| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.857142857142857, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 3.078125, |
| "learning_rate": 1.1171428571428571e-05, |
| "loss": 1.6553, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 2.5625, |
| "learning_rate": 2.5135714285714285e-05, |
| "loss": 1.5594, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 2.5625, |
| "learning_rate": 3.91e-05, |
| "loss": 1.4914, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 2.078125, |
| "learning_rate": 5.306428571428571e-05, |
| "loss": 1.3912, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "eval_loss": 1.416105031967163, |
| "eval_runtime": 10.5759, |
| "eval_samples_per_second": 13.332, |
| "eval_steps_per_second": 13.332, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.1904761904761905, |
| "grad_norm": 2.265625, |
| "learning_rate": 6.702857142857144e-05, |
| "loss": 1.304, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 1.9609375, |
| "learning_rate": 8.099285714285715e-05, |
| "loss": 1.2533, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 2.875, |
| "learning_rate": 9.495714285714286e-05, |
| "loss": 1.2274, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 2.109375, |
| "learning_rate": 9.339386807685766e-05, |
| "loss": 1.2204, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "eval_loss": 1.3032252788543701, |
| "eval_runtime": 10.4999, |
| "eval_samples_per_second": 13.429, |
| "eval_steps_per_second": 13.429, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.142857142857143, |
| "grad_norm": 1.84375, |
| "learning_rate": 7.716526096571837e-05, |
| "loss": 1.0658, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.380952380952381, |
| "grad_norm": 1.5390625, |
| "learning_rate": 5.3762500000000006e-05, |
| "loss": 1.0063, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.619047619047619, |
| "grad_norm": 1.4375, |
| "learning_rate": 3.0359739034281636e-05, |
| "loss": 0.9935, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 1.390625, |
| "learning_rate": 1.4131131923142345e-05, |
| "loss": 0.9698, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "eval_loss": 1.2711824178695679, |
| "eval_runtime": 10.5832, |
| "eval_samples_per_second": 13.323, |
| "eval_steps_per_second": 13.323, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 63, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5825719078682624e+16, |
| "train_batch_size": 70, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
