| { | |
| "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": 2.3402533531188965, | |
| "eval_runtime": 165.6221, | |
| "eval_samples_per_second": 15.384, | |
| "eval_steps_per_second": 7.692, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004957858205255329, | |
| "grad_norm": 3.68485164642334, | |
| "learning_rate": 6e-05, | |
| "loss": 10.4689, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009915716410510659, | |
| "grad_norm": 3.789649248123169, | |
| "learning_rate": 0.00012, | |
| "loss": 10.0151, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013220955214014213, | |
| "eval_loss": 2.0409507751464844, | |
| "eval_runtime": 165.7016, | |
| "eval_samples_per_second": 15.377, | |
| "eval_steps_per_second": 7.689, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001487357461576599, | |
| "grad_norm": 4.704958915710449, | |
| "learning_rate": 0.00018, | |
| "loss": 9.2207, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019831432821021317, | |
| "grad_norm": 6.374767303466797, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 7.3447, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002478929102627665, | |
| "grad_norm": 8.407645225524902, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.7431, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026441910428028426, | |
| "eval_loss": 1.731627345085144, | |
| "eval_runtime": 165.7838, | |
| "eval_samples_per_second": 15.369, | |
| "eval_steps_per_second": 7.685, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002974714923153198, | |
| "grad_norm": 7.1827712059021, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.0048, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0034705007436787306, | |
| "grad_norm": 18.893150329589844, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 6.83, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0039662865642042635, | |
| "grad_norm": 12.152100563049316, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 6.4333, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0039662865642042635, | |
| "eval_loss": 1.6485315561294556, | |
| "eval_runtime": 165.7096, | |
| "eval_samples_per_second": 15.376, | |
| "eval_steps_per_second": 7.688, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004462072384729797, | |
| "grad_norm": 9.412213325500488, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 6.8263, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00495785820525533, | |
| "grad_norm": 25.07528305053711, | |
| "learning_rate": 0.0, | |
| "loss": 6.6015, | |
| "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 | |
| } | |