| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 5, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04060913705583756, |
| "grad_norm": 0.14325366914272308, |
| "learning_rate": 0.0, |
| "loss": 1.7207, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.08121827411167512, |
| "grad_norm": 0.06042660400271416, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.1313, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.1218274111675127, |
| "grad_norm": 0.10992968082427979, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 1.5121, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.16243654822335024, |
| "grad_norm": 0.09151983261108398, |
| "learning_rate": 0.0001, |
| "loss": 1.1648, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.20304568527918782, |
| "grad_norm": 0.08963117748498917, |
| "learning_rate": 9.954196488464198e-05, |
| "loss": 1.2226, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.20304568527918782, |
| "eval_loss": 1.2259185314178467, |
| "eval_runtime": 2.4501, |
| "eval_samples_per_second": 2.041, |
| "eval_steps_per_second": 0.408, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2436548223350254, |
| "grad_norm": 0.11823192238807678, |
| "learning_rate": 9.81771838126524e-05, |
| "loss": 1.0848, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.28426395939086296, |
| "grad_norm": 0.1623338758945465, |
| "learning_rate": 9.593343979095333e-05, |
| "loss": 1.3967, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3248730964467005, |
| "grad_norm": 0.13381925225257874, |
| "learning_rate": 9.285640897740315e-05, |
| "loss": 1.4821, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.36548223350253806, |
| "grad_norm": 0.0808931291103363, |
| "learning_rate": 8.900873084594164e-05, |
| "loss": 1.0707, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.40609137055837563, |
| "grad_norm": 0.09358401596546173, |
| "learning_rate": 8.446873302753784e-05, |
| "loss": 1.2233, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.40609137055837563, |
| "eval_loss": 1.1297461986541748, |
| "eval_runtime": 2.4101, |
| "eval_samples_per_second": 2.075, |
| "eval_steps_per_second": 0.415, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4467005076142132, |
| "grad_norm": 0.07968752086162567, |
| "learning_rate": 7.93288367855019e-05, |
| "loss": 1.0929, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4873096446700508, |
| "grad_norm": 0.08660563081502914, |
| "learning_rate": 7.369367558508489e-05, |
| "loss": 1.1422, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5279187817258884, |
| "grad_norm": 0.08944746851921082, |
| "learning_rate": 6.767796505786435e-05, |
| "loss": 1.1354, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5685279187817259, |
| "grad_norm": 0.08512604236602783, |
| "learning_rate": 6.140416772229784e-05, |
| "loss": 1.1468, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6091370558375635, |
| "grad_norm": 0.060771163552999496, |
| "learning_rate": 5.500000000000001e-05, |
| "loss": 0.9811, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6091370558375635, |
| "eval_loss": 1.0929244756698608, |
| "eval_runtime": 2.3979, |
| "eval_samples_per_second": 2.085, |
| "eval_steps_per_second": 0.417, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.649746192893401, |
| "grad_norm": 0.08931197226047516, |
| "learning_rate": 4.859583227770218e-05, |
| "loss": 1.192, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.6903553299492385, |
| "grad_norm": 0.07212094217538834, |
| "learning_rate": 4.232203494213567e-05, |
| "loss": 0.9975, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7309644670050761, |
| "grad_norm": 0.08329902589321136, |
| "learning_rate": 3.630632441491512e-05, |
| "loss": 1.112, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7715736040609137, |
| "grad_norm": 0.0639733150601387, |
| "learning_rate": 3.067116321449813e-05, |
| "loss": 1.0809, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.8121827411167513, |
| "grad_norm": 0.04949946328997612, |
| "learning_rate": 2.5531266972462177e-05, |
| "loss": 0.9506, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8121827411167513, |
| "eval_loss": 1.0761111974716187, |
| "eval_runtime": 2.3972, |
| "eval_samples_per_second": 2.086, |
| "eval_steps_per_second": 0.417, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8527918781725888, |
| "grad_norm": 0.0763203576207161, |
| "learning_rate": 2.0991269154058385e-05, |
| "loss": 1.1912, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8934010152284264, |
| "grad_norm": 0.08623254299163818, |
| "learning_rate": 1.7143591022596845e-05, |
| "loss": 1.1505, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.934010152284264, |
| "grad_norm": 0.09479203075170517, |
| "learning_rate": 1.4066560209046673e-05, |
| "loss": 1.3198, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9746192893401016, |
| "grad_norm": 0.07144231349229813, |
| "learning_rate": 1.1822816187347623e-05, |
| "loss": 1.0606, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.08518268167972565, |
| "learning_rate": 1.0458035115358032e-05, |
| "loss": 1.1098, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.0701267719268799, |
| "eval_runtime": 2.3956, |
| "eval_samples_per_second": 2.087, |
| "eval_steps_per_second": 0.417, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 25, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.269669952833192e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
