| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1317289423685877, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01013299556681444, | |
| "grad_norm": 2.299077033996582, | |
| "learning_rate": 1e-05, | |
| "loss": 3.7257, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01013299556681444, | |
| "eval_loss": 3.523265838623047, | |
| "eval_runtime": 98.4632, | |
| "eval_samples_per_second": 1.696, | |
| "eval_steps_per_second": 0.853, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02026599113362888, | |
| "grad_norm": 2.1457676887512207, | |
| "learning_rate": 2e-05, | |
| "loss": 3.3609, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.030398986700443317, | |
| "grad_norm": 2.0729289054870605, | |
| "learning_rate": 3e-05, | |
| "loss": 3.2415, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04053198226725776, | |
| "grad_norm": 2.152341365814209, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0918, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0506649778340722, | |
| "grad_norm": 2.4330685138702393, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1871, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.060797973400886635, | |
| "grad_norm": 2.830127000808716, | |
| "learning_rate": 6e-05, | |
| "loss": 3.007, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07093096896770108, | |
| "grad_norm": 2.7601826190948486, | |
| "learning_rate": 7e-05, | |
| "loss": 2.7736, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08106396453451552, | |
| "grad_norm": 3.2441565990448, | |
| "learning_rate": 8e-05, | |
| "loss": 2.668, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09119696010132995, | |
| "grad_norm": 3.553675651550293, | |
| "learning_rate": 9e-05, | |
| "loss": 2.3073, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1013299556681444, | |
| "grad_norm": 3.3283772468566895, | |
| "learning_rate": 0.0001, | |
| "loss": 2.017, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11146295123495883, | |
| "grad_norm": 3.136801242828369, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 1.7767, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12159594680177327, | |
| "grad_norm": 2.8050150871276855, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.563, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1317289423685877, | |
| "grad_norm": 2.3837151527404785, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 1.1287, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1317289423685877, | |
| "eval_loss": 1.2567861080169678, | |
| "eval_runtime": 3.9408, | |
| "eval_samples_per_second": 42.377, | |
| "eval_steps_per_second": 21.315, | |
| "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 | |
| } | |