{ "model_dir": "models/prompt_tuning/llama-30b-code_low_quality", "distribution_id": "code", "timestamp": "2023-10-13 13:28:41", "eval_loss": 2.361328125, "eval_score": -0.2427978515625, "eval_brier_score": 0.24279397868201957, "eval_average_probability": 0.6225336566766103, "eval_accuracy": 0.6893333333333334, "eval_probabilities": [ 0.0, 0.0, 0.0, 0.658203125, 0.9794921875, 0.6298828125, 0.5, 0.78271484375, 0.5078125, 0.7490234375, 0.84814453125, 0.5546875, 0.73095703125, 0.92431640625, 0.62255859375, 0.546875, 0.96044921875, 0.966796875, 0.7607421875, 0.90478515625, 0.46875, 0.05419921875, 0.138427734375, 0.1422119140625, 7.510185241699219e-06, 6.616115570068359e-06, 1.6987323760986328e-05, 0.22265625, 0.5849609375, 0.978515625, 0.43017578125, 0.9794921875, 0.70556640625, 0.0, 0.0, 0.0, 0.6826171875, 0.658203125, 0.57373046875, 0.99951171875, 0.99951171875, 0.99560546875, 0.78271484375, 0.85986328125, 0.73095703125, 0.94189453125, 1.0, 0.9970703125, 0.5390625, 0.822265625, 0.99853515625, 1.0, 1.0, 0.998046875, 0.76611328125, 0.71875, 0.615234375, 0.72509765625, 0.931640625, 0.63330078125, 0.08038330078125, 0.06463623046875, 0.06561279296875, 0.294189453125, 0.49609375, 0.43408203125, 0.94482421875, 0.5849609375, 0.363037109375, 0.79833984375, 0.53125, 0.71240234375, 0.1143798828125, 0.1688232421875, 0.294189453125, 1.0, 0.978515625, 1.0, 0.84375, 0.2337646484375, 0.48828125, 0.85205078125, 0.484375, 0.57763671875, 0.84375, 0.4609375, 0.99609375, 0.97705078125, 0.9287109375, 0.8896484375, 0.1441650390625, 0.546875, 0.7490234375, 0.26904296875, 0.281494140625, 0.453369140625, 0.0164031982421875, 0.004608154296875, 0.0226287841796875, 0.4765625, 0.70556640625, 0.060089111328125, 0.89892578125, 0.99951171875, 0.9755859375, 0.84375, 0.2337646484375, 0.64404296875, 0.12249755859375, 0.2017822265625, 0.140380859375, 1.0, 1.0, 0.98681640625, 0.2281494140625, 0.04742431640625, 0.1259765625, 0.9990234375, 0.97509765625, 0.9755859375, 0.64404296875, 0.69287109375, 0.9853515625, 0.97607421875, 0.92529296875, 0.011688232421875, 0.0, 0.0, 0.0, 0.94189453125, 0.9970703125, 0.70556640625, 0.84375, 0.83544921875, 0.84814453125, 0.76611328125, 0.7373046875, 0.445556640625, 0.07586669921875, 0.53125, 0.5234375, 0.0, 0.0, 0.0, 0.64404296875, 0.051849365234375, 0.08038330078125, 0.57763671875, 0.6513671875, 0.86328125, 0.77197265625, 0.95751953125, 0.8974609375, 0.2147216796875, 0.1688232421875, 0.11279296875, 0.0, 0.0, 0.0, 0.998046875, 0.32763671875, 0.66552734375, 0.3486328125, 0.2451171875, 0.294189453125, 1.0, 0.99267578125, 0.998046875, 0.6513671875, 0.53125, 0.67919921875, 0.57763671875, 0.77734375, 0.32080078125, 0.5849609375, 0.5, 0.85986328125, 0.79833984375, 0.9814453125, 1.0, 0.43017578125, 0.422607421875, 0.53125, 0.99755859375, 0.984375, 0.93896484375, 0.68603515625, 0.7373046875, 0.355712890625, 0.0259552001953125, 0.09808349609375, 0.37744140625, 0.7548828125, 0.7548828125, 0.8173828125, 0.9609375, 0.9423828125, 0.9970703125, 0.7373046875, 0.56982421875, 0.79833984375, 0.007694244384765625, 0.000720977783203125, 0.003765106201171875, 0.5078125, 0.5927734375, 0.8671875, 0.363037109375, 0.445556640625, 0.5390625, 0.5234375, 0.59619140625, 0.51171875, 0.5849609375, 0.51171875, 0.515625, 0.53125, 0.97705078125, 0.99755859375, 0.303955078125, 0.57763671875, 0.611328125, 0.56982421875, 0.93798828125, 0.87060546875, 0.363037109375, 0.2783203125, 0.546875, 0.607421875, 0.64404296875, 0.9931640625, 0.880859375, 0.9775390625, 0.99951171875, 0.87744140625, 0.91943359375, 0.5234375, 0.69287109375, 0.62255859375, 0.56201171875, 0.0, 0.0, 0.0, 0.97265625, 0.62255859375, 0.76611328125, 0.1441650390625, 0.418701171875, 0.96044921875, 0.98974609375, 0.19677734375, 0.99169921875, 0.71875, 0.87744140625, 0.453369140625, 0.2393798828125, 0.81982421875, 0.99853515625, 0.453369140625, 0.8916015625, 0.453369140625, 0.99755859375, 0.81982421875, 0.8291015625, 0.951171875, 0.5, 0.57763671875, 0.0, 0.0, 0.0, 0.96044921875, 0.998046875, 0.982421875, 0.9306640625, 0.7548828125, 0.7607421875, 0.984375, 0.99951171875, 0.77734375, 0.880859375, 0.7373046875, 0.5234375, 0.89013671875, 0.78271484375, 0.7490234375, 0.84375, 0.68603515625, 0.46875, 0.65478515625, 0.73388671875, 0.8916015625, 0.5849609375, 0.6513671875, 0.5078125, 0.7373046875, 0.307373046875, 0.96875, 0.54296875, 0.10089111328125, 0.810546875, 0.962890625, 0.9931640625, 0.90966796875, 0.84814453125, 0.91748046875, 0.9150390625, 0.6298828125, 0.57763671875, 0.97265625, 0.9638671875, 0.87060546875, 0.85595703125, 0.414794921875, 0.275146484375, 0.392333984375, 0.921875, 0.91259765625, 0.92822265625, 0.7431640625, 0.740234375, 0.9609375, 0.60400390625, 0.5390625, 0.50390625, 0.7744140625, 0.994140625, 0.041473388671875, 0.60009765625, 0.56201171875, 0.32080078125, 0.56201171875, 0.56201171875, 0.546875, 0.62255859375, 0.67236328125, 0.56201171875, 0.2509765625, 0.10821533203125, 0.175537109375, 0.99853515625, 0.99951171875, 0.99951171875, 0.7373046875, 0.7607421875, 0.385009765625, 0.95263671875, 0.80322265625, 0.95751953125, 0.484375, 0.4921875, 0.484375, 0.0, 0.0, 0.0, 1.0, 0.341552734375, 0.63720703125, 0.69287109375, 0.97265625, 0.615234375, 0.5390625, 0.437744140625, 0.484375, 0.60009765625, 0.57763671875, 0.8671875, 0.7431640625, 1.0, 0.98974609375, 0.62255859375, 0.658203125, 0.5078125, 0.484375, 0.5927734375, 0.95458984375, 0.355712890625, 0.32763671875, 0.69921875, 0.60009765625, 0.546875, 0.2509765625, 0.01132965087890625, 0.83984375, 0.94677734375, 0.87744140625, 0.88720703125, 0.943359375, 0.1480712890625, 0.17333984375, 0.50390625, 0.0020198822021484375, 0.0966796875, 0.9501953125, 0.99951171875, 0.72509765625, 0.392333984375, 0.51953125, 0.441650390625, 0.52734375, 0.607421875, 0.43017578125, 0.437744140625, 0.546875, 0.4609375, 0.418701171875, 0.0, 0.0, 0.0, 0.5234375, 0.26904296875, 0.546875, 0.453369140625, 0.7548828125, 0.79833984375, 0.2451171875, 0.1519775390625, 0.5927734375, 0.67236328125, 0.73095703125, 0.67236328125, 0.91748046875, 0.7490234375, 0.80322265625, 0.422607421875, 0.21728515625, 0.5234375, 0.5, 0.5, 0.392333984375, 0.67236328125, 0.86328125, 0.9794921875, 1.0, 1.0, 1.0, 0.9677734375, 0.9482421875, 0.98828125, 0.9697265625, 0.91748046875, 0.9951171875, 0.984375, 0.91259765625, 0.69287109375, 0.83544921875, 0.1561279296875, 0.88427734375, 0.80810546875, 0.60009765625, 0.355712890625, 0.30078125, 0.99560546875, 0.978515625, 0.453369140625, 0.53125, 0.92431640625, 0.69287109375, 0.445556640625, 0.6513671875, 0.8740234375, 0.9775390625, 0.363037109375, 0.763671875, 0.962890625, 0.98681640625, 0.0, 0.0, 0.0, 0.8671875, 0.91259765625, 0.92822265625, 0.88720703125, 0.17333984375, 0.8740234375, 0.955078125, 0.7880859375, 0.58154296875, 0.46484375, 0.7490234375, 0.392333984375, 0.998046875, 0.98876953125, 0.99853515625, 7.033348083496094e-05, 0.81298828125, 0.71875, 0.91748046875, 0.80810546875, 0.822265625, 0.9970703125, 0.607421875, 0.99609375, 1.0, 0.7880859375, 0.8173828125, 0.95263671875, 0.69287109375, 0.99755859375, 0.7373046875, 0.9833984375, 0.79296875, 0.740234375, 0.4609375, 0.4072265625, 0.615234375, 0.39990234375, 0.56982421875, 0.52734375, 0.3701171875, 0.2783203125, 0.0, 0.0, 0.0, 0.89892578125, 0.9150390625, 0.9326171875, 0.1365966796875, 0.07366943359375, 0.12939453125, 0.93994140625, 0.294189453125, 0.82666015625, 0.81298828125, 0.63330078125, 0.7958984375, 0.91943359375, 0.9306640625, 0.9365234375, 0.64404296875, 0.7490234375, 0.6513671875, 0.74609375, 0.95263671875, 0.66552734375, 0.12249755859375, 0.275146484375, 0.56201171875, 0.88427734375, 0.94482421875, 0.81298828125, 0.99951171875, 0.97705078125, 0.994140625, 0.97314453125, 0.9814453125, 0.99951171875, 0.80322265625, 0.79296875, 0.880859375, 0.9853515625, 0.21728515625, 0.307373046875, 0.9580078125, 0.262939453125, 0.33447265625, 0.0, 0.0, 0.0, 0.7490234375, 0.4765625, 0.46875, 0.105224609375, 0.45703125, 0.338134765625, 0.96142578125, 0.9677734375, 0.7607421875, 0.3701171875, 0.76611328125, 0.900390625, 1.0, 0.73095703125, 0.7578125, 0.31396484375, 0.931640625, 0.76904296875, 1.0, 0.99560546875, 0.99462890625, 0.9921875, 1.0, 1.0, 0.5, 0.385009765625, 0.5, 0.0, 0.0, 0.0, 0.403564453125, 0.74609375, 0.92724609375, 0.515625, 0.4921875, 0.5, 0.955078125, 0.99658203125, 0.76611328125, 0.4072265625, 0.73095703125, 0.5078125, 0.607421875, 0.82666015625, 0.77734375, 0.0, 0.0, 0.0, 0.4765625, 0.5, 0.39990234375, 0.931640625, 1.0, 0.63720703125, 1.0, 0.2451171875, 0.0330810546875, 0.10089111328125, 0.0169219970703125, 0.16455078125, 0.80810546875, 0.7880859375, 0.37744140625, 0.9755859375, 0.80322265625, 0.970703125, 0.69287109375, 0.62255859375, 0.89306640625, 0.56201171875, 0.484375, 0.5, 0.99072265625, 0.1895751953125, 0.25390625, 0.33447265625, 0.998046875, 0.82666015625, 0.97265625, 0.06658935546875, 0.98388671875, 0.5, 0.57763671875, 0.56982421875, 0.7373046875, 0.9931640625, 0.31396484375, 0.0169219970703125, 0.64404296875, 0.80810546875, 0.943359375, 0.7880859375, 0.5, 0.96875, 0.607421875, 0.880859375, 0.88720703125, 0.363037109375, 0.91943359375, 0.994140625, 0.822265625, 0.96142578125, 0.9794921875, 0.998046875, 0.97900390625, 0.71875, 0.92822265625, 1.0, 0.445556640625, 0.62255859375, 0.99951171875, 0.88720703125, 0.921875, 0.281494140625, 0.0021820068359375, 4.988908767700195e-05, 0.003376007080078125, 0.8056640625, 0.88427734375, 0.91748046875, 0.7578125, 0.9990234375, 0.9326171875, 0.85595703125, 0.27197265625, 0.4072265625, 0.73095703125, 0.355712890625, 0.10968017578125, 0.99951171875, 0.9794921875, 0.98486328125, 0.12420654296875, 0.1461181640625, 0.6298828125, 0.182373046875, 0.70263671875, 0.92626953125, 0.5234375, 0.615234375, 0.84375, 0.385009765625, 0.2451171875, 0.363037109375, 0.46875, 0.57763671875, 0.546875, 0.32080078125, 0.47265625, 0.57373046875, 0.99951171875, 0.99853515625, 0.99609375, 0.53515625, 0.72509765625, 0.9306640625, 0.99365234375, 0.8671875, 0.84375, 0.62255859375, 0.5927734375, 0.5849609375, 0.6298828125, 0.8173828125, 0.77734375, 0.615234375, 0.4609375, 0.83740234375, 0.6298828125, 0.99755859375, 0.29736328125, 0.67919921875, 0.66552734375, 0.484375, 0.32763671875, 1.0, 0.9990234375, 0.37744140625, 0.43017578125, 0.1688232421875, 0.83984375, 0.51953125, 0.92919921875, 0.810546875, 0.8056640625, 0.56591796875, 0.99853515625, 0.99267578125, 0.96484375, 0.63720703125, 0.437744140625, 0.9677734375 ], "eval_runtime": 92.8235, "eval_samples_per_second": 8.08, "eval_steps_per_second": 0.259, "eval_rms_calibration_error": 0.3013630901326771 }