| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.896, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 3.609203815460205, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.4792, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 3.4065887928009033, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.4425, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 3.396181583404541, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4887, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 1.740384578704834, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.3527, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.299846887588501, | |
| "learning_rate": 9.86522435289912e-06, | |
| "loss": 0.3075, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 1.0410711765289307, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.3255, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 0.9354220628738403, | |
| "learning_rate": 9.468163201617063e-06, | |
| "loss": 0.2772, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.684252917766571, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.2475, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 0.548189640045166, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.2523, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.5903598070144653, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.2553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.064, | |
| "grad_norm": 1.125814437866211, | |
| "learning_rate": 7.985792958513932e-06, | |
| "loss": 0.4129, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.6294312477111816, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.2131, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.256, | |
| "grad_norm": 0.6567461490631104, | |
| "learning_rate": 6.980398830195785e-06, | |
| "loss": 0.2005, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3519999999999999, | |
| "grad_norm": 0.5858513712882996, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.2022, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.448, | |
| "grad_norm": 0.6008303761482239, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.1983, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.544, | |
| "grad_norm": 0.6003760099411011, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.1655, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 0.5758850574493408, | |
| "learning_rate": 4.7092758554476215e-06, | |
| "loss": 0.1897, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.736, | |
| "grad_norm": 0.5658831000328064, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.1846, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8319999999999999, | |
| "grad_norm": 0.4785068929195404, | |
| "learning_rate": 3.5659838364445505e-06, | |
| "loss": 0.1496, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.928, | |
| "grad_norm": 0.5116356015205383, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.1628, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.032, | |
| "grad_norm": 0.9877704381942749, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.2728, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.128, | |
| "grad_norm": 0.51435786485672, | |
| "learning_rate": 2.0142070414860704e-06, | |
| "loss": 0.1391, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.224, | |
| "grad_norm": 0.4802136719226837, | |
| "learning_rate": 1.5687918106563326e-06, | |
| "loss": 0.1173, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 0.45264706015586853, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.1175, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.416, | |
| "grad_norm": 0.506596565246582, | |
| "learning_rate": 8.225609429353187e-07, | |
| "loss": 0.139, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.512, | |
| "grad_norm": 0.5231615304946899, | |
| "learning_rate": 5.318367983829393e-07, | |
| "loss": 0.1215, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.608, | |
| "grad_norm": 0.4291784167289734, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 0.1056, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.7039999999999997, | |
| "grad_norm": 0.4940212666988373, | |
| "learning_rate": 1.3477564710088097e-07, | |
| "loss": 0.1158, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.4577478766441345, | |
| "learning_rate": 3.3808211290284886e-08, | |
| "loss": 0.1173, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.896, | |
| "grad_norm": 0.48457086086273193, | |
| "learning_rate": 0.0, | |
| "loss": 0.1155, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.896, | |
| "step": 30, | |
| "total_flos": 14576698425344.0, | |
| "train_loss": 0.2289695508778095, | |
| "train_runtime": 1925.3202, | |
| "train_samples_per_second": 1.558, | |
| "train_steps_per_second": 0.016 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 14576698425344.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |