| { | |
| "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": 34.803749574601504, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 3.2079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12779552715654952, | |
| "grad_norm": 8.393596619540387, | |
| "learning_rate": 3.958333333333333e-06, | |
| "loss": 2.3077, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19169329073482427, | |
| "grad_norm": 4.54582398918815, | |
| "learning_rate": 6.041666666666667e-06, | |
| "loss": 1.6795, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25559105431309903, | |
| "grad_norm": 2.88137111898239, | |
| "learning_rate": 8.125000000000001e-06, | |
| "loss": 1.3798, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3194888178913738, | |
| "grad_norm": 3.470416724559835, | |
| "learning_rate": 9.999862102299874e-06, | |
| "loss": 1.2363, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.38338658146964855, | |
| "grad_norm": 3.111739768988857, | |
| "learning_rate": 9.983323579940351e-06, | |
| "loss": 1.1359, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4472843450479233, | |
| "grad_norm": 2.63691114437442, | |
| "learning_rate": 9.939310009499348e-06, | |
| "loss": 1.0504, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5111821086261981, | |
| "grad_norm": 2.3175377091892346, | |
| "learning_rate": 9.868064055324204e-06, | |
| "loss": 1.0116, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5750798722044729, | |
| "grad_norm": 2.30928876775904, | |
| "learning_rate": 9.76997852474223e-06, | |
| "loss": 0.9679, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6389776357827476, | |
| "grad_norm": 2.2162135977370196, | |
| "learning_rate": 9.645594202357438e-06, | |
| "loss": 0.944, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7028753993610224, | |
| "grad_norm": 1.9916201881672246, | |
| "learning_rate": 9.495596868489588e-06, | |
| "loss": 0.921, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7667731629392971, | |
| "grad_norm": 2.2617620915408914, | |
| "learning_rate": 9.320813518194084e-06, | |
| "loss": 0.9022, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8306709265175719, | |
| "grad_norm": 2.4967363173333292, | |
| "learning_rate": 9.122207801708802e-06, | |
| "loss": 0.895, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8945686900958466, | |
| "grad_norm": 2.2712304513946906, | |
| "learning_rate": 8.900874711466436e-06, | |
| "loss": 0.864, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9584664536741214, | |
| "grad_norm": 1.9051776400686733, | |
| "learning_rate": 8.658034544965003e-06, | |
| "loss": 0.8608, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0191693290734825, | |
| "grad_norm": 1.9166530255225462, | |
| "learning_rate": 8.395026176781627e-06, | |
| "loss": 0.8301, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0830670926517572, | |
| "grad_norm": 2.064754006824319, | |
| "learning_rate": 8.113299676823614e-06, | |
| "loss": 0.7483, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1469648562300319, | |
| "grad_norm": 2.082411427574368, | |
| "learning_rate": 7.814408315515419e-06, | |
| "loss": 0.7494, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2108626198083068, | |
| "grad_norm": 2.2742401088702873, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.7281, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.2747603833865815, | |
| "grad_norm": 2.177821331073625, | |
| "learning_rate": 7.1718081885702905e-06, | |
| "loss": 0.7254, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.3386581469648562, | |
| "grad_norm": 2.270677294458059, | |
| "learning_rate": 6.831642333423068e-06, | |
| "loss": 0.7254, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4025559105431311, | |
| "grad_norm": 1.876950473520462, | |
| "learning_rate": 6.481377904428171e-06, | |
| "loss": 0.7098, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.4664536741214058, | |
| "grad_norm": 1.9386787003754147, | |
| "learning_rate": 6.122946048915991e-06, | |
| "loss": 0.7025, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.5303514376996805, | |
| "grad_norm": 2.098949126790221, | |
| "learning_rate": 5.75832294449293e-06, | |
| "loss": 0.7031, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.5942492012779552, | |
| "grad_norm": 1.9482130248993954, | |
| "learning_rate": 5.389518903587016e-06, | |
| "loss": 0.699, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.65814696485623, | |
| "grad_norm": 2.2416291315780845, | |
| "learning_rate": 5.0185672897946515e-06, | |
| "loss": 0.679, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.7220447284345048, | |
| "grad_norm": 2.0218332843155133, | |
| "learning_rate": 4.647513307137076e-06, | |
| "loss": 0.6905, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.7859424920127795, | |
| "grad_norm": 1.8220659272587023, | |
| "learning_rate": 4.278402724035868e-06, | |
| "loss": 0.6763, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.8498402555910545, | |
| "grad_norm": 1.9040499495108065, | |
| "learning_rate": 3.913270594176665e-06, | |
| "loss": 0.6666, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.9137380191693292, | |
| "grad_norm": 1.9584612801162502, | |
| "learning_rate": 3.5541300364475067e-06, | |
| "loss": 0.652, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.9776357827476039, | |
| "grad_norm": 2.0067481902852218, | |
| "learning_rate": 3.202961135812437e-06, | |
| "loss": 0.6407, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.038338658146965, | |
| "grad_norm": 2.2045322624750185, | |
| "learning_rate": 2.861700026314308e-06, | |
| "loss": 0.5873, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.1022364217252396, | |
| "grad_norm": 1.9777465745041298, | |
| "learning_rate": 2.5322282163965096e-06, | |
| "loss": 0.5501, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.1661341853035143, | |
| "grad_norm": 2.188183911470147, | |
| "learning_rate": 2.216362215397393e-06, | |
| "loss": 0.5408, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.230031948881789, | |
| "grad_norm": 1.994203838618425, | |
| "learning_rate": 1.91584351841065e-06, | |
| "loss": 0.5307, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.2939297124600637, | |
| "grad_norm": 2.1333509330982396, | |
| "learning_rate": 1.6323290047291196e-06, | |
| "loss": 0.5185, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.357827476038339, | |
| "grad_norm": 2.0993869032798114, | |
| "learning_rate": 1.367381802809185e-06, | |
| "loss": 0.5134, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.4217252396166136, | |
| "grad_norm": 1.954631998509726, | |
| "learning_rate": 1.1224626721209141e-06, | |
| "loss": 0.5196, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.4856230031948883, | |
| "grad_norm": 1.9740302894409982, | |
| "learning_rate": 8.989219493991791e-07, | |
| "loss": 0.5114, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.549520766773163, | |
| "grad_norm": 2.089443520663485, | |
| "learning_rate": 6.979921036993042e-07, | |
| "loss": 0.5143, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.6134185303514377, | |
| "grad_norm": 2.1355946780064587, | |
| "learning_rate": 5.207809413041914e-07, | |
| "loss": 0.506, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.6773162939297124, | |
| "grad_norm": 2.1209465409863024, | |
| "learning_rate": 3.6826549794698074e-07, | |
| "loss": 0.5048, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.741214057507987, | |
| "grad_norm": 1.9717542566555746, | |
| "learning_rate": 2.4128665202382327e-07, | |
| "loss": 0.5104, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.8051118210862622, | |
| "grad_norm": 1.9192059742029721, | |
| "learning_rate": 1.4054448849631087e-07, | |
| "loss": 0.5039, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.8690095846645365, | |
| "grad_norm": 2.0469451263493657, | |
| "learning_rate": 6.659443904419638e-08, | |
| "loss": 0.5093, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.9329073482428116, | |
| "grad_norm": 2.0780858253955454, | |
| "learning_rate": 1.984421974927375e-08, | |
| "loss": 0.4971, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.9968051118210863, | |
| "grad_norm": 2.2435204264420503, | |
| "learning_rate": 5.515831941993455e-10, | |
| "loss": 0.5139, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 471, | |
| "total_flos": 36429583613952.0, | |
| "train_loss": 0.8295695250201377, | |
| "train_runtime": 3334.6516, | |
| "train_samples_per_second": 9.004, | |
| "train_steps_per_second": 0.141 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 471, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 36429583613952.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |