| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006578947368421052, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006578947368421052, | |
| "grad_norm": 1.1157801151275635, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3279, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006578947368421052, | |
| "eval_loss": 1.2261788845062256, | |
| "eval_runtime": 37.4346, | |
| "eval_samples_per_second": 17.096, | |
| "eval_steps_per_second": 8.548, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013157894736842105, | |
| "grad_norm": 0.889941394329071, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3279, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001973684210526316, | |
| "grad_norm": 1.2564910650253296, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4406, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001973684210526316, | |
| "eval_loss": 1.2141008377075195, | |
| "eval_runtime": 36.932, | |
| "eval_samples_per_second": 17.329, | |
| "eval_steps_per_second": 8.665, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002631578947368421, | |
| "grad_norm": 1.0116472244262695, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0018, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003289473684210526, | |
| "grad_norm": 0.9317536354064941, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0223, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003947368421052632, | |
| "grad_norm": 1.0897796154022217, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2913, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003947368421052632, | |
| "eval_loss": 0.9801298975944519, | |
| "eval_runtime": 36.9176, | |
| "eval_samples_per_second": 17.336, | |
| "eval_steps_per_second": 8.668, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004605263157894736, | |
| "grad_norm": 0.8095595836639404, | |
| "learning_rate": 0.00014, | |
| "loss": 0.9642, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "grad_norm": 0.8359549045562744, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6362, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0059210526315789476, | |
| "grad_norm": 0.9505390524864197, | |
| "learning_rate": 0.00018, | |
| "loss": 0.6104, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0059210526315789476, | |
| "eval_loss": 0.6365758776664734, | |
| "eval_runtime": 36.9069, | |
| "eval_samples_per_second": 17.341, | |
| "eval_steps_per_second": 8.67, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006578947368421052, | |
| "grad_norm": 1.086848258972168, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7216, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |