| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.043402777777777776, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008680555555555555, | |
| "eval_loss": 4.605380535125732, | |
| "eval_runtime": 21.8282, | |
| "eval_samples_per_second": 22.219, | |
| "eval_steps_per_second": 11.132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004340277777777778, | |
| "grad_norm": 1.5089558362960815, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1534, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008680555555555556, | |
| "grad_norm": 1.6227378845214844, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2115, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008680555555555556, | |
| "eval_loss": 4.272531509399414, | |
| "eval_runtime": 17.0616, | |
| "eval_samples_per_second": 28.426, | |
| "eval_steps_per_second": 14.243, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013020833333333334, | |
| "grad_norm": 2.2388646602630615, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.6183, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017361111111111112, | |
| "grad_norm": 3.2893173694610596, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.1206, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017361111111111112, | |
| "eval_loss": 2.4937543869018555, | |
| "eval_runtime": 16.1492, | |
| "eval_samples_per_second": 30.033, | |
| "eval_steps_per_second": 15.047, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021701388888888888, | |
| "grad_norm": 3.498352289199829, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8513, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026041666666666668, | |
| "grad_norm": 3.8759148120880127, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4983, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.026041666666666668, | |
| "eval_loss": 1.2910934686660767, | |
| "eval_runtime": 16.1354, | |
| "eval_samples_per_second": 30.058, | |
| "eval_steps_per_second": 15.06, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030381944444444444, | |
| "grad_norm": 2.2127106189727783, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0924, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.034722222222222224, | |
| "grad_norm": 2.26999831199646, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0614, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.034722222222222224, | |
| "eval_loss": 0.9549398422241211, | |
| "eval_runtime": 16.2023, | |
| "eval_samples_per_second": 29.934, | |
| "eval_steps_per_second": 14.998, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0390625, | |
| "grad_norm": 2.241302728652954, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9946, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.043402777777777776, | |
| "grad_norm": 2.1079211235046387, | |
| "learning_rate": 0.0, | |
| "loss": 0.9447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.043402777777777776, | |
| "eval_loss": 0.9167178273200989, | |
| "eval_runtime": 15.9527, | |
| "eval_samples_per_second": 30.402, | |
| "eval_steps_per_second": 15.233, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1581936279552000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |