| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 78, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1282051282051282, |
| "grad_norm": 1.2449700832366943, |
| "learning_rate": 4.997482666353287e-06, |
| "loss": 0.07149758338928222, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2564102564102564, |
| "grad_norm": 1.2092856168746948, |
| "learning_rate": 4.701488829641845e-06, |
| "loss": 0.06979185938835145, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.38461538461538464, |
| "grad_norm": 1.251923680305481, |
| "learning_rate": 3.969463130731183e-06, |
| "loss": 0.07346434593200683, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5128205128205128, |
| "grad_norm": 1.6888631582260132, |
| "learning_rate": 2.946392236996592e-06, |
| "loss": 0.07525330185890197, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6410256410256411, |
| "grad_norm": 1.2313798666000366, |
| "learning_rate": 1.8349078860833125e-06, |
| "loss": 0.07232255935668945, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 1.2999941110610962, |
| "learning_rate": 8.551531851507186e-07, |
| "loss": 0.07458277940750122, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.8974358974358975, |
| "grad_norm": 1.4668843746185303, |
| "learning_rate": 2.0118056862137358e-07, |
| "loss": 0.07144420742988586, |
| "step": 70 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 78, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 117274396590080.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
