| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0010985117911509383, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00010985117911509383, |
| "grad_norm": 2.085447311401367, |
| "learning_rate": 0.0001936842105263158, |
| "loss": 3.2352, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.00021970235823018765, |
| "grad_norm": 1.401716947555542, |
| "learning_rate": 0.00017473684210526317, |
| "loss": 1.3128, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0003295535373452815, |
| "grad_norm": 0.77020263671875, |
| "learning_rate": 0.0001536842105263158, |
| "loss": 0.8921, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0004394047164603753, |
| "grad_norm": 0.7875494956970215, |
| "learning_rate": 0.00013263157894736842, |
| "loss": 0.8159, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0005492558955754692, |
| "grad_norm": 0.502890944480896, |
| "learning_rate": 0.00011157894736842105, |
| "loss": 0.7328, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.000659107074690563, |
| "grad_norm": 0.42759764194488525, |
| "learning_rate": 9.052631578947369e-05, |
| "loss": 0.7261, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.0007689582538056568, |
| "grad_norm": 0.309189110994339, |
| "learning_rate": 6.947368421052632e-05, |
| "loss": 0.7057, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.0008788094329207506, |
| "grad_norm": 0.31502893567085266, |
| "learning_rate": 4.842105263157895e-05, |
| "loss": 0.7072, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.0009886606120358445, |
| "grad_norm": 0.24574220180511475, |
| "learning_rate": 2.7368421052631583e-05, |
| "loss": 0.7098, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.0010985117911509383, |
| "grad_norm": 0.23801881074905396, |
| "learning_rate": 6.315789473684211e-06, |
| "loss": 0.6984, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 100, |
| "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": 4021786178666496.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
