| { |
| "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": 3.4628968238830566, |
| "learning_rate": 2.9985590229902075e-05, |
| "loss": 0.9977, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2702702702702703, |
| "grad_norm": 3.1211934089660645, |
| "learning_rate": 2.9730185992421254e-05, |
| "loss": 0.8362, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.40540540540540543, |
| "grad_norm": 2.522186756134033, |
| "learning_rate": 2.9160833414327637e-05, |
| "loss": 0.8647, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5405405405405406, |
| "grad_norm": 2.729247570037842, |
| "learning_rate": 2.828966725734167e-05, |
| "loss": 0.837, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6756756756756757, |
| "grad_norm": 2.6614463329315186, |
| "learning_rate": 2.7135254915624213e-05, |
| "loss": 0.8413, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8108108108108109, |
| "grad_norm": 3.090808391571045, |
| "learning_rate": 2.5722200684005718e-05, |
| "loss": 0.9284, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9459459459459459, |
| "grad_norm": 2.503873825073242, |
| "learning_rate": 2.408062136015872e-05, |
| "loss": 0.7899, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0810810810810811, |
| "grad_norm": 2.2136685848236084, |
| "learning_rate": 2.224550435734272e-05, |
| "loss": 0.6479, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.2162162162162162, |
| "grad_norm": 2.1826860904693604, |
| "learning_rate": 2.025596200843394e-05, |
| "loss": 0.6081, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.3513513513513513, |
| "grad_norm": 2.014763593673706, |
| "learning_rate": 1.8154397954454996e-05, |
| "loss": 0.5017, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4864864864864864, |
| "grad_norm": 2.49580454826355, |
| "learning_rate": 1.5985603384585545e-05, |
| "loss": 0.5468, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.6216216216216215, |
| "grad_norm": 2.2139554023742676, |
| "learning_rate": 1.3795802389729185e-05, |
| "loss": 0.482, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.7567567567567568, |
| "grad_norm": 2.7212271690368652, |
| "learning_rate": 1.1631666776267804e-05, |
| "loss": 0.5352, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.8918918918918919, |
| "grad_norm": 2.4166877269744873, |
| "learning_rate": 9.5393213375378e-06, |
| "loss": 0.4888, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.027027027027027, |
| "grad_norm": 2.273552179336548, |
| "learning_rate": 7.563360783939724e-06, |
| "loss": 0.5366, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.1621621621621623, |
| "grad_norm": 1.7606693506240845, |
| "learning_rate": 5.7458992841091544e-06, |
| "loss": 0.3542, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.2972972972972974, |
| "grad_norm": 2.0976758003234863, |
| "learning_rate": 4.125672874528797e-06, |
| "loss": 0.3404, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.4324324324324325, |
| "grad_norm": 1.9870134592056274, |
| "learning_rate": 2.7372138681624246e-06, |
| "loss": 0.3338, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.5675675675675675, |
| "grad_norm": 2.1549744606018066, |
| "learning_rate": 1.6101148581573276e-06, |
| "loss": 0.3467, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.7027027027027026, |
| "grad_norm": 2.2090368270874023, |
| "learning_rate": 7.683980030985655e-07, |
| "loss": 0.3048, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.8378378378378377, |
| "grad_norm": 1.95921790599823, |
| "learning_rate": 2.300030364048139e-07, |
| "loss": 0.3687, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.972972972972973, |
| "grad_norm": 1.614331603050232, |
| "learning_rate": 6.404912056610091e-09, |
| "loss": 0.3171, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 222, |
| "total_flos": 7707233982873600.0, |
| "train_loss": 0.5811844650689546, |
| "train_runtime": 78.8486, |
| "train_samples_per_second": 44.744, |
| "train_steps_per_second": 2.816 |
| } |
| ], |
| "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 |
| } |
|
|
