{ "model_dir": "models/prompt_tuning/llama-13b-code", "distribution_id": "counterfactual_python", "timestamp": "2023-10-23 23:36:17", "eval_loss": 0.67822265625, "eval_score": -0.2177734375, "eval_brier_score": 0.21778765376124648, "eval_average_probability": 0.6279779103597005, "eval_accuracy": 0.6906666666666667, "eval_probabilities": [ 0.388671875, 0.437744140625, 0.5078125, 0.60400390625, 0.57763671875, 0.43408203125, 1.0, 0.998046875, 0.99853515625, 0.51171875, 0.65478515625, 0.61865234375, 0.87451171875, 0.2039794921875, 0.405029296875, 0.63525390625, 0.1993408203125, 0.1312255859375, 0.0247955322265625, 0.0169219970703125, 0.0156707763671875, 0.037322998046875, 0.015899658203125, 0.0316162109375, 0.0869140625, 0.09271240234375, 0.11517333984375, 0.89306640625, 0.7958984375, 0.99658203125, 0.0203399658203125, 0.01666259765625, 0.439697265625, 0.75439453125, 0.9951171875, 0.356689453125, 0.83740234375, 0.85009765625, 0.8173828125, 0.5927734375, 0.363037109375, 0.26904296875, 0.921875, 0.83740234375, 0.83984375, 0.537109375, 0.443603515625, 0.548828125, 0.58154296875, 0.46484375, 0.546875, 0.341552734375, 0.2069091796875, 0.1943359375, 0.352294921875, 0.4072265625, 0.388671875, 0.3701171875, 0.55810546875, 0.51953125, 0.77197265625, 0.5234375, 0.437744140625, 0.71240234375, 0.6943359375, 0.172119140625, 0.509765625, 0.77587890625, 0.66015625, 0.5927734375, 0.4609375, 0.59619140625, 0.83349609375, 0.751953125, 0.63330078125, 0.47265625, 0.80078125, 0.58154296875, 0.9951171875, 0.359375, 0.56591796875, 0.6494140625, 0.58154296875, 0.7431640625, 0.87744140625, 0.0078125, 0.6513671875, 1.0, 1.0, 1.0, 0.74462890625, 0.97216796875, 0.94091796875, 0.482421875, 0.552734375, 0.61865234375, 0.607421875, 0.515625, 0.58154296875, 0.708984375, 0.4765625, 0.7216796875, 0.80322265625, 0.85400390625, 0.69091796875, 0.99072265625, 0.984375, 0.958984375, 1.0, 1.0, 1.0, 0.90478515625, 0.98095703125, 0.89501953125, 0.94873046875, 0.87060546875, 0.99951171875, 0.9150390625, 0.9677734375, 0.90966796875, 0.96484375, 0.7880859375, 0.71875, 0.97265625, 0.98291015625, 0.73095703125, 0.80810546875, 0.79296875, 0.517578125, 0.515625, 0.484375, 0.54296875, 0.1470947265625, 0.78662109375, 0.035400390625, 0.60009765625, 0.5888671875, 0.64794921875, 0.5234375, 0.103759765625, 0.71240234375, 0.48046875, 0.7578125, 0.6826171875, 0.56591796875, 0.46875, 0.8291015625, 0.59619140625, 0.83544921875, 0.69287109375, 0.673828125, 0.71875, 0.943359375, 0.8857421875, 0.42626953125, 0.97509765625, 0.6533203125, 0.79296875, 0.81982421875, 0.767578125, 0.361083984375, 0.708984375, 0.2281494140625, 0.445556640625, 0.441650390625, 0.611328125, 0.381103515625, 0.58154296875, 0.77734375, 0.2509765625, 0.31396484375, 0.77587890625, 0.89892578125, 0.89404296875, 0.57470703125, 0.5341796875, 0.671875, 0.82666015625, 0.88232421875, 0.46484375, 0.662109375, 0.53515625, 0.52734375, 0.82568359375, 0.63525390625, 0.7138671875, 0.59814453125, 0.638671875, 0.5947265625, 0.46875, 0.56982421875, 0.66552734375, 0.23095703125, 0.2239990234375, 0.2379150390625, 0.12249755859375, 0.003795623779296875, 0.2120361328125, 0.178955078125, 0.62255859375, 0.69921875, 0.04486083984375, 0.303955078125, 0.07501220703125, 0.98193359375, 0.9384765625, 0.64013671875, 0.06658935546875, 0.50390625, 0.2783203125, 0.48046875, 0.51953125, 0.51171875, 0.67724609375, 0.56787109375, 0.62060546875, 0.99951171875, 0.6494140625, 0.57568359375, 0.73291015625, 0.67236328125, 0.6337890625, 0.6826171875, 0.84716796875, 0.8056640625, 0.71875, 0.19677734375, 0.740234375, 0.115966796875, 0.0792236328125, 0.0966796875, 0.1259765625, 0.08880615234375, 1.0, 0.994140625, 0.9990234375, 0.9951171875, 0.60009765625, 0.6298828125, 0.5849609375, 0.93994140625, 0.94189453125, 0.437744140625, 0.4072265625, 0.97216796875, 0.896484375, 0.91650390625, 0.287841796875, 0.96142578125, 0.81298828125, 0.73095703125, 0.57373046875, 0.74609375, 0.338134765625, 0.49609375, 0.82763671875, 0.458984375, 0.388671875, 0.70263671875, 0.505859375, 0.5927734375, 0.7578125, 0.85595703125, 0.9951171875, 0.5078125, 0.53125, 0.546875, 0.77587890625, 0.94189453125, 0.95166015625, 0.642578125, 0.74169921875, 0.611328125, 0.437744140625, 0.53125, 0.392333984375, 0.5234375, 0.5078125, 0.53125, 0.50390625, 0.541015625, 0.38671875, 0.3701171875, 0.2509765625, 0.19189453125, 0.85107421875, 0.82080078125, 0.2783203125, 0.91650390625, 0.79296875, 0.9794921875, 0.9990234375, 0.98388671875, 0.9970703125, 0.9921875, 0.99169921875, 0.9990234375, 0.99072265625, 0.99169921875, 0.99560546875, 1.0, 0.98779296875, 0.99755859375, 0.8291015625, 0.529296875, 0.3701171875, 0.43017578125, 0.39599609375, 0.4609375, 0.30908203125, 0.403564453125, 0.525390625, 0.39990234375, 0.609375, 0.78662109375, 0.2337646484375, 0.264404296875, 0.59814453125, 0.1561279296875, 0.31396484375, 0.46875, 0.548828125, 0.57958984375, 0.66015625, 0.25390625, 0.294189453125, 0.32421875, 0.6259765625, 0.62255859375, 0.615234375, 0.59619140625, 0.46875, 0.57763671875, 0.99560546875, 0.99951171875, 0.99755859375, 0.04742431640625, 0.48828125, 0.71875, 0.86865234375, 0.99951171875, 0.55810546875, 0.445556640625, 0.54296875, 0.437744140625, 0.521484375, 0.67236328125, 0.5390625, 0.275146484375, 0.7431640625, 0.763671875, 0.63330078125, 0.55810546875, 0.689453125, 0.422607421875, 0.5078125, 0.385009765625, 0.9365234375, 0.5546875, 0.53125, 0.4091796875, 0.638671875, 0.61328125, 0.99951171875, 0.37744140625, 0.63720703125, 0.70556640625, 0.9560546875, 0.67236328125, 0.96435546875, 0.9365234375, 0.9892578125, 0.9345703125, 0.92578125, 0.92578125, 0.2578125, 0.355224609375, 0.273681640625, 0.71533203125, 0.70263671875, 0.8291015625, 0.7705078125, 0.943359375, 0.89501953125, 0.99609375, 1.0, 0.99267578125, 0.10089111328125, 0.10968017578125, 0.529296875, 0.92431640625, 0.4765625, 0.84375, 0.4921875, 0.50390625, 0.46484375, 0.5234375, 0.51953125, 0.5078125, 0.97509765625, 0.953125, 0.394287109375, 0.004180908203125, 0.0230712890625, 0.0141143798828125, 0.96630859375, 0.35498046875, 0.9609375, 0.09332275390625, 0.043701171875, 0.04779052734375, 0.1357421875, 0.98095703125, 0.64599609375, 0.6943359375, 0.0154266357421875, 0.9541015625, 0.60009765625, 0.658203125, 0.37744140625, 0.806640625, 0.70068359375, 0.61865234375, 1.0, 1.0, 0.99951171875, 0.546875, 0.97802734375, 0.77880859375, 0.62060546875, 0.6826171875, 0.541015625, 0.9052734375, 0.96337890625, 0.83544921875, 0.3212890625, 0.65576171875, 0.46826171875, 0.5888671875, 0.740234375, 0.49609375, 0.363037109375, 0.32421875, 0.708984375, 0.541015625, 0.97216796875, 0.5234375, 0.60400390625, 0.9853515625, 0.9619140625, 0.94189453125, 0.93212890625, 0.80908203125, 0.9482421875, 0.85986328125, 0.921875, 0.96728515625, 0.962890625, 0.9462890625, 0.9462890625, 0.139404296875, 0.390380859375, 0.97900390625, 0.99951171875, 0.94873046875, 0.97998046875, 0.978515625, 0.99560546875, 0.98876953125, 0.99609375, 0.943359375, 0.8310546875, 0.83544921875, 0.90576171875, 0.67041015625, 0.96142578125, 0.8427734375, 0.99267578125, 0.5888671875, 0.9970703125, 0.6875, 0.66015625, 0.87646484375, 0.42822265625, 0.5, 0.2783203125, 0.2288818359375, 0.642578125, 0.96142578125, 0.94873046875, 0.95947265625, 0.35400390625, 0.338134765625, 0.352294921875, 0.2451171875, 0.138427734375, 0.1688232421875, 0.0792236328125, 0.52734375, 0.2108154296875, 0.20947265625, 0.51953125, 0.55810546875, 0.5947265625, 0.2120361328125, 0.56396484375, 0.515625, 0.64404296875, 0.67919921875, 0.607421875, 0.4775390625, 0.474609375, 0.46875, 0.385009765625, 0.77734375, 0.51953125, 0.76904296875, 0.6513671875, 0.79833984375, 0.89013671875, 0.95068359375, 0.94921875, 0.75048828125, 0.61865234375, 0.533203125, 0.8857421875, 0.37744140625, 0.98046875, 0.78271484375, 0.3388671875, 0.96044921875, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.31396484375, 0.418701171875, 0.607421875, 1.0, 0.99951171875, 0.998046875, 0.77197265625, 0.78271484375, 0.71875, 0.341552734375, 0.1561279296875, 0.33447265625, 0.34765625, 0.406982421875, 0.350341796875, 0.251708984375, 0.29931640625, 0.234619140625, 0.1441650390625, 0.1441650390625, 0.449462890625, 0.003429412841796875, 0.01473236083984375, 0.99951171875, 0.4765625, 0.6279296875, 0.63330078125, 0.77197265625, 0.7744140625, 0.8291015625, 0.517578125, 0.99951171875, 0.2509765625, 0.355712890625, 0.265869140625, 0.265869140625, 0.2069091796875, 0.294189453125, 0.31396484375, 0.322265625, 0.1353759765625, 0.27294921875, 0.9287109375, 0.158203125, 0.11517333984375, 0.45703125, 0.7548828125, 0.662109375, 0.276611328125, 0.420654296875, 0.77734375, 0.103759765625, 0.127685546875, 0.115966796875, 0.4931640625, 0.83740234375, 0.6298828125, 1.0, 1.0, 1.0, 0.82177734375, 0.94287109375, 0.90087890625, 0.79052734375, 0.4609375, 0.970703125, 0.388671875, 0.46484375, 0.6298828125, 0.99951171875, 0.99951171875, 0.99951171875, 0.63330078125, 0.484375, 0.6298828125, 0.71630859375, 0.5244140625, 0.480712890625, 0.56005859375, 0.505859375, 0.62451171875, 0.658203125, 0.57763671875, 0.43017578125, 0.1766357421875, 0.1688232421875, 0.1285400390625, 0.99951171875, 0.9990234375, 0.99169921875, 0.9951171875, 0.98876953125, 0.93603515625, 0.9541015625, 0.638671875, 0.73974609375, 0.640625, 0.90869140625, 0.5546875, 0.8974609375, 0.97607421875, 0.72802734375, 0.9951171875, 1.0, 0.99755859375, 0.99755859375, 0.8447265625, 0.84033203125, 0.900390625, 0.72509765625, 0.4921875, 1.0, 1.0, 1.0, 0.98193359375, 0.984375, 0.98583984375, 0.78515625, 0.7490234375, 1.0, 0.60546875, 0.48583984375, 0.509765625, 0.98388671875, 0.99560546875, 0.98388671875, 0.515625, 0.57763671875, 0.5234375, 0.73486328125, 0.66552734375, 0.004055023193359375, 0.0005664825439453125, 0.034881591796875, 0.0029354095458984375, 0.4921875, 0.5849609375, 0.66552734375, 0.689453125, 0.85888671875, 0.9345703125, 0.2254638671875, 0.294189453125, 0.437744140625, 0.58203125, 0.5556640625, 0.36572265625, 0.70068359375, 0.732421875, 0.96923828125, 0.77197265625, 0.47265625, 0.82421875, 0.4091796875, 0.73388671875, 0.71240234375, 0.53515625, 0.50390625, 0.484375, 0.2081298828125, 0.4765625, 0.289306640625, 0.45703125, 0.521484375, 0.5, 0.403564453125, 0.287841796875, 0.02886962890625, 0.90478515625, 0.89892578125, 0.99609375, 0.88427734375, 0.87060546875, 0.8173828125, 0.9111328125, 0.92529296875, 0.935546875, 1.0, 1.0, 1.0, 0.98291015625, 0.98583984375, 0.96435546875, 0.5546875, 0.287841796875, 0.39990234375, 0.56201171875, 0.307373046875, 0.32763671875, 0.87890625, 0.6494140625, 0.8701171875, 0.9267578125, 0.9111328125, 0.943359375, 0.91015625, 0.90966796875, 0.8798828125, 0.61865234375, 0.658203125, 0.865234375, 0.57763671875, 0.54296875, 0.359375, 0.91748046875, 0.69580078125, 0.9287109375, 0.264404296875, 0.99267578125, 0.036773681640625, 0.45703125, 0.67919921875, 0.53125 ], "eval_runtime": 80.1619, "eval_samples_per_second": 9.356, "eval_steps_per_second": 0.299, "eval_rms_calibration_error": 0.29831797931294723 }