| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003834723420573291, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.669446841146582e-05, | |
| "eval_loss": 1.5120909214019775, | |
| "eval_runtime": 270.3281, | |
| "eval_samples_per_second": 20.309, | |
| "eval_steps_per_second": 10.154, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003834723420573291, | |
| "grad_norm": 1.6149829626083374, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4681, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007669446841146582, | |
| "grad_norm": 1.866544246673584, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007669446841146582, | |
| "eval_loss": 0.8385525941848755, | |
| "eval_runtime": 270.7433, | |
| "eval_samples_per_second": 20.278, | |
| "eval_steps_per_second": 10.139, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011504170261719873, | |
| "grad_norm": 2.008497953414917, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7283, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015338893682293165, | |
| "grad_norm": 1.9806678295135498, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6553, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015338893682293165, | |
| "eval_loss": 0.4290267527103424, | |
| "eval_runtime": 270.8771, | |
| "eval_samples_per_second": 20.267, | |
| "eval_steps_per_second": 10.134, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019173617102866455, | |
| "grad_norm": 1.4957740306854248, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3759, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0023008340523439745, | |
| "grad_norm": 1.1098052263259888, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3243, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023008340523439745, | |
| "eval_loss": 0.3720788061618805, | |
| "eval_runtime": 271.833, | |
| "eval_samples_per_second": 20.196, | |
| "eval_steps_per_second": 10.098, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0026843063944013037, | |
| "grad_norm": 0.4442124366760254, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4469, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.003067778736458633, | |
| "grad_norm": 0.9363953471183777, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2449, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003067778736458633, | |
| "eval_loss": 0.3529892861843109, | |
| "eval_runtime": 271.127, | |
| "eval_samples_per_second": 20.249, | |
| "eval_steps_per_second": 10.124, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003451251078515962, | |
| "grad_norm": 1.0287480354309082, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2746, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003834723420573291, | |
| "grad_norm": 0.04178006201982498, | |
| "learning_rate": 0.0, | |
| "loss": 0.2152, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003834723420573291, | |
| "eval_loss": 0.3511003851890564, | |
| "eval_runtime": 270.9294, | |
| "eval_samples_per_second": 20.264, | |
| "eval_steps_per_second": 10.132, | |
| "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": 6047858904268800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |