| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8859357696566998, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004429678848283499, | |
| "eval_loss": 10.838801383972168, | |
| "eval_runtime": 0.3434, | |
| "eval_samples_per_second": 276.62, | |
| "eval_steps_per_second": 139.766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0221483942414175, | |
| "grad_norm": 0.12922966480255127, | |
| "learning_rate": 5e-05, | |
| "loss": 10.8345, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.044296788482835, | |
| "grad_norm": 0.15409621596336365, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8351, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0664451827242525, | |
| "grad_norm": 0.16463850438594818, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 10.8363, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08859357696567, | |
| "grad_norm": 0.15971654653549194, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 10.8329, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11074197120708748, | |
| "grad_norm": 0.20640374720096588, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 10.8257, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.132890365448505, | |
| "grad_norm": 0.1784103512763977, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 10.8245, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15503875968992248, | |
| "grad_norm": 0.1995667666196823, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 10.8213, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.17718715393134, | |
| "grad_norm": 0.20601214468479156, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 10.8223, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19933554817275748, | |
| "grad_norm": 0.22217710316181183, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 10.8179, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22148394241417496, | |
| "grad_norm": 0.32868528366088867, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 10.8227, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22148394241417496, | |
| "eval_loss": 10.81373119354248, | |
| "eval_runtime": 0.337, | |
| "eval_samples_per_second": 281.9, | |
| "eval_steps_per_second": 142.434, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24363233665559247, | |
| "grad_norm": 0.25537627935409546, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 10.8066, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 0.2640365660190582, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 10.8066, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28792912513842744, | |
| "grad_norm": 0.2941606640815735, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 10.7951, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 0.3043847978115082, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 10.7888, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.33222591362126247, | |
| "grad_norm": 0.2664663791656494, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 10.7881, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.35437430786268, | |
| "grad_norm": 0.3024435341358185, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 10.7854, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.37652270210409744, | |
| "grad_norm": 0.3120448887348175, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 10.781, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.39867109634551495, | |
| "grad_norm": 0.2808491587638855, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 10.7733, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.42081949058693247, | |
| "grad_norm": 0.3052971065044403, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 10.7721, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4429678848283499, | |
| "grad_norm": 0.44799819588661194, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 10.7888, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4429678848283499, | |
| "eval_loss": 10.766999244689941, | |
| "eval_runtime": 0.3358, | |
| "eval_samples_per_second": 282.876, | |
| "eval_steps_per_second": 142.927, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 0.22693148255348206, | |
| "learning_rate": 5e-05, | |
| "loss": 10.7656, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.48726467331118495, | |
| "grad_norm": 0.25195586681365967, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 10.7628, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5094130675526024, | |
| "grad_norm": 0.24384839832782745, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 10.7586, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.53156146179402, | |
| "grad_norm": 0.21910274028778076, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 10.7505, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5537098560354374, | |
| "grad_norm": 0.2763572037220001, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 10.7494, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5758582502768549, | |
| "grad_norm": 0.23573029041290283, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 10.758, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5980066445182725, | |
| "grad_norm": 0.22336480021476746, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 10.7592, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 0.2121262103319168, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 10.7607, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6423034330011074, | |
| "grad_norm": 0.2790408134460449, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 10.75, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6644518272425249, | |
| "grad_norm": 0.36312904953956604, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 10.7721, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6644518272425249, | |
| "eval_loss": 10.751730918884277, | |
| "eval_runtime": 0.3354, | |
| "eval_samples_per_second": 283.275, | |
| "eval_steps_per_second": 143.128, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6866002214839424, | |
| "grad_norm": 0.23820596933364868, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 10.7486, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.70874861572536, | |
| "grad_norm": 0.1970384567975998, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 10.7485, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7308970099667774, | |
| "grad_norm": 0.1786661446094513, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 10.7446, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7530454042081949, | |
| "grad_norm": 0.18778419494628906, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 10.7532, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7751937984496124, | |
| "grad_norm": 0.19150562584400177, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 10.7434, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7973421926910299, | |
| "grad_norm": 0.1973363310098648, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 10.7504, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8194905869324474, | |
| "grad_norm": 0.221753790974617, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 10.753, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8416389811738649, | |
| "grad_norm": 0.225653275847435, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 10.7533, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8637873754152824, | |
| "grad_norm": 0.26362743973731995, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 10.7592, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8859357696566998, | |
| "grad_norm": 0.35018375515937805, | |
| "learning_rate": 0.0, | |
| "loss": 10.7569, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8859357696566998, | |
| "eval_loss": 10.749935150146484, | |
| "eval_runtime": 0.3361, | |
| "eval_samples_per_second": 282.658, | |
| "eval_steps_per_second": 142.817, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 32811830476800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |