{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.4982456140350875, "eval_steps": 500, "global_step": 500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.07017543859649122, "grad_norm": 5993.8466796875, "learning_rate": 1.8e-05, "loss": 0.1944, "step": 10 }, { "epoch": 0.14035087719298245, "grad_norm": 3562.712646484375, "learning_rate": 3.8e-05, "loss": 0.1443, "step": 20 }, { "epoch": 0.21052631578947367, "grad_norm": 3539.65087890625, "learning_rate": 5.8e-05, "loss": 0.1224, "step": 30 }, { "epoch": 0.2807017543859649, "grad_norm": 3544.288330078125, "learning_rate": 7.800000000000001e-05, "loss": 0.0958, "step": 40 }, { "epoch": 0.3508771929824561, "grad_norm": 5689.3173828125, "learning_rate": 9.8e-05, "loss": 0.1047, "step": 50 }, { "epoch": 0.42105263157894735, "grad_norm": 4658.375, "learning_rate": 9.827586206896552e-05, "loss": 0.0718, "step": 60 }, { "epoch": 0.49122807017543857, "grad_norm": 4036.04052734375, "learning_rate": 9.6360153256705e-05, "loss": 0.0741, "step": 70 }, { "epoch": 0.5614035087719298, "grad_norm": 4587.62841796875, "learning_rate": 9.444444444444444e-05, "loss": 0.068, "step": 80 }, { "epoch": 0.631578947368421, "grad_norm": 4352.63671875, "learning_rate": 9.252873563218392e-05, "loss": 0.0653, "step": 90 }, { "epoch": 0.7017543859649122, "grad_norm": 5600.20703125, "learning_rate": 9.061302681992338e-05, "loss": 0.0679, "step": 100 }, { "epoch": 0.7719298245614035, "grad_norm": 3705.227294921875, "learning_rate": 8.869731800766284e-05, "loss": 0.0623, "step": 110 }, { "epoch": 0.8421052631578947, "grad_norm": 4062.218505859375, "learning_rate": 8.67816091954023e-05, "loss": 0.0622, "step": 120 }, { "epoch": 0.9122807017543859, "grad_norm": 4199.43994140625, "learning_rate": 8.486590038314178e-05, "loss": 0.059, "step": 130 }, { "epoch": 0.9824561403508771, "grad_norm": 3701.624267578125, "learning_rate": 8.295019157088123e-05, "loss": 0.0588, "step": 140 }, { "epoch": 1.0491228070175438, "grad_norm": 4788.91552734375, "learning_rate": 8.103448275862069e-05, "loss": 0.0598, "step": 150 }, { "epoch": 1.119298245614035, "grad_norm": 3091.700439453125, "learning_rate": 7.911877394636016e-05, "loss": 0.056, "step": 160 }, { "epoch": 1.1894736842105262, "grad_norm": 3443.362548828125, "learning_rate": 7.720306513409961e-05, "loss": 0.0557, "step": 170 }, { "epoch": 1.2596491228070175, "grad_norm": 3259.4931640625, "learning_rate": 7.528735632183909e-05, "loss": 0.0495, "step": 180 }, { "epoch": 1.329824561403509, "grad_norm": 3825.1728515625, "learning_rate": 7.337164750957855e-05, "loss": 0.0535, "step": 190 }, { "epoch": 1.4, "grad_norm": 3203.66552734375, "learning_rate": 7.145593869731801e-05, "loss": 0.0489, "step": 200 }, { "epoch": 1.4701754385964914, "grad_norm": 4477.1640625, "learning_rate": 6.954022988505747e-05, "loss": 0.0508, "step": 210 }, { "epoch": 1.5403508771929824, "grad_norm": 4661.5703125, "learning_rate": 6.762452107279695e-05, "loss": 0.0436, "step": 220 }, { "epoch": 1.6105263157894738, "grad_norm": 3914.212890625, "learning_rate": 6.570881226053641e-05, "loss": 0.0496, "step": 230 }, { "epoch": 1.6807017543859648, "grad_norm": 5168.2548828125, "learning_rate": 6.379310344827587e-05, "loss": 0.0517, "step": 240 }, { "epoch": 1.7508771929824563, "grad_norm": 3639.001953125, "learning_rate": 6.187739463601533e-05, "loss": 0.0522, "step": 250 }, { "epoch": 1.8210526315789473, "grad_norm": 4367.4833984375, "learning_rate": 5.9961685823754786e-05, "loss": 0.0502, "step": 260 }, { "epoch": 1.8912280701754387, "grad_norm": 3486.47607421875, "learning_rate": 5.8045977011494254e-05, "loss": 0.0456, "step": 270 }, { "epoch": 1.9614035087719297, "grad_norm": 3831.04736328125, "learning_rate": 5.6130268199233716e-05, "loss": 0.0486, "step": 280 }, { "epoch": 2.0280701754385966, "grad_norm": 3694.040283203125, "learning_rate": 5.4214559386973184e-05, "loss": 0.0413, "step": 290 }, { "epoch": 2.0982456140350876, "grad_norm": 3733.336669921875, "learning_rate": 5.2298850574712646e-05, "loss": 0.046, "step": 300 }, { "epoch": 2.168421052631579, "grad_norm": 4054.663818359375, "learning_rate": 5.0383141762452114e-05, "loss": 0.0429, "step": 310 }, { "epoch": 2.23859649122807, "grad_norm": 3458.208251953125, "learning_rate": 4.846743295019157e-05, "loss": 0.042, "step": 320 }, { "epoch": 2.3087719298245615, "grad_norm": 4682.77294921875, "learning_rate": 4.655172413793104e-05, "loss": 0.0415, "step": 330 }, { "epoch": 2.3789473684210525, "grad_norm": 3480.484130859375, "learning_rate": 4.46360153256705e-05, "loss": 0.0398, "step": 340 }, { "epoch": 2.449122807017544, "grad_norm": 3643.171630859375, "learning_rate": 4.272030651340996e-05, "loss": 0.0403, "step": 350 }, { "epoch": 2.519298245614035, "grad_norm": 3384.7724609375, "learning_rate": 4.080459770114943e-05, "loss": 0.0403, "step": 360 }, { "epoch": 2.5894736842105264, "grad_norm": 5074.3017578125, "learning_rate": 3.888888888888889e-05, "loss": 0.0451, "step": 370 }, { "epoch": 2.659649122807018, "grad_norm": 4794.37646484375, "learning_rate": 3.697318007662835e-05, "loss": 0.0409, "step": 380 }, { "epoch": 2.729824561403509, "grad_norm": 3055.15869140625, "learning_rate": 3.505747126436782e-05, "loss": 0.0394, "step": 390 }, { "epoch": 2.8, "grad_norm": 4893.79052734375, "learning_rate": 3.314176245210728e-05, "loss": 0.0471, "step": 400 }, { "epoch": 2.8701754385964913, "grad_norm": 4101.93017578125, "learning_rate": 3.1226053639846744e-05, "loss": 0.0478, "step": 410 }, { "epoch": 2.9403508771929827, "grad_norm": 3935.029052734375, "learning_rate": 2.9310344827586206e-05, "loss": 0.0381, "step": 420 }, { "epoch": 3.007017543859649, "grad_norm": 4287.02880859375, "learning_rate": 2.739463601532567e-05, "loss": 0.0397, "step": 430 }, { "epoch": 3.07719298245614, "grad_norm": 3702.27490234375, "learning_rate": 2.5478927203065132e-05, "loss": 0.0355, "step": 440 }, { "epoch": 3.1473684210526316, "grad_norm": 4088.54052734375, "learning_rate": 2.3563218390804597e-05, "loss": 0.0356, "step": 450 }, { "epoch": 3.2175438596491226, "grad_norm": 5307.07470703125, "learning_rate": 2.1647509578544062e-05, "loss": 0.0426, "step": 460 }, { "epoch": 3.287719298245614, "grad_norm": 4035.5810546875, "learning_rate": 1.9731800766283527e-05, "loss": 0.0378, "step": 470 }, { "epoch": 3.3578947368421055, "grad_norm": 4500.57470703125, "learning_rate": 1.781609195402299e-05, "loss": 0.0424, "step": 480 }, { "epoch": 3.4280701754385965, "grad_norm": 4739.67431640625, "learning_rate": 1.5900383141762454e-05, "loss": 0.041, "step": 490 }, { "epoch": 3.4982456140350875, "grad_norm": 3640.994384765625, "learning_rate": 1.3984674329501916e-05, "loss": 0.0381, "step": 500 } ], "logging_steps": 10, "max_steps": 572, "num_input_tokens_seen": 0, "num_train_epochs": 4, "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": 3.4406372122423296e+17, "train_batch_size": 4, "trial_name": null, "trial_params": null }