{ "model_dir": "models/prompt_tuning/llama-13b-counterfactual_python", "distribution_id": "counterfactual_python", "timestamp": "2023-10-23 23:33:48", "eval_loss": 0.693359375, "eval_score": -0.2203369140625, "eval_brier_score": 0.2203369140625, "eval_average_probability": 0.6357421875, "eval_accuracy": 0.6773333333333333, "eval_probabilities": [ 0.4609375, 0.260498046875, 0.72021484375, 0.90283203125, 0.76708984375, 0.414794921875, 1.0, 1.0, 1.0, 0.51171875, 0.69921875, 0.71630859375, 0.98095703125, 0.1839599609375, 0.93212890625, 0.422607421875, 0.78271484375, 0.39990234375, 0.7802734375, 0.65380859375, 0.57666015625, 0.10821533203125, 0.307373046875, 0.611328125, 0.78125, 0.7431640625, 0.7607421875, 0.99951171875, 0.99951171875, 0.998046875, 0.6611328125, 0.318359375, 0.1798095703125, 0.990234375, 0.9833984375, 0.63330078125, 0.8984375, 0.955078125, 0.962890625, 0.57763671875, 0.72509765625, 0.73583984375, 0.59619140625, 0.54296875, 0.5849609375, 0.43017578125, 0.401611328125, 0.48046875, 0.244384765625, 0.294921875, 0.2379150390625, 0.708984375, 0.70068359375, 0.5888671875, 0.1358642578125, 0.10845947265625, 0.10260009765625, 0.56103515625, 0.595703125, 0.82177734375, 0.7744140625, 0.5390625, 0.236572265625, 0.235107421875, 0.435791015625, 0.60107421875, 0.6806640625, 0.671875, 0.253173828125, 0.56591796875, 0.5927734375, 0.61669921875, 0.99609375, 0.99853515625, 0.89013671875, 0.51171875, 0.66552734375, 0.60009765625, 0.90576171875, 0.861328125, 0.291015625, 0.189697265625, 0.328125, 0.796875, 0.84912109375, 0.9912109375, 0.6533203125, 1.0, 1.0, 1.0, 0.376953125, 0.2154541015625, 0.70654296875, 0.8359375, 0.9150390625, 0.697265625, 0.75830078125, 0.68212890625, 0.7705078125, 0.69775390625, 0.5390625, 0.85693359375, 0.0013780593872070312, 0.0018825531005859375, 0.0017547607421875, 0.99169921875, 0.98388671875, 0.99658203125, 1.0, 1.0, 1.0, 0.95458984375, 0.99755859375, 0.91357421875, 0.546875, 0.908203125, 0.990234375, 0.99853515625, 0.9970703125, 0.943359375, 0.99560546875, 0.765625, 0.71533203125, 0.994140625, 0.99560546875, 0.9306640625, 0.85205078125, 0.623046875, 0.822265625, 0.53369140625, 0.446044921875, 0.3662109375, 0.1412353515625, 0.5830078125, 0.1019287109375, 0.5888671875, 0.5888671875, 0.61865234375, 0.58056640625, 0.5146484375, 0.9365234375, 0.7548828125, 0.9267578125, 0.57275390625, 0.382568359375, 0.5478515625, 0.77978515625, 0.443603515625, 0.470703125, 0.86083984375, 0.603515625, 0.580078125, 0.53369140625, 0.9208984375, 0.78857421875, 0.8017578125, 1.0, 1.0, 1.0, 0.35009765625, 0.271484375, 0.457763671875, 0.67333984375, 0.388671875, 0.5283203125, 0.70458984375, 0.7177734375, 0.65380859375, 0.8779296875, 0.054351806640625, 0.2587890625, 0.99951171875, 0.98779296875, 0.98828125, 0.60009765625, 0.307373046875, 0.79248046875, 0.7890625, 0.67724609375, 0.341064453125, 0.482421875, 0.525390625, 0.462890625, 0.99853515625, 0.974609375, 0.966796875, 0.60400390625, 0.6806640625, 0.73193359375, 0.490234375, 0.6435546875, 0.78076171875, 0.391357421875, 0.30908203125, 0.451416015625, 0.505859375, 0.1778564453125, 0.120849609375, 0.7607421875, 0.91943359375, 0.5888671875, 0.99609375, 0.9970703125, 0.98583984375, 0.9990234375, 0.9990234375, 0.98974609375, 0.441650390625, 0.48828125, 0.478515625, 0.607421875, 0.5, 0.462890625, 0.478515625, 0.5634765625, 0.474609375, 1.0, 0.24365234375, 0.0115966796875, 0.99951171875, 0.99609375, 0.8505859375, 0.0003936290740966797, 0.0043487548828125, 0.61865234375, 0.896484375, 0.5849609375, 0.98681640625, 0.61865234375, 0.287841796875, 0.4072265625, 0.48828125, 0.363037109375, 0.97607421875, 0.7470703125, 0.7236328125, 0.93701171875, 0.96533203125, 0.95947265625, 0.90185546875, 0.85009765625, 0.98486328125, 0.99755859375, 0.1864013671875, 0.91748046875, 0.7265625, 0.25244140625, 0.1302490234375, 0.98193359375, 0.94775390625, 0.716796875, 0.609375, 0.66552734375, 0.105224609375, 0.39990234375, 0.5771484375, 0.66064453125, 0.93310546875, 0.23681640625, 0.1959228515625, 0.796875, 0.94140625, 0.68701171875, 0.93896484375, 0.3916015625, 0.326904296875, 0.448486328125, 0.89013671875, 0.98876953125, 0.919921875, 0.2666015625, 0.2337646484375, 0.5908203125, 0.56201171875, 0.546875, 0.54296875, 0.278564453125, 0.435791015625, 0.59326171875, 0.896484375, 0.20947265625, 0.16455078125, 0.9931640625, 0.978515625, 0.990234375, 0.66015625, 0.9716796875, 0.63525390625, 0.051849365234375, 0.00864410400390625, 0.047088623046875, 0.70751953125, 0.1993408203125, 0.56982421875, 0.352294921875, 0.449462890625, 0.9150390625, 0.0026531219482421875, 0.5029296875, 0.505859375, 0.611328125, 0.440673828125, 0.1485595703125, 0.175537109375, 0.401123046875, 0.8515625, 0.5537109375, 0.250244140625, 0.63720703125, 0.045654296875, 0.0982666015625, 0.5478515625, 0.385009765625, 0.97216796875, 0.96826171875, 0.403564453125, 0.8623046875, 0.97265625, 0.8564453125, 0.9599609375, 0.4599609375, 0.173828125, 0.369873046875, 0.2469482421875, 0.873046875, 0.806640625, 0.46875, 0.406982421875, 0.3408203125, 0.34765625, 0.385009765625, 0.56396484375, 0.2476806640625, 0.57373046875, 0.71240234375, 0.7216796875, 0.388916015625, 0.75537109375, 0.64208984375, 0.9443359375, 0.609375, 0.66552734375, 0.64892578125, 0.405029296875, 0.31494140625, 0.5615234375, 0.55908203125, 0.59814453125, 0.1343994140625, 0.431884765625, 0.10028076171875, 0.66552734375, 0.78271484375, 0.763671875, 0.43017578125, 0.57177734375, 0.36376953125, 0.8056640625, 0.64599609375, 0.9033203125, 0.54296875, 0.1591796875, 0.190673828125, 0.8447265625, 0.9169921875, 0.80419921875, 0.86474609375, 0.03033447265625, 0.55810546875, 0.9638671875, 0.99951171875, 0.978515625, 0.99609375, 0.9931640625, 0.99365234375, 1.0, 1.0, 1.0, 0.1947021484375, 0.180419921875, 0.45849609375, 0.763671875, 0.67236328125, 0.37939453125, 0.99560546875, 0.998046875, 0.99951171875, 0.275390625, 0.48681640625, 0.351318359375, 0.403564453125, 0.359375, 0.33447265625, 0.5888671875, 0.82421875, 0.69091796875, 0.93994140625, 0.69287109375, 0.80810546875, 0.94921875, 0.99462890625, 0.94677734375, 0.9931640625, 0.85595703125, 1.0, 0.9921875, 0.982421875, 0.97998046875, 0.99609375, 0.9814453125, 0.98876953125, 0.73388671875, 0.92529296875, 0.73095703125, 0.99951171875, 0.9501953125, 0.8466796875, 0.307373046875, 0.458984375, 0.08880615234375, 0.5625, 0.57568359375, 0.437255859375, 0.99951171875, 1.0, 0.9990234375, 0.414306640625, 0.97021484375, 0.5615234375, 0.248046875, 0.1461181640625, 0.04132080078125, 0.338134765625, 0.85205078125, 0.69580078125, 0.99951171875, 0.99853515625, 1.0, 0.340576171875, 0.94677734375, 0.57861328125, 0.3564453125, 0.47265625, 0.76171875, 0.67724609375, 0.8125, 0.5419921875, 0.82421875, 0.998046875, 0.99951171875, 0.275146484375, 0.5849609375, 0.2239990234375, 0.329833984375, 0.100341796875, 0.3037109375, 0.99853515625, 0.99462890625, 0.9765625, 0.546875, 0.0574951171875, 0.204345703125, 0.9345703125, 1.0, 0.1175537109375, 0.0038547515869140625, 0.0526123046875, 0.2281494140625, 0.99609375, 0.95458984375, 0.7255859375, 0.47265625, 0.56591796875, 0.5234375, 0.193115234375, 0.1766357421875, 0.1795654296875, 0.9794921875, 0.80322265625, 0.77685546875, 0.384033203125, 0.8544921875, 0.88232421875, 0.1744384765625, 0.282958984375, 0.291015625, 0.99755859375, 0.99853515625, 