| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 471, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06389776357827476, | |
| "grad_norm": 27.007149720149624, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 3.0251, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12779552715654952, | |
| "grad_norm": 7.200384353707933, | |
| "learning_rate": 3.958333333333333e-06, | |
| "loss": 2.2511, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19169329073482427, | |
| "grad_norm": 3.556500087950233, | |
| "learning_rate": 6.041666666666667e-06, | |
| "loss": 1.6305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25559105431309903, | |
| "grad_norm": 2.6746825713695674, | |
| "learning_rate": 8.125000000000001e-06, | |
| "loss": 1.2942, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3194888178913738, | |
| "grad_norm": 3.016385157178359, | |
| "learning_rate": 9.999862102299874e-06, | |
| "loss": 1.1516, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.38338658146964855, | |
| "grad_norm": 2.6763627648882995, | |
| "learning_rate": 9.983323579940351e-06, | |
| "loss": 1.0652, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4472843450479233, | |
| "grad_norm": 2.4049859456438094, | |
| "learning_rate": 9.939310009499348e-06, | |
| "loss": 0.9943, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5111821086261981, | |
| "grad_norm": 2.105383899953641, | |
| "learning_rate": 9.868064055324204e-06, | |
| "loss": 0.9601, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5750798722044729, | |
| "grad_norm": 2.1151352790518603, | |
| "learning_rate": 9.76997852474223e-06, | |
| "loss": 0.9231, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6389776357827476, | |
| "grad_norm": 1.792736838810565, | |
| "learning_rate": 9.645594202357438e-06, | |
| "loss": 0.9041, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7028753993610224, | |
| "grad_norm": 1.8385962515662637, | |
| "learning_rate": 9.495596868489588e-06, | |
| "loss": 0.8842, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7667731629392971, | |
| "grad_norm": 2.05797408169935, | |
| "learning_rate": 9.320813518194084e-06, | |
| "loss": 0.8689, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8306709265175719, | |
| "grad_norm": 2.0006315711572107, | |
| "learning_rate": 9.122207801708802e-06, | |
| "loss": 0.8651, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8945686900958466, | |
| "grad_norm": 2.0622583744546685, | |
| "learning_rate": 8.900874711466436e-06, | |
| "loss": 0.8368, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9584664536741214, | |
| "grad_norm": 1.9281533048022628, | |
| "learning_rate": 8.658034544965003e-06, | |
| "loss": 0.8362, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0191693290734825, | |
| "grad_norm": 1.7856911939628375, | |
| "learning_rate": 8.395026176781627e-06, | |
| "loss": 0.8083, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0830670926517572, | |
| "grad_norm": 1.857546453101415, | |
| "learning_rate": 8.113299676823614e-06, | |
| "loss": 0.7305, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1469648562300319, | |
| "grad_norm": 1.870887786495633, | |
| "learning_rate": 7.814408315515419e-06, | |
| "loss": 0.7347, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2108626198083068, | |
| "grad_norm": 1.936193043129797, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.7142, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.2747603833865815, | |
| "grad_norm": 2.083355561746048, | |
| "learning_rate": 7.1718081885702905e-06, | |
| "loss": 0.7132, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.3386581469648562, | |
| "grad_norm": 2.2188701115912477, | |
| "learning_rate": 6.831642333423068e-06, | |
| "loss": 0.7146, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4025559105431311, | |
| "grad_norm": 1.7246379127732157, | |
| "learning_rate": 6.481377904428171e-06, | |
| "loss": 0.6986, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.4664536741214058, | |
| "grad_norm": 1.7746101845242512, | |
| "learning_rate": 6.122946048915991e-06, | |
| "loss": 0.692, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.5303514376996805, | |
| "grad_norm": 1.9854646827619695, | |
| "learning_rate": 5.75832294449293e-06, | |
| "loss": 0.6934, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.5942492012779552, | |
| "grad_norm": 2.804872064894909, | |
| "learning_rate": 5.389518903587016e-06, | |
| "loss": 0.6904, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.65814696485623, | |
| "grad_norm": 2.1688342723582665, | |
| "learning_rate": 5.0185672897946515e-06, | |
| "loss": 0.6717, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.7220447284345048, | |
| "grad_norm": 1.8837334998414557, | |
| "learning_rate": 4.647513307137076e-06, | |
| "loss": 0.6835, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.7859424920127795, | |
| "grad_norm": 1.7206260961087232, | |
| "learning_rate": 4.278402724035868e-06, | |
| "loss": 0.6692, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.8498402555910545, | |
| "grad_norm": 1.7927077279083763, | |
| "learning_rate": 3.913270594176665e-06, | |
| "loss": 0.6597, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.9137380191693292, | |
| "grad_norm": 1.8582153739647842, | |
| "learning_rate": 3.5541300364475067e-06, | |
| "loss": 0.6467, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.9776357827476039, | |
| "grad_norm": 1.9389771348545655, | |
| "learning_rate": 3.202961135812437e-06, | |
| "loss": 0.6351, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.038338658146965, | |
| "grad_norm": 2.186799488826696, | |
| "learning_rate": 2.861700026314308e-06, | |
| "loss": 0.5844, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.1022364217252396, | |
| "grad_norm": 1.862856927563484, | |
| "learning_rate": 2.5322282163965096e-06, | |
| "loss": 0.5498, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.1661341853035143, | |
| "grad_norm": 2.076202990686732, | |
| "learning_rate": 2.216362215397393e-06, | |
| "loss": 0.5414, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.230031948881789, | |
| "grad_norm": 1.9052335758846242, | |
| "learning_rate": 1.91584351841065e-06, | |
| "loss": 0.531, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.2939297124600637, | |
| "grad_norm": 2.0645734722050144, | |
| "learning_rate": 1.6323290047291196e-06, | |
| "loss": 0.5197, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.357827476038339, | |
| "grad_norm": 2.026798582289315, | |
| "learning_rate": 1.367381802809185e-06, | |
| "loss": 0.5145, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.4217252396166136, | |
| "grad_norm": 1.9047823063501508, | |
| "learning_rate": 1.1224626721209141e-06, | |
| "loss": 0.52, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.4856230031948883, | |
| "grad_norm": 1.9193918008729423, | |
| "learning_rate": 8.989219493991791e-07, | |
| "loss": 0.5122, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.549520766773163, | |
| "grad_norm": 2.0562904526376458, | |
| "learning_rate": 6.979921036993042e-07, | |
| "loss": 0.5144, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.6134185303514377, | |
| "grad_norm": 2.1108260659301337, | |
| "learning_rate": 5.207809413041914e-07, | |
| "loss": 0.5074, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.6773162939297124, | |
| "grad_norm": 2.0723767617401934, | |
| "learning_rate": 3.6826549794698074e-07, | |
| "loss": 0.506, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.741214057507987, | |
| "grad_norm": 1.909988078795231, | |
| "learning_rate": 2.4128665202382327e-07, | |
| "loss": 0.5118, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.8051118210862622, | |
| "grad_norm": 1.846789019250583, | |
| "learning_rate": 1.4054448849631087e-07, | |
| "loss": 0.506, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.8690095846645365, | |
| "grad_norm": 1.9548999747777782, | |
| "learning_rate": 6.659443904419638e-08, | |
| "loss": 0.5087, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.9329073482428116, | |
| "grad_norm": 2.0005201002401614, | |
| "learning_rate": 1.984421974927375e-08, | |
| "loss": 0.4988, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.9968051118210863, | |
| "grad_norm": 2.120862010811792, | |
| "learning_rate": 5.515831941993455e-10, | |
| "loss": 0.5143, | |
| "step": 470 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 471, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 36562564546560.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |