| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0101010101010102, | |
| "eval_steps": 19, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013468013468013467, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013468013468013467, | |
| "eval_loss": NaN, | |
| "eval_runtime": 150.507, | |
| "eval_samples_per_second": 0.831, | |
| "eval_steps_per_second": 0.419, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026936026936026935, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04040404040404041, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05387205387205387, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06734006734006734, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09427609427609428, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10774410774410774, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13468013468013468, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994161134161634e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.976658173588244e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1750841750841751, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.947531997255256e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18855218855218855, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.906850630697068e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21548821548821548, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.791229145545831e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22895622895622897, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.716559066288715e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.630873244788883e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2558922558922559, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.534371804252728e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2558922558922559, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1562, | |
| "eval_samples_per_second": 30.076, | |
| "eval_steps_per_second": 15.158, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.26936026936026936, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2828282828282828, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.309848334400246e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.182350690051133e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.30976430976430974, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.898371770316111e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3367003367003367, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3501683501683502, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.577994803720606e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.405079293933986e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3771043771043771, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.224211063680853e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.39057239057239057, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.035812539093557e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4175084175084175, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.638201220530665e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43097643097643096, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.42991706621303e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.215957727996207e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.45791245791245794, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.996822917828477e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4713804713804714, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4983164983164983, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.313536890992935e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5117845117845118, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.078920983839031e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5117845117845118, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1693, | |
| "eval_samples_per_second": 29.981, | |
| "eval_steps_per_second": 15.11, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5252525252525253, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.841785206735192e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5387205387205387, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5521885521885522, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3621740008088126e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5656565656565656, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1208187261806615e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5791245791245792, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.87918127381934e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6378259991911886e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6195286195286195, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1582147932648074e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.632996632996633, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.92107901616097e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6464646464646465, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6864631090070655e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6599326599326599, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6734006734006734, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6868686868686869, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.003177082171523e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7003367003367004, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.784042272003794e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7138047138047138, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.57008293378697e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.361798779469336e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7542087542087542, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9641874609064443e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7676767676767676, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7757889363191483e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7676767676767676, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.5724, | |
| "eval_samples_per_second": 19.019, | |
| "eval_steps_per_second": 9.586, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7811447811447811, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5949207060660138e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.7946127946127947, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.422005196279395e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8215488215488216, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1016282296838887e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.835016835016835, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.176493099488663e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.8619528619528619, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.901516655997536e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8754208754208754, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.65628195747273e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.9023569023569024, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.691267552111183e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.9158249158249159, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8344093371128424e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.9292929292929293, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.087708544541689e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9427609427609428, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9562289562289562, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.314936930293283e-07, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.246800274474439e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.9831649831649831, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.334182641175686e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.9966329966329966, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.838865838366792e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.0101010101010102, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 19, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.83543405945815e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |