| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.99203187250996, | |
| "eval_steps": 500, | |
| "global_step": 376, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9880478087649402, | |
| "grad_norm": 0.2889673113822937, | |
| "learning_rate": 0.0002974798061389337, | |
| "loss": 0.7635, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.9920318725099602, | |
| "grad_norm": 0.34704622626304626, | |
| "learning_rate": 0.0002944264943457189, | |
| "loss": 0.5643, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.99601593625498, | |
| "grad_norm": 0.32337236404418945, | |
| "learning_rate": 0.00029137318255250403, | |
| "loss": 0.47, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.5398977994918823, | |
| "learning_rate": 0.00028831987075928915, | |
| "loss": 0.3844, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 4.98804780876494, | |
| "grad_norm": 0.4496667981147766, | |
| "learning_rate": 0.0002853150242326333, | |
| "loss": 0.3176, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 5.99203187250996, | |
| "grad_norm": 0.4373694062232971, | |
| "learning_rate": 0.0002822617124394184, | |
| "loss": 0.2479, | |
| "step": 376 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 6200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.955060003563684e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |