| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1220703125, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01220703125, | |
| "grad_norm": 2.114661455154419, | |
| "learning_rate": 0.0002964111328125, | |
| "loss": 3.2018, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0244140625, | |
| "grad_norm": 2.3655176162719727, | |
| "learning_rate": 0.00029274902343749996, | |
| "loss": 2.6421, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03662109375, | |
| "grad_norm": 1.6293455362319946, | |
| "learning_rate": 0.0002890869140625, | |
| "loss": 2.6106, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.048828125, | |
| "grad_norm": 1.7300739288330078, | |
| "learning_rate": 0.00028542480468749995, | |
| "loss": 2.4284, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06103515625, | |
| "grad_norm": 1.9834566116333008, | |
| "learning_rate": 0.0002817626953125, | |
| "loss": 2.2976, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0732421875, | |
| "grad_norm": 2.1146440505981445, | |
| "learning_rate": 0.0002781005859375, | |
| "loss": 2.3931, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08544921875, | |
| "grad_norm": 1.6163794994354248, | |
| "learning_rate": 0.00027443847656249997, | |
| "loss": 2.317, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.09765625, | |
| "grad_norm": 2.4195892810821533, | |
| "learning_rate": 0.0002707763671875, | |
| "loss": 2.2919, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.10986328125, | |
| "grad_norm": 2.2845382690429688, | |
| "learning_rate": 0.00026711425781249996, | |
| "loss": 2.3967, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1220703125, | |
| "grad_norm": 1.858925223350525, | |
| "learning_rate": 0.0002634521484375, | |
| "loss": 2.2228, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 4096, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2120417910349824.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |