| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9963060686015831, | |
| "eval_steps": 500, | |
| "global_step": 236, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04221635883905013, | |
| "grad_norm": 0.50788813829422, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.0916, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08443271767810026, | |
| "grad_norm": 0.31596097350120544, | |
| "learning_rate": 2.9996874776728528e-05, | |
| "loss": 3.8989, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1266490765171504, | |
| "grad_norm": 0.28351184725761414, | |
| "learning_rate": 2.998418103705505e-05, | |
| "loss": 3.6225, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16886543535620052, | |
| "grad_norm": 0.2747008502483368, | |
| "learning_rate": 2.996173263030885e-05, | |
| "loss": 3.3931, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21108179419525067, | |
| "grad_norm": 0.27435237169265747, | |
| "learning_rate": 2.9929545796017835e-05, | |
| "loss": 3.1614, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2532981530343008, | |
| "grad_norm": 0.31030479073524475, | |
| "learning_rate": 2.9887643818640412e-05, | |
| "loss": 2.882, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2955145118733509, | |
| "grad_norm": 0.3085922598838806, | |
| "learning_rate": 2.983605701072119e-05, | |
| "loss": 2.6283, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.33773087071240104, | |
| "grad_norm": 0.230041041970253, | |
| "learning_rate": 2.9774822690962358e-05, | |
| "loss": 2.3723, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.37994722955145116, | |
| "grad_norm": 0.19185876846313477, | |
| "learning_rate": 2.9703985157226802e-05, | |
| "loss": 2.1931, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.42216358839050133, | |
| "grad_norm": 0.17534567415714264, | |
| "learning_rate": 2.9623595654492328e-05, | |
| "loss": 2.1193, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.46437994722955145, | |
| "grad_norm": 0.15833114087581635, | |
| "learning_rate": 2.953371233778022e-05, | |
| "loss": 2.0044, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5065963060686016, | |
| "grad_norm": 0.152941033244133, | |
| "learning_rate": 2.943440023008502e-05, | |
| "loss": 2.0208, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5488126649076517, | |
| "grad_norm": 0.14308719336986542, | |
| "learning_rate": 2.932573117533585e-05, | |
| "loss": 2.0013, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5910290237467019, | |
| "grad_norm": 0.12415236979722977, | |
| "learning_rate": 2.9207783786423436e-05, | |
| "loss": 1.9719, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.633245382585752, | |
| "grad_norm": 0.14564257860183716, | |
| "learning_rate": 2.9080643388330266e-05, | |
| "loss": 1.9659, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6754617414248021, | |
| "grad_norm": 0.14092124998569489, | |
| "learning_rate": 2.8944401956405192e-05, | |
| "loss": 1.9645, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7176781002638523, | |
| "grad_norm": 0.14931683242321014, | |
| "learning_rate": 2.8799158049827027e-05, | |
| "loss": 1.902, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7598944591029023, | |
| "grad_norm": 0.13305355608463287, | |
| "learning_rate": 2.8645016740305286e-05, | |
| "loss": 2.0203, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8021108179419525, | |
| "grad_norm": 0.13253405690193176, | |
| "learning_rate": 2.8482089536069683e-05, | |
| "loss": 1.92, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8443271767810027, | |
| "grad_norm": 0.15814724564552307, | |
| "learning_rate": 2.8310494301203323e-05, | |
| "loss": 1.9354, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8865435356200527, | |
| "grad_norm": 0.12858152389526367, | |
| "learning_rate": 2.8130355170378002e-05, | |
| "loss": 1.8576, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9287598944591029, | |
| "grad_norm": 0.15734779834747314, | |
| "learning_rate": 2.7941802459053222e-05, | |
| "loss": 1.8994, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9709762532981531, | |
| "grad_norm": 0.13302397727966309, | |
| "learning_rate": 2.7744972569203985e-05, | |
| "loss": 1.9127, | |
| "step": 230 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1180, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 1.069072485482496e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |