| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.050100200400801605, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000250501002004008, | |
| "eval_loss": 3.704983949661255, | |
| "eval_runtime": 18.3825, | |
| "eval_samples_per_second": 91.446, | |
| "eval_steps_per_second": 45.75, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00125250501002004, | |
| "grad_norm": 0.9701552391052246, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6869, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00250501002004008, | |
| "grad_norm": 1.407057523727417, | |
| "learning_rate": 0.0001, | |
| "loss": 3.577, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00375751503006012, | |
| "grad_norm": 1.114660620689392, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 3.6649, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00501002004008016, | |
| "grad_norm": 1.180700659751892, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 3.4819, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006262525050100201, | |
| "grad_norm": 1.1361351013183594, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 3.1851, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00751503006012024, | |
| "grad_norm": 1.2357608079910278, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 3.1741, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00876753507014028, | |
| "grad_norm": 1.252459168434143, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 3.1116, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01002004008016032, | |
| "grad_norm": 1.5677341222763062, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 2.9296, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011272545090180362, | |
| "grad_norm": 1.991075873374939, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 2.8175, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012525050100200401, | |
| "grad_norm": 1.5289764404296875, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 2.7057, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012525050100200401, | |
| "eval_loss": 2.62386417388916, | |
| "eval_runtime": 18.7414, | |
| "eval_samples_per_second": 89.694, | |
| "eval_steps_per_second": 44.874, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01377755511022044, | |
| "grad_norm": 1.3579661846160889, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 2.561, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01503006012024048, | |
| "grad_norm": 1.8097760677337646, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 2.5397, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01628256513026052, | |
| "grad_norm": 1.3172852993011475, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 2.4455, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01753507014028056, | |
| "grad_norm": 2.0352325439453125, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 2.4834, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.018787575150300603, | |
| "grad_norm": 1.3835731744766235, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 2.4561, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02004008016032064, | |
| "grad_norm": 1.4761914014816284, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 2.3603, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.021292585170340682, | |
| "grad_norm": 1.3032515048980713, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 2.2767, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.022545090180360723, | |
| "grad_norm": 1.3516151905059814, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 2.3037, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02379759519038076, | |
| "grad_norm": 1.2633843421936035, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 2.3047, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.025050100200400802, | |
| "grad_norm": 2.345054864883423, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 2.3067, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.025050100200400802, | |
| "eval_loss": 2.3011841773986816, | |
| "eval_runtime": 18.2416, | |
| "eval_samples_per_second": 92.152, | |
| "eval_steps_per_second": 46.103, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02630260521042084, | |
| "grad_norm": 1.3435356616973877, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2789, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02755511022044088, | |
| "grad_norm": 1.5827653408050537, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 2.2494, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.028807615230460923, | |
| "grad_norm": 1.6257189512252808, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 2.1587, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.03006012024048096, | |
| "grad_norm": 1.565990686416626, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 2.2483, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.031312625250501, | |
| "grad_norm": 1.6951042413711548, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 2.1623, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.03256513026052104, | |
| "grad_norm": 1.3800190687179565, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 2.1412, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03381763527054108, | |
| "grad_norm": 1.6663275957107544, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 2.1782, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.03507014028056112, | |
| "grad_norm": 1.4055718183517456, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 2.1664, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.036322645290581164, | |
| "grad_norm": 1.295013189315796, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 2.0866, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.037575150300601205, | |
| "grad_norm": 2.0372097492218018, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 2.0893, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.037575150300601205, | |
| "eval_loss": 2.1908504962921143, | |
| "eval_runtime": 18.5604, | |
| "eval_samples_per_second": 90.569, | |
| "eval_steps_per_second": 45.312, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03882765531062124, | |
| "grad_norm": 1.412229061126709, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 2.1178, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.04008016032064128, | |
| "grad_norm": 1.448472023010254, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 2.2415, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04133266533066132, | |
| "grad_norm": 1.5521998405456543, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 2.1963, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.042585170340681364, | |
| "grad_norm": 1.5726743936538696, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 2.2136, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.043837675350701405, | |
| "grad_norm": 1.397105097770691, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 2.1761, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.045090180360721446, | |
| "grad_norm": 1.438555359840393, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 2.0546, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04634268537074148, | |
| "grad_norm": 1.6175150871276855, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 2.149, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.04759519038076152, | |
| "grad_norm": 1.9222791194915771, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 2.1708, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.04884769539078156, | |
| "grad_norm": 1.566523790359497, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 2.1843, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.050100200400801605, | |
| "grad_norm": 1.3286877870559692, | |
| "learning_rate": 0.0, | |
| "loss": 2.1899, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.050100200400801605, | |
| "eval_loss": 2.1727023124694824, | |
| "eval_runtime": 18.36, | |
| "eval_samples_per_second": 91.558, | |
| "eval_steps_per_second": 45.806, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1371706019020800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |