| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.984189723320158, | |
| "eval_steps": 500, | |
| "global_step": 126, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.31620553359683795, | |
| "grad_norm": 0.8500133156776428, | |
| "learning_rate": 9.473684210526316e-05, | |
| "loss": 0.2864, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6324110671936759, | |
| "grad_norm": 0.37896090745925903, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1421, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9486166007905138, | |
| "grad_norm": 0.6776529550552368, | |
| "learning_rate": 0.00019823576812941137, | |
| "loss": 0.1037, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2648221343873518, | |
| "grad_norm": 0.7092404365539551, | |
| "learning_rate": 0.00019300532279950948, | |
| "loss": 0.0727, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5810276679841897, | |
| "grad_norm": 0.40299248695373535, | |
| "learning_rate": 0.00018449321837726208, | |
| "loss": 0.0728, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8972332015810278, | |
| "grad_norm": 0.6488421559333801, | |
| "learning_rate": 0.00017299980138081922, | |
| "loss": 0.0647, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.2134387351778657, | |
| "grad_norm": 0.5246128439903259, | |
| "learning_rate": 0.00015893061286152276, | |
| "loss": 0.0613, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.5296442687747036, | |
| "grad_norm": 0.21512803435325623, | |
| "learning_rate": 0.0001427820790349539, | |
| "loss": 0.0462, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.8458498023715415, | |
| "grad_norm": 0.33750829100608826, | |
| "learning_rate": 0.0001251239950619149, | |
| "loss": 0.0335, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.1620553359683794, | |
| "grad_norm": 0.2763144373893738, | |
| "learning_rate": 0.00010657942003278107, | |
| "loss": 0.0296, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.4782608695652173, | |
| "grad_norm": 0.42852267622947693, | |
| "learning_rate": 8.78026925534108e-05, | |
| "loss": 0.0254, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.794466403162055, | |
| "grad_norm": 0.4685889780521393, | |
| "learning_rate": 6.945634264469339e-05, | |
| "loss": 0.0207, | |
| "step": 120 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 186, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 4.723094972352922e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |