| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1951219512195122, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0150093808630394, | |
| "grad_norm": 51.73713302612305, | |
| "learning_rate": 1e-05, | |
| "loss": 7.7969, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0150093808630394, | |
| "eval_loss": 7.751512050628662, | |
| "eval_runtime": 43.6829, | |
| "eval_samples_per_second": 10.279, | |
| "eval_steps_per_second": 1.305, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0300187617260788, | |
| "grad_norm": 48.8546028137207, | |
| "learning_rate": 2e-05, | |
| "loss": 7.8854, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0450281425891182, | |
| "grad_norm": 43.629215240478516, | |
| "learning_rate": 3e-05, | |
| "loss": 7.4761, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0600375234521576, | |
| "grad_norm": 40.31449508666992, | |
| "learning_rate": 4e-05, | |
| "loss": 6.7166, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.075046904315197, | |
| "grad_norm": 31.518842697143555, | |
| "learning_rate": 5e-05, | |
| "loss": 6.0265, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0900562851782364, | |
| "grad_norm": 27.299909591674805, | |
| "learning_rate": 6e-05, | |
| "loss": 5.1312, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1050656660412758, | |
| "grad_norm": 24.453201293945312, | |
| "learning_rate": 7e-05, | |
| "loss": 4.2289, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1200750469043152, | |
| "grad_norm": 21.977622985839844, | |
| "learning_rate": 8e-05, | |
| "loss": 3.409, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1350844277673546, | |
| "grad_norm": 21.064271926879883, | |
| "learning_rate": 9e-05, | |
| "loss": 2.7192, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.150093808630394, | |
| "grad_norm": 18.23163414001465, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9203, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1651031894934334, | |
| "grad_norm": 18.346233367919922, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 1.3844, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1801125703564728, | |
| "grad_norm": 17.36043357849121, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.0357, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 6.1927690505981445, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 0.8596, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "eval_loss": 0.7876977324485779, | |
| "eval_runtime": 4.0203, | |
| "eval_samples_per_second": 111.684, | |
| "eval_steps_per_second": 14.178, | |
| "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": 1.499584945717248e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |