| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 558, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.26881720430107525, |
| "grad_norm": 0.35296472907066345, |
| "learning_rate": 4.375e-05, |
| "loss": 2.7131, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5376344086021505, |
| "grad_norm": 46.055992126464844, |
| "learning_rate": 4.5717131474103586e-05, |
| "loss": 2.2691, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8064516129032258, |
| "grad_norm": 85.04060363769531, |
| "learning_rate": 4.073705179282869e-05, |
| "loss": 0.7322, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.075268817204301, |
| "grad_norm": 7.298253059387207, |
| "learning_rate": 3.5756972111553785e-05, |
| "loss": 0.3116, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.3440860215053765, |
| "grad_norm": 17.628334045410156, |
| "learning_rate": 3.0776892430278885e-05, |
| "loss": 0.1814, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.6129032258064515, |
| "grad_norm": 24.634273529052734, |
| "learning_rate": 2.5796812749003984e-05, |
| "loss": 0.1889, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.881720430107527, |
| "grad_norm": 7.957954406738281, |
| "learning_rate": 2.0816733067729087e-05, |
| "loss": 0.1983, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.150537634408602, |
| "grad_norm": 6.165184497833252, |
| "learning_rate": 1.5836653386454183e-05, |
| "loss": 0.1158, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.4193548387096775, |
| "grad_norm": 1.3016605377197266, |
| "learning_rate": 1.0856573705179284e-05, |
| "loss": 0.0726, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.688172043010753, |
| "grad_norm": 0.6304020285606384, |
| "learning_rate": 5.8764940239043834e-06, |
| "loss": 0.07, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.956989247311828, |
| "grad_norm": 23.746200561523438, |
| "learning_rate": 8.964143426294822e-07, |
| "loss": 0.0833, |
| "step": 550 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 558, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
