| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002498091735479842, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002775657483866491, | |
| "eval_loss": 0.5042526125907898, | |
| "eval_runtime": 655.4432, | |
| "eval_samples_per_second": 9.258, | |
| "eval_steps_per_second": 1.158, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008326972451599472, | |
| "grad_norm": 0.27662014961242676, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.526, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016653944903198944, | |
| "grad_norm": 0.27963921427726746, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4897, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002498091735479842, | |
| "grad_norm": 0.29799002408981323, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.5052, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002498091735479842, | |
| "eval_loss": 0.4782797694206238, | |
| "eval_runtime": 660.6166, | |
| "eval_samples_per_second": 9.185, | |
| "eval_steps_per_second": 1.149, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.852452537316147e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |