| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031012375130460713, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023855673177277472, | |
| "grad_norm": 1.3246102333068848, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9265, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023855673177277472, | |
| "eval_loss": 0.9870346188545227, | |
| "eval_runtime": 65.1117, | |
| "eval_samples_per_second": 10.843, | |
| "eval_steps_per_second": 5.421, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0047711346354554944, | |
| "grad_norm": 1.5241637229919434, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0298, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007156701953183241, | |
| "grad_norm": 1.3183329105377197, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9629, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009542269270910989, | |
| "grad_norm": 1.3316704034805298, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9491, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011927836588638736, | |
| "grad_norm": 1.2836781740188599, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8294, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014313403906366482, | |
| "grad_norm": 1.3446112871170044, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7596, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01669897122409423, | |
| "grad_norm": 1.3533251285552979, | |
| "learning_rate": 7e-05, | |
| "loss": 0.8652, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019084538541821978, | |
| "grad_norm": 1.2886685132980347, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6794, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021470105859549723, | |
| "grad_norm": 1.0436530113220215, | |
| "learning_rate": 9e-05, | |
| "loss": 0.5633, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02385567317727747, | |
| "grad_norm": 0.8520669937133789, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4955, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02624124049500522, | |
| "grad_norm": 0.7037628889083862, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 0.3973, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.028626807812732965, | |
| "grad_norm": 0.8181518912315369, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.4359, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.031012375130460713, | |
| "grad_norm": 0.6722888946533203, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 0.3231, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.031012375130460713, | |
| "eval_loss": 0.303219199180603, | |
| "eval_runtime": 16.6267, | |
| "eval_samples_per_second": 42.462, | |
| "eval_steps_per_second": 21.231, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8568679201505280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |