| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008939346533768381, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017878693067536764, | |
| "eval_loss": 2.933220624923706, | |
| "eval_runtime": 233.474, | |
| "eval_samples_per_second": 10.091, | |
| "eval_steps_per_second": 5.046, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008939346533768382, | |
| "grad_norm": 0.2832305431365967, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8622, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017878693067536764, | |
| "grad_norm": 0.40609437227249146, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7993, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017878693067536764, | |
| "eval_loss": 2.906853437423706, | |
| "eval_runtime": 242.4442, | |
| "eval_samples_per_second": 9.718, | |
| "eval_steps_per_second": 4.859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0026818039601305146, | |
| "grad_norm": 0.3924393951892853, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.764, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0035757386135073527, | |
| "grad_norm": 0.4617941379547119, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.7949, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0035757386135073527, | |
| "eval_loss": 2.8182547092437744, | |
| "eval_runtime": 241.8579, | |
| "eval_samples_per_second": 9.741, | |
| "eval_steps_per_second": 4.871, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0044696732668841905, | |
| "grad_norm": 0.5247169137001038, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.6913, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005363607920261029, | |
| "grad_norm": 0.5109822750091553, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7626, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005363607920261029, | |
| "eval_loss": 2.7879366874694824, | |
| "eval_runtime": 241.7636, | |
| "eval_samples_per_second": 9.745, | |
| "eval_steps_per_second": 4.873, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006257542573637867, | |
| "grad_norm": 0.4426691234111786, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8036, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0071514772270147055, | |
| "grad_norm": 0.514265775680542, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.6892, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0071514772270147055, | |
| "eval_loss": 2.772698402404785, | |
| "eval_runtime": 241.7888, | |
| "eval_samples_per_second": 9.744, | |
| "eval_steps_per_second": 4.872, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008045411880391543, | |
| "grad_norm": 0.6126759648323059, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.7549, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008939346533768381, | |
| "grad_norm": 0.5537281632423401, | |
| "learning_rate": 0.0, | |
| "loss": 2.7579, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008939346533768381, | |
| "eval_loss": 2.7696890830993652, | |
| "eval_runtime": 241.7278, | |
| "eval_samples_per_second": 9.747, | |
| "eval_steps_per_second": 4.873, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.088596299743232e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |