| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013157894736842105, | |
| "eval_steps": 8, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013157894736842105, | |
| "eval_loss": 1.5495436191558838, | |
| "eval_runtime": 63.8211, | |
| "eval_samples_per_second": 5.014, | |
| "eval_steps_per_second": 2.507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003947368421052632, | |
| "grad_norm": 1.9250959157943726, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6027, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007894736842105263, | |
| "grad_norm": 1.0903421640396118, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3339, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "eval_loss": 1.0197498798370361, | |
| "eval_runtime": 64.8541, | |
| "eval_samples_per_second": 4.934, | |
| "eval_steps_per_second": 2.467, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011842105263157895, | |
| "grad_norm": 6.691552639007568, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0887, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4118062710128640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |