| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005055931239335145, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.055931239335145e-05, | |
| "grad_norm": 2.6913185138255358e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.055931239335145e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 56.3246, | |
| "eval_samples_per_second": 147.857, | |
| "eval_steps_per_second": 73.929, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001011186247867029, | |
| "grad_norm": 1.257632811757503e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00015167793718005436, | |
| "grad_norm": 1.7909394955495372e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015167793718005436, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 56.5462, | |
| "eval_samples_per_second": 147.278, | |
| "eval_steps_per_second": 73.639, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002022372495734058, | |
| "grad_norm": 5.206894638831727e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00025279656196675726, | |
| "grad_norm": 1.0826270226971246e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00030335587436010873, | |
| "grad_norm": 1.5332319890148938e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00030335587436010873, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 56.9386, | |
| "eval_samples_per_second": 146.263, | |
| "eval_steps_per_second": 73.131, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00035391518675346014, | |
| "grad_norm": 2.807706368912477e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004044744991468116, | |
| "grad_norm": 1.6189480447792448e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00045503381154016307, | |
| "grad_norm": 2.7867310564033687e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00045503381154016307, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 56.8147, | |
| "eval_samples_per_second": 146.582, | |
| "eval_steps_per_second": 73.291, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005055931239335145, | |
| "grad_norm": 5.764033630839549e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 368573251584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |