| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9696969696969697, |
| "eval_steps": 500, |
| "global_step": 8, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12121212121212122, |
| "grad_norm": 2.50050950050354, |
| "learning_rate": 2.5e-06, |
| "loss": 0.8407, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.24242424242424243, |
| "grad_norm": 2.2383944988250732, |
| "learning_rate": 5e-06, |
| "loss": 0.7878, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 2.1805531978607178, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.8026, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.48484848484848486, |
| "grad_norm": 2.0964150428771973, |
| "learning_rate": 1e-05, |
| "loss": 0.8133, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.6060606060606061, |
| "grad_norm": 1.5487000942230225, |
| "learning_rate": 9.968561049466214e-06, |
| "loss": 0.7608, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 1.7998461723327637, |
| "learning_rate": 9.874639560909118e-06, |
| "loss": 0.7272, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.8484848484848485, |
| "grad_norm": 1.9523899555206299, |
| "learning_rate": 9.719416651541839e-06, |
| "loss": 0.6923, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.9696969696969697, |
| "grad_norm": 4.303847312927246, |
| "learning_rate": 9.504844339512096e-06, |
| "loss": 0.6853, |
| "step": 8 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 32, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 8, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 21013697134592.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
