9e-05, | |
| "loss": 9.8275, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019831432821021317, | |
| "grad_norm": 5.170561790466309, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 8.1643, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002478929102627665, | |
| "grad_norm": 20.678876876831055, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.0025, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026441910428028426, | |
| "eval_loss": 1.8248341083526611, | |
| "eval_runtime": 339.9053, | |
| "eval_samples_per_second": 7.496, | |
| "eval_steps_per_second": 3.748, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002974714923153198, | |
| "grad_norm": 8.31513786315918, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 7.5478, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0034705007436787306, | |
| "grad_norm": 6.001852512359619, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 7.4144, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0039662865642042635, | |
| "grad_norm": 5.518805503845215, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 6.8937, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0039662865642042635, | |
| "eval_loss": 1.7441750764846802, | |
| "eval_runtime": 339.7556, | |
| "eval_samples_per_second": 7.5, | |
| "eval_steps_per_second": 3.75, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004462072384729797, | |
| "grad_norm": 6.916284561157227, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 7.2328, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00495785820525533, | |
| "grad_norm": 4.421989917755127, | |
| "learning_rate": 0.0, | |
| "loss": 6.9671, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8738917338624000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |