| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 222, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13513513513513514, |
| "grad_norm": 3.246851921081543, |
| "learning_rate": 2.9985590229902075e-05, |
| "loss": 0.9981, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2702702702702703, |
| "grad_norm": 2.6752474308013916, |
| "learning_rate": 2.9730185992421254e-05, |
| "loss": 0.9153, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.40540540540540543, |
| "grad_norm": 2.484593391418457, |
| "learning_rate": 2.9160833414327637e-05, |
| "loss": 0.8844, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5405405405405406, |
| "grad_norm": 2.1777572631835938, |
| "learning_rate": 2.828966725734167e-05, |
| "loss": 0.8282, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6756756756756757, |
| "grad_norm": 2.242386817932129, |
| "learning_rate": 2.7135254915624213e-05, |
| "loss": 0.8295, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8108108108108109, |
| "grad_norm": 2.2411763668060303, |
| "learning_rate": 2.5722200684005718e-05, |
| "loss": 0.8388, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9459459459459459, |
| "grad_norm": 2.4796392917633057, |
| "learning_rate": 2.408062136015872e-05, |
| "loss": 0.738, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0810810810810811, |
| "grad_norm": 2.1897037029266357, |
| "learning_rate": 2.224550435734272e-05, |
| "loss": 0.7047, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.2162162162162162, |
| "grad_norm": 2.007591724395752, |
| "learning_rate": 2.025596200843394e-05, |
| "loss": 0.5431, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.3513513513513513, |
| "grad_norm": 2.17893648147583, |
| "learning_rate": 1.8154397954454996e-05, |
| "loss": 0.4875, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4864864864864864, |
| "grad_norm": 2.388317584991455, |
| "learning_rate": 1.5985603384585545e-05, |
| "loss": 0.5281, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.6216216216216215, |
| "grad_norm": 2.5765843391418457, |
| "learning_rate": 1.3795802389729185e-05, |
| "loss": 0.5056, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.7567567567567568, |
| "grad_norm": 2.7746734619140625, |
| "learning_rate": 1.1631666776267804e-05, |
| "loss": 0.5434, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.8918918918918919, |
| "grad_norm": 2.220118761062622, |
| "learning_rate": 9.5393213375378e-06, |
| "loss": 0.4903, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.027027027027027, |
| "grad_norm": 2.0366766452789307, |
| "learning_rate": 7.563360783939724e-06, |
| "loss": 0.5343, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.1621621621621623, |
| "grad_norm": 1.8910408020019531, |
| "learning_rate": 5.7458992841091544e-06, |
| "loss": 0.336, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.2972972972972974, |
| "grad_norm": 2.4479243755340576, |
| "learning_rate": 4.125672874528797e-06, |
| "loss": 0.3423, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.4324324324324325, |
| "grad_norm": 2.0346922874450684, |
| "learning_rate": 2.7372138681624246e-06, |
| "loss": 0.3206, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.5675675675675675, |
| "grad_norm": 1.753401279449463, |
| "learning_rate": 1.6101148581573276e-06, |
| "loss": 0.3201, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.7027027027027026, |
| "grad_norm": 2.1877281665802, |
| "learning_rate": 7.683980030985655e-07, |
| "loss": 0.3051, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.8378378378378377, |
| "grad_norm": 1.7870614528656006, |
| "learning_rate": 2.300030364048139e-07, |
| "loss": 0.3445, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.972972972972973, |
| "grad_norm": 1.6742513179779053, |
| "learning_rate": 6.404912056610091e-09, |
| "loss": 0.3238, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 222, |
| "total_flos": 7707233982873600.0, |
| "train_loss": 0.5738734350548135, |
| "train_runtime": 373.8141, |
| "train_samples_per_second": 9.438, |
| "train_steps_per_second": 0.594 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 222, |
| "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": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7707233982873600.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
