| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00843775049571784, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016875500991435683, | |
| "eval_loss": 13.2659912109375, | |
| "eval_runtime": 269.2511, | |
| "eval_samples_per_second": 9.266, | |
| "eval_steps_per_second": 4.635, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008437750495717841, | |
| "grad_norm": 53.10976028442383, | |
| "learning_rate": 5e-05, | |
| "loss": 12.199, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016875500991435683, | |
| "grad_norm": 16.650381088256836, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9923, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016875500991435683, | |
| "eval_loss": 0.210619255900383, | |
| "eval_runtime": 277.0683, | |
| "eval_samples_per_second": 9.005, | |
| "eval_steps_per_second": 4.504, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025313251487153526, | |
| "grad_norm": 19.800888061523438, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1909, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033751001982871365, | |
| "grad_norm": 0.48582473397254944, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1785, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033751001982871365, | |
| "eval_loss": 0.47386130690574646, | |
| "eval_runtime": 275.2918, | |
| "eval_samples_per_second": 9.063, | |
| "eval_steps_per_second": 4.533, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00421887524785892, | |
| "grad_norm": 9.057249069213867, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3445, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005062650297430705, | |
| "grad_norm": 4.749142646789551, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1914, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005062650297430705, | |
| "eval_loss": 0.12951725721359253, | |
| "eval_runtime": 275.4126, | |
| "eval_samples_per_second": 9.059, | |
| "eval_steps_per_second": 4.531, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005906425347002489, | |
| "grad_norm": 3.5826656818389893, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1027, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006750200396574273, | |
| "grad_norm": 0.13712178170681, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0248, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006750200396574273, | |
| "eval_loss": 0.09175414592027664, | |
| "eval_runtime": 274.9654, | |
| "eval_samples_per_second": 9.074, | |
| "eval_steps_per_second": 4.539, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007593975446146058, | |
| "grad_norm": 0.8356569409370422, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0174, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00843775049571784, | |
| "grad_norm": 0.07038362324237823, | |
| "learning_rate": 0.0, | |
| "loss": 0.0588, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00843775049571784, | |
| "eval_loss": 0.10671614110469818, | |
| "eval_runtime": 274.8351, | |
| "eval_samples_per_second": 9.078, | |
| "eval_steps_per_second": 4.541, | |
| "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": 1.02619680866304e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |