| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5784526391901663, |
| "eval_steps": 50, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.028922631959508314, |
| "grad_norm": 0.3374865651130676, |
| "learning_rate": 0.00018, |
| "loss": 2.0231, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05784526391901663, |
| "grad_norm": 0.20978349447250366, |
| "learning_rate": 0.0001905263157894737, |
| "loss": 1.1149, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.08676789587852494, |
| "grad_norm": 0.11324426531791687, |
| "learning_rate": 0.00018, |
| "loss": 0.8403, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.11569052783803326, |
| "grad_norm": 0.10928981751203537, |
| "learning_rate": 0.00016947368421052633, |
| "loss": 0.7539, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.14461315979754158, |
| "grad_norm": 0.08820035308599472, |
| "learning_rate": 0.00015894736842105264, |
| "loss": 0.7341, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1735357917570499, |
| "grad_norm": 0.1019802913069725, |
| "learning_rate": 0.00014842105263157895, |
| "loss": 0.6881, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2024584237165582, |
| "grad_norm": 0.10406459867954254, |
| "learning_rate": 0.00013789473684210527, |
| "loss": 0.6202, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2313810556760665, |
| "grad_norm": 0.1173112764954567, |
| "learning_rate": 0.00012736842105263158, |
| "loss": 0.6308, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2603036876355748, |
| "grad_norm": 0.11734358966350555, |
| "learning_rate": 0.00011684210526315791, |
| "loss": 0.6048, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.28922631959508316, |
| "grad_norm": 0.13270510733127594, |
| "learning_rate": 0.00010631578947368421, |
| "loss": 0.6347, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.31814895155459144, |
| "grad_norm": 0.127024307847023, |
| "learning_rate": 9.578947368421052e-05, |
| "loss": 0.5998, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.3470715835140998, |
| "grad_norm": 0.1302337944507599, |
| "learning_rate": 8.526315789473685e-05, |
| "loss": 0.5987, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.3759942154736081, |
| "grad_norm": 0.11779110878705978, |
| "learning_rate": 7.473684210526316e-05, |
| "loss": 0.5897, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.4049168474331164, |
| "grad_norm": 0.12403657287359238, |
| "learning_rate": 6.421052631578948e-05, |
| "loss": 0.5914, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.43383947939262474, |
| "grad_norm": 0.12974581122398376, |
| "learning_rate": 5.368421052631579e-05, |
| "loss": 0.603, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.462762111352133, |
| "grad_norm": 0.12593378126621246, |
| "learning_rate": 4.3157894736842105e-05, |
| "loss": 0.5707, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.49168474331164136, |
| "grad_norm": 0.1275719851255417, |
| "learning_rate": 3.2631578947368426e-05, |
| "loss": 0.546, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.5206073752711496, |
| "grad_norm": 0.1218939870595932, |
| "learning_rate": 2.2105263157894736e-05, |
| "loss": 0.5871, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.549530007230658, |
| "grad_norm": 0.10984767973423004, |
| "learning_rate": 1.1578947368421053e-05, |
| "loss": 0.5978, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.5784526391901663, |
| "grad_norm": 0.1242329478263855, |
| "learning_rate": 1.0526315789473685e-06, |
| "loss": 0.5879, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5784526391901663, |
| "step": 200, |
| "total_flos": 4.2983824905968026e+17, |
| "train_loss": 0.7258491277694702, |
| "train_runtime": 2490.1271, |
| "train_samples_per_second": 2.57, |
| "train_steps_per_second": 0.08 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.2983824905968026e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
