| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000717240060248165, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.390800200827217e-05, | |
| "eval_loss": 3.313004493713379, | |
| "eval_runtime": 1025.2737, | |
| "eval_samples_per_second": 17.178, | |
| "eval_steps_per_second": 8.589, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.17240060248165e-05, | |
| "grad_norm": 0.719241738319397, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9884, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000143448012049633, | |
| "grad_norm": 1.0542523860931396, | |
| "learning_rate": 0.00012, | |
| "loss": 3.239, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019126401606617735, | |
| "eval_loss": 3.1983094215393066, | |
| "eval_runtime": 1029.1587, | |
| "eval_samples_per_second": 17.113, | |
| "eval_steps_per_second": 8.557, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002151720180744495, | |
| "grad_norm": 0.9659188389778137, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1847, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000286896024099266, | |
| "grad_norm": 0.5769478678703308, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.5024, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003586200301240825, | |
| "grad_norm": 1.169776439666748, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.9598, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003825280321323547, | |
| "eval_loss": 2.9964921474456787, | |
| "eval_runtime": 1029.7079, | |
| "eval_samples_per_second": 17.104, | |
| "eval_steps_per_second": 8.552, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.000430344036148899, | |
| "grad_norm": 1.353364109992981, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.0052, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005020680421737155, | |
| "grad_norm": 1.4587379693984985, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 3.0622, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.000573792048198532, | |
| "grad_norm": 0.7186371684074402, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.4507, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000573792048198532, | |
| "eval_loss": 2.9365055561065674, | |
| "eval_runtime": 1029.7686, | |
| "eval_samples_per_second": 17.103, | |
| "eval_steps_per_second": 8.551, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0006455160542233485, | |
| "grad_norm": 1.1878702640533447, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.7715, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.000717240060248165, | |
| "grad_norm": 1.223516821861267, | |
| "learning_rate": 0.0, | |
| "loss": 2.7356, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1406516984741888e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |