| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.91324200913242, |
| "eval_steps": 0, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.182648401826484, |
| "grad_norm": 0.03208735212683678, |
| "learning_rate": 4.6389697052407534e-05, |
| "loss": 1.866, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.365296803652968, |
| "grad_norm": 0.002725173020735383, |
| "learning_rate": 3.42482661901463e-05, |
| "loss": 0.0044, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.547945205479452, |
| "grad_norm": 0.0025376707781106234, |
| "learning_rate": 1.836022971459737e-05, |
| "loss": 0.0022, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.730593607305936, |
| "grad_norm": 0.0030033246148377657, |
| "learning_rate": 5.162059654089083e-06, |
| "loss": 0.002, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.91324200913242, |
| "grad_norm": 0.0022202266845852137, |
| "learning_rate": 5.244749650301639e-10, |
| "loss": 0.0019, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.91324200913242, |
| "step": 500, |
| "total_flos": 2.782892104886518e+18, |
| "train_loss": 0.3753145236670971, |
| "train_runtime": 7923.6753, |
| "train_samples_per_second": 10.096, |
| "train_steps_per_second": 0.063 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.782892104886518e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
