| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004730928444707274, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004730928444707274, | |
| "grad_norm": 1.653063554840628e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004730928444707274, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 5.1707, | |
| "eval_samples_per_second": 172.124, | |
| "eval_steps_per_second": 86.062, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009461856889414548, | |
| "grad_norm": 3.3960011933231726e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014192785334121822, | |
| "grad_norm": 2.1344882043194957e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014192785334121822, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 5.1212, | |
| "eval_samples_per_second": 173.787, | |
| "eval_steps_per_second": 86.893, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018923713778829095, | |
| "grad_norm": 1.3005676009925082e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002365464222353637, | |
| "grad_norm": 1.8302931493963115e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028385570668243644, | |
| "grad_norm": 1.3231546290626284e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0028385570668243644, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 5.3602, | |
| "eval_samples_per_second": 166.04, | |
| "eval_steps_per_second": 83.02, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033116499112950917, | |
| "grad_norm": 2.61679342656862e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003784742755765819, | |
| "grad_norm": 1.634951331652701e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004257835600236547, | |
| "grad_norm": 3.0044679078855552e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004257835600236547, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 5.2965, | |
| "eval_samples_per_second": 168.036, | |
| "eval_steps_per_second": 84.018, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004730928444707274, | |
| "grad_norm": 2.8426744393073022e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 199228784640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |