| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 1000.0, |
| "global_step": 7494, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.200160128102482, |
| "grad_norm": 2.155690908432007, |
| "learning_rate": 4.6663997864958635e-05, |
| "loss": 4.4221, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.400320256204964, |
| "grad_norm": 1.6321208477020264, |
| "learning_rate": 4.332799572991727e-05, |
| "loss": 4.1746, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.600480384307446, |
| "grad_norm": 2.751591920852661, |
| "learning_rate": 3.99919935948759e-05, |
| "loss": 4.1681, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.800640512409928, |
| "grad_norm": 1.6891682147979736, |
| "learning_rate": 3.665599145983454e-05, |
| "loss": 4.1559, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.00080064051241, |
| "grad_norm": 2.1806092262268066, |
| "learning_rate": 3.3319989324793174e-05, |
| "loss": 4.1615, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.200960768614892, |
| "grad_norm": 2.332911491394043, |
| "learning_rate": 2.9983987189751807e-05, |
| "loss": 4.1495, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.4011208967173738, |
| "grad_norm": 2.650616407394409, |
| "learning_rate": 2.6647985054710433e-05, |
| "loss": 4.1441, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.601281024819856, |
| "grad_norm": 1.7507755756378174, |
| "learning_rate": 2.331198291966907e-05, |
| "loss": 4.1309, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.801441152922338, |
| "grad_norm": 1.7960165739059448, |
| "learning_rate": 1.9975980784627705e-05, |
| "loss": 4.151, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.00160128102482, |
| "grad_norm": 2.081895112991333, |
| "learning_rate": 1.6639978649586335e-05, |
| "loss": 4.1392, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.2017614091273017, |
| "grad_norm": 2.4643125534057617, |
| "learning_rate": 1.330397651454497e-05, |
| "loss": 4.141, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.401921537229784, |
| "grad_norm": 2.676142692565918, |
| "learning_rate": 9.967974379503602e-06, |
| "loss": 4.1454, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.602081665332266, |
| "grad_norm": 2.038424015045166, |
| "learning_rate": 6.631972244462237e-06, |
| "loss": 4.1188, |
| "step": 6500 |
| }, |
| { |
| "epoch": 2.8022417934347477, |
| "grad_norm": 2.213303565979004, |
| "learning_rate": 3.29597010942087e-06, |
| "loss": 4.1281, |
| "step": 7000 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 7494, |
| "total_flos": 3.595290103775232e+16, |
| "train_loss": 4.164535013427408, |
| "train_runtime": 5790.6888, |
| "train_samples_per_second": 2.588, |
| "train_steps_per_second": 1.294 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 7494, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.595290103775232e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
