| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013651877133105802, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004550625711035267, | |
| "grad_norm": 75.894287109375, | |
| "learning_rate": 2e-05, | |
| "loss": 9.1111, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004550625711035267, | |
| "eval_loss": 8.72750473022461, | |
| "eval_runtime": 2.6439, | |
| "eval_samples_per_second": 35.176, | |
| "eval_steps_per_second": 17.777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009101251422070534, | |
| "grad_norm": 59.834877014160156, | |
| "learning_rate": 4e-05, | |
| "loss": 7.4004, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013651877133105802, | |
| "grad_norm": 61.54233169555664, | |
| "learning_rate": 6e-05, | |
| "loss": 8.4554, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013651877133105802, | |
| "eval_loss": 8.171257019042969, | |
| "eval_runtime": 1.6722, | |
| "eval_samples_per_second": 55.615, | |
| "eval_steps_per_second": 28.107, | |
| "step": 3 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 76737593475072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |