| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010767884783632815, | |
| "eval_steps": 4, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00026919711959082036, | |
| "grad_norm": 7.305245876312256, | |
| "learning_rate": 2e-05, | |
| "loss": 6.0527, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026919711959082036, | |
| "eval_loss": 6.004375457763672, | |
| "eval_runtime": 186.7841, | |
| "eval_samples_per_second": 8.379, | |
| "eval_steps_per_second": 4.192, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005383942391816407, | |
| "grad_norm": 6.773212432861328, | |
| "learning_rate": 4e-05, | |
| "loss": 6.151, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008075913587724611, | |
| "grad_norm": 7.554437160491943, | |
| "learning_rate": 6e-05, | |
| "loss": 6.398, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010767884783632815, | |
| "grad_norm": 6.408179759979248, | |
| "learning_rate": 8e-05, | |
| "loss": 5.7049, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010767884783632815, | |
| "eval_loss": 5.3220696449279785, | |
| "eval_runtime": 187.1601, | |
| "eval_samples_per_second": 8.362, | |
| "eval_steps_per_second": 4.184, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3067577446170624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |