| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.006012024048096, | |
| "eval_steps": 32, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008016032064128256, | |
| "eval_loss": 1.9255419969558716, | |
| "eval_runtime": 1.728, | |
| "eval_samples_per_second": 30.671, | |
| "eval_steps_per_second": 15.625, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04008016032064128, | |
| "grad_norm": 0.13588806986808777, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.6094, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08016032064128256, | |
| "grad_norm": 0.16010314226150513, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.7545, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12024048096192384, | |
| "grad_norm": 0.22482001781463623, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8474, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16032064128256512, | |
| "grad_norm": 0.20172171294689178, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.8395, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20040080160320642, | |
| "grad_norm": 0.3302512764930725, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.8735, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24048096192384769, | |
| "grad_norm": 0.3265620172023773, | |
| "learning_rate": 0.0001, | |
| "loss": 1.897, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2565130260521042, | |
| "eval_loss": 1.7114530801773071, | |
| "eval_runtime": 1.7112, | |
| "eval_samples_per_second": 30.973, | |
| "eval_steps_per_second": 15.779, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.280561122244489, | |
| "grad_norm": 0.2647479772567749, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.6295, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32064128256513025, | |
| "grad_norm": 0.31674087047576904, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.4848, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36072144288577157, | |
| "grad_norm": 0.34860819578170776, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.4407, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40080160320641284, | |
| "grad_norm": 0.36754506826400757, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.4599, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4408817635270541, | |
| "grad_norm": 0.4718535542488098, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.494, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48096192384769537, | |
| "grad_norm": 0.44895780086517334, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.3686, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5130260521042084, | |
| "eval_loss": 1.3507245779037476, | |
| "eval_runtime": 1.7092, | |
| "eval_samples_per_second": 31.009, | |
| "eval_steps_per_second": 15.797, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5210420841683366, | |
| "grad_norm": 0.4155556857585907, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 1.3898, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.561122244488978, | |
| "grad_norm": 0.3329876661300659, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 1.256, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6012024048096193, | |
| "grad_norm": 0.35974693298339844, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 1.2483, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6412825651302605, | |
| "grad_norm": 0.38245144486427307, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 1.24, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6813627254509018, | |
| "grad_norm": 0.3876368999481201, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 1.2751, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7214428857715431, | |
| "grad_norm": 0.4511187672615051, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 1.328, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7615230460921844, | |
| "grad_norm": 0.35906171798706055, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 1.2162, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7695390781563126, | |
| "eval_loss": 1.2686041593551636, | |
| "eval_runtime": 1.7108, | |
| "eval_samples_per_second": 30.979, | |
| "eval_steps_per_second": 15.782, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8016032064128257, | |
| "grad_norm": 0.37810012698173523, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 1.3341, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8416833667334669, | |
| "grad_norm": 0.406786173582077, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 1.2894, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8817635270541082, | |
| "grad_norm": 0.3965968191623688, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 1.2744, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9218436873747495, | |
| "grad_norm": 0.37193533778190613, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 1.1671, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9619238476953907, | |
| "grad_norm": 0.4367169141769409, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 1.2177, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.006012024048096, | |
| "grad_norm": 0.7495393753051758, | |
| "learning_rate": 0.0, | |
| "loss": 1.4924, | |
| "step": 125 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 9951787352064000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |