| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04449197860962567, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003422459893048128, | |
| "grad_norm": 1.7999919652938843, | |
| "learning_rate": 1e-05, | |
| "loss": 1.43, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003422459893048128, | |
| "eval_loss": 1.5696145296096802, | |
| "eval_runtime": 93.9699, | |
| "eval_samples_per_second": 5.246, | |
| "eval_steps_per_second": 2.629, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006844919786096256, | |
| "grad_norm": 1.4601882696151733, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5299, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010267379679144385, | |
| "grad_norm": 1.357947587966919, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4347, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013689839572192513, | |
| "grad_norm": 1.7744206190109253, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5207, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017112299465240642, | |
| "grad_norm": 1.8218324184417725, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6008, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02053475935828877, | |
| "grad_norm": 1.1797770261764526, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2966, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023957219251336898, | |
| "grad_norm": 1.1083546876907349, | |
| "learning_rate": 7e-05, | |
| "loss": 1.2069, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027379679144385025, | |
| "grad_norm": 0.9623205661773682, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1496, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.030802139037433156, | |
| "grad_norm": 0.78102046251297, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3235, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.034224598930481284, | |
| "grad_norm": 0.8298507332801819, | |
| "learning_rate": 0.0001, | |
| "loss": 1.212, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03764705882352941, | |
| "grad_norm": 0.8449644446372986, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 1.0372, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04106951871657754, | |
| "grad_norm": 0.8819606900215149, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.1813, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04449197860962567, | |
| "grad_norm": 0.8829816579818726, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 0.9319, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04449197860962567, | |
| "eval_loss": 1.018886923789978, | |
| "eval_runtime": 17.4921, | |
| "eval_samples_per_second": 28.184, | |
| "eval_steps_per_second": 14.121, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3748962364293120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |