| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.029931158335827598, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000598623166716552, | |
| "eval_loss": 10.375690460205078, | |
| "eval_runtime": 3.1882, | |
| "eval_samples_per_second": 220.817, | |
| "eval_steps_per_second": 110.408, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00299311583358276, | |
| "grad_norm": 0.06843896210193634, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3737, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00598623166716552, | |
| "grad_norm": 0.09720660001039505, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3748, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00598623166716552, | |
| "eval_loss": 10.375232696533203, | |
| "eval_runtime": 3.2182, | |
| "eval_samples_per_second": 218.753, | |
| "eval_steps_per_second": 109.376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008979347500748278, | |
| "grad_norm": 0.08863717317581177, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3737, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01197246333433104, | |
| "grad_norm": 0.06964217871427536, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3752, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01197246333433104, | |
| "eval_loss": 10.374236106872559, | |
| "eval_runtime": 3.3114, | |
| "eval_samples_per_second": 212.602, | |
| "eval_steps_per_second": 106.301, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014965579167913799, | |
| "grad_norm": 0.0676875039935112, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3772, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017958695001496557, | |
| "grad_norm": 0.1013355627655983, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3708, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017958695001496557, | |
| "eval_loss": 10.373512268066406, | |
| "eval_runtime": 3.3474, | |
| "eval_samples_per_second": 210.309, | |
| "eval_steps_per_second": 105.155, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020951810835079316, | |
| "grad_norm": 0.09376264363527298, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3715, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02394492666866208, | |
| "grad_norm": 0.0710802972316742, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3768, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02394492666866208, | |
| "eval_loss": 10.373151779174805, | |
| "eval_runtime": 3.4379, | |
| "eval_samples_per_second": 204.777, | |
| "eval_steps_per_second": 102.388, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02693804250224484, | |
| "grad_norm": 0.10302187502384186, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3794, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.029931158335827598, | |
| "grad_norm": 0.08117420226335526, | |
| "learning_rate": 0.0, | |
| "loss": 10.3763, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.029931158335827598, | |
| "eval_loss": 10.373087882995605, | |
| "eval_runtime": 3.3578, | |
| "eval_samples_per_second": 209.66, | |
| "eval_steps_per_second": 104.83, | |
| "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": 646545408000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |