{ "model_dir": "models/prompt_tuning/llama-7b-counterfactual_python", "distribution_id": "counterfactual_python", "timestamp": "2023-10-19 22:38:50", "eval_loss": 0.64111328125, "eval_score": -0.201171875, "eval_brier_score": 0.201171875, "eval_average_probability": 0.66796875, "eval_accuracy": 0.6986666666666667, "eval_probabilities": [ 0.658203125, 0.5, 0.607421875, 0.6259765625, 0.32763671875, 0.50390625, 0.9990234375, 0.9931640625, 0.994140625, 0.58154296875, 0.62255859375, 0.77197265625, 0.32763671875, 0.99853515625, 0.56591796875, 0.76611328125, 0.6826171875, 0.1895751953125, 0.010009765625, 0.056640625, 0.0293121337890625, 1.0, 1.0, 0.1365966796875, 0.498046875, 0.4970703125, 0.4990234375, 0.98876953125, 0.9912109375, 0.986328125, 0.9921875, 0.392333984375, 0.2337646484375, 0.95654296875, 0.0013885498046875, 0.5390625, 0.99169921875, 0.990234375, 0.98974609375, 0.97705078125, 0.48046875, 0.98193359375, 0.50390625, 0.5029296875, 0.50146484375, 0.525390625, 0.458984375, 0.5849609375, 0.08447265625, 0.02655029296875, 0.06707763671875, 0.4990234375, 0.4990234375, 0.4970703125, 0.72802734375, 0.71533203125, 0.6826171875, 0.29248046875, 0.385009765625, 0.392333984375, 0.27197265625, 0.27197265625, 0.1480712890625, 0.951171875, 1.0, 0.99658203125, 0.7373046875, 0.998046875, 0.9775390625, 0.99951171875, 0.453369140625, 0.98681640625, 0.99462890625, 1.0, 0.92919921875, 0.5, 0.5029296875, 0.49560546875, 0.03021240234375, 0.92724609375, 0.70556640625, 0.82421875, 0.97314453125, 1.0, 0.92626953125, 0.99853515625, 0.57373046875, 1.0, 1.0, 1.0, 0.3486328125, 0.32080078125, 0.546875, 0.37744140625, 0.287841796875, 0.98046875, 0.99951171875, 0.98828125, 1.0, 0.57958984375, 0.60400390625, 0.60205078125, 0.00400543212890625, 0.00130462646484375, 0.0035381317138671875, 0.97607421875, 0.9716796875, 0.9677734375, 1.0, 1.0, 1.0, 0.662109375, 0.95263671875, 0.89013671875, 0.4921875, 0.9345703125, 0.7607421875, 0.09814453125, 0.4580078125, 0.53173828125, 0.998046875, 0.98828125, 0.99365234375, 0.99951171875, 0.998046875, 0.9931640625, 0.97265625, 0.63330078125, 0.453369140625, 0.275146484375, 0.615234375, 0.4111328125, 0.65673828125, 0.85498046875, 0.420654296875, 0.5, 0.5, 0.5009765625, 0.6689453125, 1.0, 0.67578125, 0.68603515625, 0.9638671875, 0.363037109375, 0.88427734375, 0.5078125, 0.69921875, 0.7880859375, 0.5078125, 0.72509765625, 0.05706787109375, 0.0953369140625, 0.97216796875, 0.9443359375, 0.418701171875, 0.90576171875, 0.94677734375, 0.94580078125, 0.9150390625, 0.8974609375, 0.8310546875, 0.39990234375, 0.607421875, 0.51953125, 0.7548828125, 0.355712890625, 0.42626953125, 0.56591796875, 0.640625, 0.437744140625, 0.373779296875, 0.98828125, 0.98876953125, 0.98779296875, 0.66552734375, 0.91259765625, 0.822265625, 0.5390625, 0.86865234375, 0.9072265625, 0.51171875, 0.445556640625, 0.57763671875, 1.0, 1.0, 1.0, 0.51953125, 0.50390625, 0.640625, 0.0078125, 0.77734375, 0.84814453125, 0.611328125, 0.385009765625, 0.60009765625, 0.50390625, 0.158203125, 0.6826171875, 0.4921875, 0.56982421875, 0.42626953125, 0.98681640625, 1.0, 0.99560546875, 0.99658203125, 0.9912109375, 0.56982421875, 0.96875, 0.615234375, 0.62255859375, 0.48828125, 0.484375, 0.58154296875, 0.1441650390625, 0.453369140625, 0.4765625, 0.027587890625, 0.29248046875, 8.64267349243164e-06, 0.9921875, 0.98974609375, 0.9482421875, 0.9970703125, 0.9970703125, 1.0, 0.97314453125, 0.56201171875, 0.97998046875, 0.50244140625, 0.50830078125, 0.50244140625, 0.49609375, 0.49658203125, 0.49267578125, 0.99951171875, 1.0, 1.0, 0.99951171875, 0.99853515625, 1.0, 0.99951171875, 1.0, 1.0, 0.403564453125, 0.95654296875, 0.91943359375, 0.98974609375, 0.99951171875, 1.0, 0.92431640625, 0.39990234375, 0.381103515625, 0.62255859375, 0.76611328125, 0.66552734375, 0.85888671875, 0.20556640625, 0.05224609375, 0.5390625, 0.5927734375, 0.97265625, 0.329345703125, 0.018402099609375, 0.2281494140625, 0.4921875, 0.57763671875, 0.94970703125, 0.99951171875, 0.9990234375, 0.9892578125, 0.9912109375, 0.1451416015625, 0.740234375, 0.49853515625, 0.498046875, 0.49853515625, 0.4921875, 0.449462890625, 0.47265625, 0.09271240234375, 0.0203399658203125, 0.32763671875, 1.0, 0.99951171875, 1.0, 0.974609375, 0.403564453125, 0.80419921875, 0.029083251953125, 0.11676025390625, 0.036224365234375, 0.49609375, 0.289306640625, 0.1441650390625, 0.79296875, 0.78662109375, 0.97119140625, 1.0, 1.0, 0.91845703125, 0.37744140625, 0.0013885498046875, 0.352294921875, 0.050323486328125, 0.53125, 0.09808349609375, 0.5927734375, 0.546875, 0.55078125, 0.57373046875, 0.5234375, 0.6513671875, 0.9326171875, 0.56982421875, 0.98974609375, 0.5390625, 0.99365234375, 0.37744140625, 0.66552734375, 0.56591796875, 0.60009765625, 0.740234375, 0.64404296875, 0.61865234375, 0.99853515625, 1.0, 0.76611328125, 0.70751953125, 0.63330078125, 0.689453125, 0.75048828125, 0.6259765625, 0.7744140625, 0.49853515625, 0.49853515625, 0.49853515625, 1.0, 1.0, 0.94873046875, 0.484375, 0.0031719207763671875, 0.106689453125, 0.60009765625, 0.445556640625, 0.4765625, 0.6298828125, 0.46875, 0.55078125, 0.9580078125, 0.1943359375, 0.39990234375, 0.50048828125, 0.50390625, 0.50048828125, 0.5234375, 0.63720703125, 0.80322265625, 0.93994140625, 0.96875, 0.373779296875, 0.546875, 0.58154296875, 0.9609375, 0.87255859375, 0.388671875, 0.658203125, 0.34521484375, 0.88330078125, 0.29736328125, 0.9990234375, 1.0, 0.99853515625, 0.204345703125, 0.1312255859375, 0.2393798828125, 1.0, 1.0, 1.0, 0.26904296875, 0.275146484375, 0.546875, 0.26904296875, 0.994140625, 0.1895751953125, 1.0, 0.9990234375, 1.0, 0.71533203125, 0.30078125, 0.33447265625, 0.5048828125, 0.5009765625, 0.5009765625, 0.275146484375, 0.3701171875, 0.546875, 0.484375, 0.515625, 0.47265625, 0.982421875, 0.99365234375, 0.7373046875, 1.0, 0.99951171875, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.49462890625, 0.4990234375, 0.50830078125, 0.94970703125, 0.0017824172973632812, 0.9990234375, 0.5, 0.294189453125, 0.388671875, 0.5390625, 0.822265625, 0.53515625, 1.0, 1.0, 1.0, 0.97412109375, 0.9990234375, 0.841796875, 0.59619140625, 0.615234375, 0.287841796875, 0.99951171875, 0.94677734375, 0.9990234375, 1.0, 1.0, 0.99951171875, 0.2017822265625, 0.48046875, 0.4072265625, 0.449462890625, 0.6298828125, 0.978515625, 0.453369140625, 0.99609375, 0.484375, 0.953125, 0.99951171875, 0.9970703125, 0.57763671875, 0.58154296875, 0.287841796875, 0.4921875, 0.4921875, 0.5927734375, 0.947265625, 0.97216796875, 0.74609375, 0.1519775390625, 0.041473388671875, 0.37744140625, 0.9697265625, 1.0, 0.99951171875, 0.69287109375, 0.6513671875, 0.92431640625, 0.7431640625, 0.515625, 0.7216796875, 0.501953125, 0.5048828125, 0.50048828125, 0.99462890625, 0.338134765625, 0.751953125, 0.338134765625, 0.9912109375, 0.89892578125, 0.34521484375, 0.83349609375, 0.87060546875, 0.445556640625, 0.57763671875, 0.5234375, 0.99169921875, 0.98193359375, 0.99267578125, 0.5390625, 0.36669921875, 0.3486328125, 0.67919921875, 0.6513671875, 0.375732421875, 0.01214599609375, 0.2254638671875, 0.015899658203125, 0.31396484375, 0.30078125, 0.5, 0.62255859375, 0.46875, 0.81982421875, 0.94970703125, 0.71240234375, 0.56982421875, 0.80078125, 0.78125, 0.80078125, 0.341552734375, 0.52734375, 0.46484375, 0.350341796875, 0.0293121337890625, 0.900390625, 0.84814453125, 0.92431640625, 0.94189453125, 0.931640625, 0.83544921875, 0.90869140625, 0.67578125, 0.5234375, 0.5546875, 1.0, 1.0, 1.0, 0.90966796875, 0.97314453125, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.0108184814453125, 0.0994873046875, 0.363037109375, 0.99951171875, 1.0, 0.9990234375, 0.8056640625, 0.96923828125, 0.9072265625, 0.1800537109375, 0.79296875, 0.943359375, 0.611328125, 0.55810546875, 0.5234375, 0.352294921875, 0.2509765625, 0.294189453125, 0.89013671875, 0.47265625, 0.1422119140625, 0.0226287841796875, 0.2421875, 0.09808349609375, 0.303955078125, 0.5, 0.8740234375, 0.99365234375, 0.98779296875, 0.99609375, 1.0, 0.998046875, 0.37744140625, 0.662109375, 0.552734375, 0.70263671875, 0.37744140625, 0.61865234375, 0.7744140625, 0.3701171875, 0.953125, 0.53515625, 1.0, 0.640625, 0.888671875, 0.9951171875, 0.97412109375, 0.9833984375, 0.962890625, 0.98193359375, 0.98974609375, 0.103759765625, 0.06561279296875, 0.105224609375, 0.99755859375, 0.99951171875, 0.8291015625, 1.0, 1.0, 1.0, 0.994140625, 0.9794921875, 1.0, 0.99951171875, 0.83984375, 1.0, 0.5009765625, 0.501953125, 0.4990234375, 1.0, 1.0, 1.0, 0.373779296875, 0.37744140625, 0.154052734375, 0.445556640625, 0.31396484375, 0.30078125, 0.26904296875, 0.2254638671875, 0.2493896484375, 0.50244140625, 0.50341796875, 0.50146484375, 0.9658203125, 0.947265625, 0.92529296875, 0.97265625, 0.94970703125, 0.039642333984375, 0.99755859375, 0.99072265625, 0.99853515625, 0.67919921875, 0.4609375, 0.33447265625, 0.26904296875, 0.85205078125, 0.0236968994140625, 0.8310546875, 1.0, 1.0, 0.998046875, 0.99951171875, 0.9990234375, 0.99560546875, 1.0, 0.26904296875, 0.5, 0.517578125, 0.346923828125, 1.0, 1.0, 1.0, 0.9990234375, 0.99853515625, 0.9990234375, 0.8896484375, 0.94189453125, 0.99072265625, 0.56982421875, 0.248046875, 0.25830078125, 0.50390625, 0.5087890625, 0.50830078125, 0.32421875, 0.32763671875, 0.31396484375, 0.958984375, 0.83984375, 0.99951171875, 1.0, 0.9033203125, 1.0, 0.55810546875, 0.69921875, 0.607421875, 0.9853515625, 0.80810546875, 0.8154296875, 0.9814453125, 0.9912109375, 1.0, 0.2379150390625, 0.275146484375, 0.2254638671875, 0.99755859375, 0.97314453125, 0.96875, 0.51220703125, 0.5126953125, 0.5107421875, 0.56591796875, 0.23095703125, 0.275146484375, 0.4990234375, 0.4990234375, 0.5029296875, 0.61865234375, 0.9873046875, 0.12420654296875, 0.515625, 0.6513671875, 0.54296875, 0.50146484375, 0.50048828125, 0.498046875, 1.0, 1.0, 0.9970703125, 0.88232421875, 0.865234375, 0.85791015625, 0.91943359375, 0.9306640625, 0.99560546875, 1.0, 1.0, 1.0, 0.184814453125, 0.24072265625, 0.27978515625, 0.515625, 0.484375, 0.83544921875, 0.8310546875, 0.381103515625, 0.287841796875, 0.943359375, 0.4609375, 0.037322998046875, 0.98095703125, 0.98095703125, 0.97802734375, 0.951171875, 1.0, 0.83984375, 0.462890625, 0.4921875, 0.74755859375, 0.70751953125, 0.90576171875, 0.72509765625, 0.92431640625, 0.955078125, 0.4921875, 1.0, 0.99658203125, 1.0, 0.611328125, 0.94677734375, 0.962890625 ], "eval_runtime": 47.6405, "eval_samples_per_second": 15.743, "eval_steps_per_second": 0.504 }