| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993935718617344, | |
| "eval_steps": 500, | |
| "global_step": 412, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02425712553062462, | |
| "grad_norm": 86.94617462158203, | |
| "learning_rate": 1.1904761904761906e-06, | |
| "loss": 2.9554, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04851425106124924, | |
| "grad_norm": 29.724809646606445, | |
| "learning_rate": 2.380952380952381e-06, | |
| "loss": 1.5779, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07277137659187387, | |
| "grad_norm": 16.428190231323242, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 1.2023, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09702850212249849, | |
| "grad_norm": 17.30933380126953, | |
| "learning_rate": 4.761904761904762e-06, | |
| "loss": 1.1538, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1212856276531231, | |
| "grad_norm": 15.137809753417969, | |
| "learning_rate": 4.994234734765043e-06, | |
| "loss": 1.0789, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14554275318374774, | |
| "grad_norm": 11.950181007385254, | |
| "learning_rate": 4.9708589101037306e-06, | |
| "loss": 1.0103, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16979987871437235, | |
| "grad_norm": 14.55068302154541, | |
| "learning_rate": 4.92968049037552e-06, | |
| "loss": 1.0078, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19405700424499697, | |
| "grad_norm": 27.079729080200195, | |
| "learning_rate": 4.870996167038154e-06, | |
| "loss": 1.0301, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2183141297756216, | |
| "grad_norm": 16.41851043701172, | |
| "learning_rate": 4.7952287619860276e-06, | |
| "loss": 1.0042, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2425712553062462, | |
| "grad_norm": 14.759162902832031, | |
| "learning_rate": 4.702924181108745e-06, | |
| "loss": 0.9602, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2668283808368708, | |
| "grad_norm": 14.426393508911133, | |
| "learning_rate": 4.594747481026685e-06, | |
| "loss": 0.978, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2910855063674955, | |
| "grad_norm": 11.475569725036621, | |
| "learning_rate": 4.471478077342798e-06, | |
| "loss": 0.9809, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31534263189812006, | |
| "grad_norm": 14.514723777770996, | |
| "learning_rate": 4.334004128935342e-06, | |
| "loss": 0.981, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3395997574287447, | |
| "grad_norm": 11.994640350341797, | |
| "learning_rate": 4.183316138752799e-06, | |
| "loss": 0.9829, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3638568829593693, | |
| "grad_norm": 81.57245635986328, | |
| "learning_rate": 4.020499817217441e-06, | |
| "loss": 0.9799, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38811400848999394, | |
| "grad_norm": 13.99566650390625, | |
| "learning_rate": 3.84672825965686e-06, | |
| "loss": 0.9717, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 12.517782211303711, | |
| "learning_rate": 3.663253494125244e-06, | |
| "loss": 0.9327, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4366282595512432, | |
| "grad_norm": 13.505069732666016, | |
| "learning_rate": 3.4713974605125634e-06, | |
| "loss": 0.9839, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.46088538508186777, | |
| "grad_norm": 12.123452186584473, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.9508, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4851425106124924, | |
| "grad_norm": 29.056503295898438, | |
| "learning_rate": 3.0681213250482255e-06, | |
| "loss": 0.9075, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.509399636143117, | |
| "grad_norm": 11.140923500061035, | |
| "learning_rate": 2.8596068369936386e-06, | |
| "loss": 0.9405, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5336567616737417, | |
| "grad_norm": 14.713190078735352, | |
| "learning_rate": 2.648501373438142e-06, | |
| "loss": 0.8641, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5579138872043663, | |
| "grad_norm": 19.95207405090332, | |
| "learning_rate": 2.436325954084122e-06, | |
| "loss": 0.9529, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.582171012734991, | |
| "grad_norm": 11.159050941467285, | |
| "learning_rate": 2.2246093076900145e-06, | |
| "loss": 0.9201, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6064281382656155, | |
| "grad_norm": 12.661371231079102, | |
| "learning_rate": 2.014876857544562e-06, | |
| "loss": 0.9249, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6306852637962401, | |
| "grad_norm": 12.855792045593262, | |
| "learning_rate": 1.8086397307570724e-06, | |
| "loss": 0.9223, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6549423893268648, | |
| "grad_norm": 12.543617248535156, | |
| "learning_rate": 1.6073838705519618e-06, | |
| "loss": 0.9151, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6791995148574894, | |
| "grad_norm": 11.495418548583984, | |
| "learning_rate": 1.4125593300137767e-06, | |
| "loss": 0.8661, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7034566403881141, | |
| "grad_norm": 15.451556205749512, | |
| "learning_rate": 1.2255698244214863e-06, | |
| "loss": 0.946, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7277137659187386, | |
| "grad_norm": 14.111011505126953, | |
| "learning_rate": 1.0477626174477403e-06, | |
| "loss": 0.9041, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7519708914493632, | |
| "grad_norm": 9.91163444519043, | |
| "learning_rate": 8.804188140932251e-07, | |
| "loss": 0.8724, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7762280169799879, | |
| "grad_norm": 17.55638313293457, | |
| "learning_rate": 7.247441302957858e-07, | |
| "loss": 0.888, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8004851425106125, | |
| "grad_norm": 16.491750717163086, | |
| "learning_rate": 5.818602057194589e-07, | |
| "loss": 0.8579, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8247422680412371, | |
| "grad_norm": 10.457083702087402, | |
| "learning_rate": 4.527965223149958e-07, | |
| "loss": 0.8965, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8489993935718617, | |
| "grad_norm": 10.995795249938965, | |
| "learning_rate": 3.3848298687881143e-07, | |
| "loss": 0.8624, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8732565191024864, | |
| "grad_norm": 15.046560287475586, | |
| "learning_rate": 2.397432310532133e-07, | |
| "loss": 0.8749, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.897513644633111, | |
| "grad_norm": 12.04796314239502, | |
| "learning_rate": 1.5728867704154076e-07, | |
| "loss": 0.857, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9217707701637355, | |
| "grad_norm": 14.930426597595215, | |
| "learning_rate": 9.171341179489034e-08, | |
| "loss": 0.8997, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9460278956943602, | |
| "grad_norm": 16.0552978515625, | |
| "learning_rate": 4.348990660201669e-08, | |
| "loss": 0.8803, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9702850212249848, | |
| "grad_norm": 11.000052452087402, | |
| "learning_rate": 1.296561292287446e-08, | |
| "loss": 0.95, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9945421467556095, | |
| "grad_norm": 14.236842155456543, | |
| "learning_rate": 3.604589928837832e-10, | |
| "loss": 0.8863, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9993935718617344, | |
| "step": 412, | |
| "total_flos": 4.874908633965527e+17, | |
| "train_loss": 1.011520906270129, | |
| "train_runtime": 2109.7946, | |
| "train_samples_per_second": 25.008, | |
| "train_steps_per_second": 0.195 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 412, | |
| "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": 4.874908633965527e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |