| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.004255998297600681, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0004255998297600681, |
| "grad_norm": 5634.16845703125, |
| "learning_rate": 2.4e-07, |
| "loss": 14.1264, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0008511996595201362, |
| "grad_norm": 2312.5771484375, |
| "learning_rate": 1.04e-06, |
| "loss": 13.2905, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0012767994892802044, |
| "grad_norm": 2110.1591796875, |
| "learning_rate": 1.84e-06, |
| "loss": 12.6236, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0017023993190402723, |
| "grad_norm": 1493.8431396484375, |
| "learning_rate": 2.64e-06, |
| "loss": 12.3954, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0021279991488003403, |
| "grad_norm": 1430.7598876953125, |
| "learning_rate": 3.44e-06, |
| "loss": 12.265, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0025535989785604087, |
| "grad_norm": 2192.621826171875, |
| "learning_rate": 4.24e-06, |
| "loss": 12.018, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.0029791988083204767, |
| "grad_norm": 1678.5159912109375, |
| "learning_rate": 5.04e-06, |
| "loss": 11.8932, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.0034047986380805447, |
| "grad_norm": 1261.883056640625, |
| "learning_rate": 5.84e-06, |
| "loss": 11.8077, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.0038303984678406127, |
| "grad_norm": 1710.3070068359375, |
| "learning_rate": 6.640000000000001e-06, |
| "loss": 11.6841, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.004255998297600681, |
| "grad_norm": 2306.063232421875, |
| "learning_rate": 7.44e-06, |
| "loss": 11.5426, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 10000000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 426, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1466185913548800.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