1.0, 0.82421875, 0.81982421875, 0.437744140625, 0.312255859375, 0.2421875, 0.2281494140625, 0.321533203125, 0.1014404296875, 0.42724609375, 0.7353515625, 0.63671875, 0.5517578125, 0.6015625, 0.6181640625, 0.52099609375, 0.1134033203125, 0.72412109375, 0.6318359375, 0.525390625, 0.69580078125, 0.416748046875, 0.501953125, 0.63330078125, 0.4921875, 0.1573486328125, 0.052734375, 0.66748046875, 0.95068359375, 0.93603515625, 0.97314453125, 0.9990234375, 0.9990234375, 0.9990234375, 0.437744140625, 0.76025390625, 0.564453125, 0.73046875, 0.8310546875, 0.998046875, 0.6689453125, 0.182373046875, 0.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.0240478515625, 0.0330810546875, 0.1175537109375, 1.0, 0.9853515625, 0.9951171875, 0.33203125, 0.93359375, 0.609375, 0.65478515625, 0.140869140625, 0.56201171875, 0.57763671875, 0.68603515625, 0.405517578125, 0.373779296875, 0.403564453125, 0.381103515625, 0.97705078125, 0.30322265625, 0.80029296875, 0.7333984375, 0.9892578125, 1.0, 0.206298828125, 0.77587890625, 0.83447265625, 0.97607421875, 0.9716796875, 0.97021484375, 0.97998046875, 0.9990234375, 0.235107421875, 0.80029296875, 0.783203125, 0.751953125, 0.6435546875, 0.552734375, 0.73828125, 0.43017578125, 0.11126708984375, 0.68701171875, 0.97119140625, 0.900390625, 0.4921875, 0.95751953125, 0.94873046875, 0.96044921875, 0.7646484375, 0.98876953125, 0.99658203125, 0.5244140625, 0.61279296875, 0.544921875, 0.97412109375, 0.99609375, 0.91552734375, 1.0, 1.0, 1.0, 0.771484375, 0.958984375, 0.9775390625, 0.7734375, 0.97412109375, 0.92626953125, 0.453369140625, 0.453369140625, 0.3701171875, 1.0, 1.0, 1.0, 0.48828125, 0.3486328125, 0.455078125, 0.22265625, 0.6298828125, 0.55810546875, 0.72998046875, 0.59912109375, 0.85009765625, 0.64404296875, 0.60400390625, 0.48828125, 0.8193359375, 0.81640625, 0.66259765625, 0.80029296875, 0.85888671875, 0.1646728515625, 0.86083984375, 0.90185546875, 0.66015625, 0.19677734375, 0.21240234375, 0.146240234375, 0.21728515625, 0.4091796875, 0.1871337890625, 0.10858154296875, 0.345947265625, 0.9560546875, 1.0, 1.0, 1.0, 0.97119140625, 0.9921875, 0.88818359375, 0.85009765625, 0.2451171875, 0.20947265625, 1.0, 1.0, 1.0, 0.25830078125, 0.312255859375, 0.2213134765625, 0.97119140625, 0.9912109375, 0.9970703125, 0.10247802734375, 0.1448974609375, 0.060028076171875, 0.7548828125, 0.79296875, 0.7431640625, 0.2322998046875, 0.315673828125, 0.18359375, 0.55078125, 0.640625, 0.10931396484375, 1.0, 1.0, 1.0, 0.235107421875, 0.76904296875, 0.638671875, 0.98779296875, 0.9970703125, 0.9931640625, 0.22607421875, 0.71044921875, 0.953125, 0.5234375, 0.60009765625, 0.22265625, 0.990234375, 0.498046875, 0.73046875, 0.5546875, 0.546875, 0.72802734375, 0.10858154296875, 0.763671875, 0.09808349609375, 0.57373046875, 0.60400390625, 0.5078125, 0.069580078125, 0.148681640625, 0.83349609375, 0.46484375, 0.63720703125, 0.55810546875, 0.392333984375, 0.39990234375, 0.53515625, 0.59619140625, 0.70751953125, 0.9990234375, 0.92333984375, 0.93798828125, 0.859375, 0.89501953125, 0.5654296875, 0.70068359375, 1.0, 1.0, 1.0, 0.5244140625, 0.366943359375, 0.2763671875, 0.127685546875, 0.120849609375, 0.3310546875, 0.28466796875, 0.56201171875, 0.307373046875, 0.09271240234375, 0.154052734375, 0.98193359375, 0.86865234375, 0.85986328125, 0.943359375, 0.708984375, 0.861328125, 0.68603515625, 0.58154296875, 0.6748046875, 0.90625, 0.73193359375, 0.73486328125, 0.456787109375, 0.55810546875, 0.83349609375, 0.6689453125, 0.998046875, 0.99853515625, 0.65478515625, 0.546875, 0.60009765625, 0.7548828125 ], "eval_runtime": 80.1206, "eval_samples_per_second": 9.361, "eval_steps_per_second": 0.3 }