| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9985869053226566, | |
| "eval_steps": 14, | |
| "global_step": 265, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0527555346208196, | |
| "grad_norm": 0.18791379034519196, | |
| "learning_rate": 0.0013333333333333333, | |
| "loss": 1.1165, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1055110692416392, | |
| "grad_norm": 1.2923468351364136, | |
| "learning_rate": 0.001044465935734187, | |
| "loss": 1.5197, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.15826660386245878, | |
| "grad_norm": 0.27302563190460205, | |
| "learning_rate": 0.0006928203230275508, | |
| "loss": 0.9163, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2110221384832784, | |
| "grad_norm": 0.252996027469635, | |
| "learning_rate": 0.0005547001962252292, | |
| "loss": 0.8046, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.263777673104098, | |
| "grad_norm": 0.25708699226379395, | |
| "learning_rate": 0.00047583095143088644, | |
| "loss": 0.7624, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.31653320772491755, | |
| "grad_norm": 0.2488645762205124, | |
| "learning_rate": 0.000423207369515159, | |
| "loss": 0.7358, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.36928874234573716, | |
| "grad_norm": 0.2357274889945984, | |
| "learning_rate": 0.00038490017945975053, | |
| "loss": 0.7009, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.4220442769665568, | |
| "grad_norm": 0.25910037755966187, | |
| "learning_rate": 0.00035540932665545545, | |
| "loss": 0.6576, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.47479981158737633, | |
| "grad_norm": 0.24194850027561188, | |
| "learning_rate": 0.00033180075816559865, | |
| "loss": 0.6456, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.527555346208196, | |
| "grad_norm": 0.31878945231437683, | |
| "learning_rate": 0.0003123475237772121, | |
| "loss": 0.6035, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5803108808290155, | |
| "grad_norm": 0.23705270886421204, | |
| "learning_rate": 0.00029595817420019407, | |
| "loss": 0.6138, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.6330664154498351, | |
| "grad_norm": 0.32103270292282104, | |
| "learning_rate": 0.0002819045914409638, | |
| "loss": 0.5941, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.6858219500706547, | |
| "grad_norm": 0.2693799138069153, | |
| "learning_rate": 0.00026967994498529687, | |
| "loss": 0.5686, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.7385774846914743, | |
| "grad_norm": 0.2850986123085022, | |
| "learning_rate": 0.0002589191112012619, | |
| "loss": 0.5854, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.7913330193122939, | |
| "grad_norm": 0.2964475154876709, | |
| "learning_rate": 0.00024935149047701483, | |
| "loss": 0.5482, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8440885539331136, | |
| "grad_norm": 0.27225586771965027, | |
| "learning_rate": 0.0002407717061715384, | |
| "loss": 0.5447, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.8968440885539332, | |
| "grad_norm": 0.24302007257938385, | |
| "learning_rate": 0.00023302069121418522, | |
| "loss": 0.5245, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.9495996231747527, | |
| "grad_norm": 0.3157835900783539, | |
| "learning_rate": 0.00022597307314641284, | |
| "loss": 0.5328, | |
| "step": 252 | |
| } | |
| ], | |
| "logging_steps": 14, | |
| "max_steps": 265, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 14, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.691462902673572e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |