| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 243, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12345679012345678, | |
| "grad_norm": 6.615536361844481, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.0007, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24691358024691357, | |
| "grad_norm": 1.9517030276543728, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.5003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 1.2616137032361001, | |
| "learning_rate": 9.98702585145264e-06, | |
| "loss": 0.3963, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": 1.1703778892793937, | |
| "learning_rate": 9.883636302119911e-06, | |
| "loss": 0.3598, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6172839506172839, | |
| "grad_norm": 0.9308014595748675, | |
| "learning_rate": 9.679000645102771e-06, | |
| "loss": 0.3459, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.9239080870941112, | |
| "learning_rate": 9.377361326497673e-06, | |
| "loss": 0.3467, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8641975308641975, | |
| "grad_norm": 0.9292175392332163, | |
| "learning_rate": 8.984971843707787e-06, | |
| "loss": 0.3371, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.9423895888927237, | |
| "learning_rate": 8.509967099778934e-06, | |
| "loss": 0.2955, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 1.0014547154310927, | |
| "learning_rate": 7.962194752988519e-06, | |
| "loss": 0.2394, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.2345679012345678, | |
| "grad_norm": 0.9750900984803165, | |
| "learning_rate": 7.353011058098104e-06, | |
| "loss": 0.2803, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3580246913580247, | |
| "grad_norm": 0.9897175591002245, | |
| "learning_rate": 6.695045431828524e-06, | |
| "loss": 0.2512, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 1.018954236882003, | |
| "learning_rate": 6.0019386235167055e-06, | |
| "loss": 0.2652, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.6049382716049383, | |
| "grad_norm": 1.1220883965697188, | |
| "learning_rate": 5.288059919122922e-06, | |
| "loss": 0.2907, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.7283950617283952, | |
| "grad_norm": 0.9390825986027425, | |
| "learning_rate": 4.568209241431615e-06, | |
| "loss": 0.2387, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.8518518518518519, | |
| "grad_norm": 1.1100888683091072, | |
| "learning_rate": 3.857310322416555e-06, | |
| "loss": 0.2614, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 1.1933595819251464, | |
| "learning_rate": 3.170101308830421e-06, | |
| "loss": 0.2313, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.0987654320987654, | |
| "grad_norm": 1.2310270632991422, | |
| "learning_rate": 2.520829215292426e-06, | |
| "loss": 0.2175, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 1.0112810436386979, | |
| "learning_rate": 1.9229545593825367e-06, | |
| "loss": 0.1842, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.3456790123456788, | |
| "grad_norm": 1.0391882674412423, | |
| "learning_rate": 1.388872302160353e-06, | |
| "loss": 0.1915, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "grad_norm": 1.0330142263823023, | |
| "learning_rate": 9.296548794875659e-07, | |
| "loss": 0.204, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.5925925925925926, | |
| "grad_norm": 0.8921694870341355, | |
| "learning_rate": 5.548226515528133e-07, | |
| "loss": 0.1984, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.7160493827160495, | |
| "grad_norm": 0.8915381430289088, | |
| "learning_rate": 2.721465295716996e-07, | |
| "loss": 0.1975, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.8395061728395063, | |
| "grad_norm": 1.0350358381925495, | |
| "learning_rate": 8.748687154702673e-08, | |
| "loss": 0.1757, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.9562619814768147, | |
| "learning_rate": 4.671987054842842e-09, | |
| "loss": 0.2137, | |
| "step": 240 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 243, | |
| "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": 9395391430656.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |