| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9019165727170236, |
| "eval_steps": 50, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04509582863585118, |
| "grad_norm": 6.922323518665507e-05, |
| "learning_rate": 3.9130434782608694e-07, |
| "loss": 1.6552, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.09019165727170236, |
| "grad_norm": 5.8861107390839607e-05, |
| "learning_rate": 8.260869565217391e-07, |
| "loss": 1.7093, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13528748590755355, |
| "grad_norm": 6.818149995524436e-05, |
| "learning_rate": 9.97758641300553e-07, |
| "loss": 1.6896, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.18038331454340473, |
| "grad_norm": 5.447689909487963e-05, |
| "learning_rate": 9.841341526992535e-07, |
| "loss": 1.9092, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2254791431792559, |
| "grad_norm": 4.812038241652772e-05, |
| "learning_rate": 9.584688140963944e-07, |
| "loss": 1.5902, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2254791431792559, |
| "eval_loss": 1.7812579870224, |
| "eval_runtime": 39.3359, |
| "eval_samples_per_second": 4.754, |
| "eval_steps_per_second": 2.39, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2705749718151071, |
| "grad_norm": 4.578845982905477e-05, |
| "learning_rate": 9.214009454506752e-07, |
| "loss": 1.5573, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.3156708004509583, |
| "grad_norm": 5.378470086725429e-05, |
| "learning_rate": 8.738524578558546e-07, |
| "loss": 1.6926, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.36076662908680945, |
| "grad_norm": 4.728526255348697e-05, |
| "learning_rate": 8.170059247861193e-07, |
| "loss": 1.6041, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.40586245772266066, |
| "grad_norm": 3.9639940951019526e-05, |
| "learning_rate": 7.522751704345887e-07, |
| "loss": 1.4226, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4509582863585118, |
| "grad_norm": 4.501069270190783e-05, |
| "learning_rate": 6.812701066393123e-07, |
| "loss": 1.5622, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4509582863585118, |
| "eval_loss": 1.648553729057312, |
| "eval_runtime": 38.7156, |
| "eval_samples_per_second": 4.83, |
| "eval_steps_per_second": 2.428, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.496054114994363, |
| "grad_norm": 3.845913670375012e-05, |
| "learning_rate": 6.057566929339095e-07, |
| "loss": 1.4544, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.5411499436302142, |
| "grad_norm": 4.5064221922075376e-05, |
| "learning_rate": 5.27613015552254e-07, |
| "loss": 1.5299, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5862457722660653, |
| "grad_norm": 1.8545288185123354e-05, |
| "learning_rate": 4.4878257774169345e-07, |
| "loss": 1.4496, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.6313416009019166, |
| "grad_norm": 3.569232649169862e-05, |
| "learning_rate": 3.7122596309655174e-07, |
| "loss": 1.4476, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6764374295377678, |
| "grad_norm": 2.6302534024580382e-05, |
| "learning_rate": 2.9687207408810555e-07, |
| "loss": 1.4962, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6764374295377678, |
| "eval_loss": 1.5979574918746948, |
| "eval_runtime": 38.7777, |
| "eval_samples_per_second": 4.822, |
| "eval_steps_per_second": 2.424, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.7215332581736189, |
| "grad_norm": 3.0995302950032055e-05, |
| "learning_rate": 2.275701585324649e-07, |
| "loss": 1.374, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7666290868094702, |
| "grad_norm": 3.3021700801327825e-05, |
| "learning_rate": 1.6504381714107252e-07, |
| "loss": 1.4554, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.8117249154453213, |
| "grad_norm": 2.8384956749505363e-05, |
| "learning_rate": 1.1084813602723514e-07, |
| "loss": 1.4978, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.8568207440811725, |
| "grad_norm": 3.126484443782829e-05, |
| "learning_rate": 6.633101032164273e-08, |
| "loss": 1.5816, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.9019165727170236, |
| "grad_norm": 2.8435692001949064e-05, |
| "learning_rate": 3.2599620813200835e-08, |
| "loss": 1.4841, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9019165727170236, |
| "eval_loss": 1.5861315727233887, |
| "eval_runtime": 38.6811, |
| "eval_samples_per_second": 4.834, |
| "eval_steps_per_second": 2.43, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 222, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.1184814522587136e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
