{ "model_dir": "models/prompt_tuning/llama-13b-code_easy", "distribution_id": "code_hard", "timestamp": "2023-10-23 23:24:33", "eval_loss": 3.12890625, "eval_score": -0.350830078125, "eval_brier_score": 0.3507780887442093, "eval_average_probability": 0.526153076728185, "eval_accuracy": 0.5626666666666666, "eval_probabilities": [ 0.99658203125, 0.84814453125, 0.83740234375, 2.384185791015625e-07, 0.0, 1.1920928955078125e-07, 0.97607421875, 0.99755859375, 0.955078125, 0.32763671875, 0.94482421875, 0.98974609375, 5.602836608886719e-06, 3.5762786865234375e-06, 1.5795230865478516e-05, 0.6943359375, 0.63916015625, 0.90283203125, 5.960464477539063e-08, 0.0, 0.0, 0.53125, 0.86328125, 0.8310546875, 0.021453857421875, 0.299072265625, 0.8681640625, 0.994140625, 0.72412109375, 0.9794921875, 0.23095703125, 0.2147216796875, 0.33642578125, 0.0247802734375, 0.10015869140625, 0.05792236328125, 0.52734375, 0.537109375, 0.0164031982421875, 0.0031490325927734375, 0.030792236328125, 0.03326416015625, 0.70068359375, 0.68701171875, 0.70654296875, 0.9951171875, 0.72119140625, 0.466796875, 1.0, 0.99951171875, 1.0, 0.10089111328125, 5.960464477539062e-07, 0.83984375, 0.0, 0.0, 0.0, 0.73876953125, 0.332763671875, 0.359375, 1.430511474609375e-06, 8.940696716308594e-07, 8.940696716308594e-07, 0.703125, 0.9970703125, 0.994140625, 0.1065673828125, 1.0, 0.132080078125, 0.7578125, 0.09808349609375, 0.4716796875, 0.83984375, 0.78271484375, 0.5546875, 0.3037109375, 0.41455078125, 0.277099609375, 0.90576171875, 0.900390625, 0.414794921875, 0.405517578125, 0.97998046875, 0.85693359375, 0.92822265625, 0.89892578125, 0.8271484375, 0.4873046875, 0.4970703125, 0.5107421875, 0.52490234375, 0.77294921875, 0.732421875, 0.99560546875, 0.99560546875, 0.9892578125, 0.462890625, 0.640625, 0.296630859375, 0.95263671875, 0.74609375, 0.83984375, 0.9140625, 0.75634765625, 0.93896484375, 0.3046875, 0.892578125, 0.431640625, 1.0, 0.2568359375, 0.06280517578125, 2.384185791015625e-07, 0.0, 0.0, 0.000255584716796875, 0.0005125999450683594, 0.00021195411682128906, 0.9853515625, 0.89892578125, 0.908203125, 0.6826171875, 0.63720703125, 0.896484375, 0.59619140625, 0.57763671875, 0.994140625, 0.83544921875, 0.849609375, 0.5244140625, 0.9853515625, 0.290283203125, 0.8203125, 0.662109375, 0.66357421875, 0.68603515625, 0.99755859375, 0.9931640625, 0.9970703125, 0.0, 0.0, 0.0, 0.89453125, 0.92626953125, 0.443603515625, 1.0, 0.427734375, 0.2685546875, 0.01519012451171875, 0.2017822265625, 0.33984375, 0.9619140625, 0.947265625, 0.99169921875, 0.422607421875, 0.19189453125, 0.1591796875, 0.20654296875, 0.1458740234375, 0.32080078125, 0.0, 0.0, 0.0, 0.227783203125, 0.351806640625, 0.62353515625, 0.44873046875, 0.54150390625, 0.328125, 0.59619140625, 0.3955078125, 0.5849609375, 0.92822265625, 0.402587890625, 0.4697265625, 0.82421875, 0.4091796875, 0.85986328125, 0.8076171875, 0.10858154296875, 0.01861572265625, 0.564453125, 0.1358642578125, 0.27783203125, 0.80810546875, 0.46875, 0.62255859375, 0.72265625, 0.375732421875, 0.94482421875, 0.392333984375, 0.6513671875, 0.57177734375, 0.6474609375, 0.53271484375, 0.3974609375, 0.9814453125, 0.93505859375, 0.307373046875, 0.2088623046875, 0.375732421875, 0.325927734375, 0.0, 5.960464477539063e-08, 5.960464477539063e-08, 0.435791015625, 0.47265625, 0.498046875, 0.0, 0.0, 0.0, 0.0007333755493164062, 0.0015192031860351562, 0.0017747879028320312, 0.375732421875, 0.391357421875, 0.447509765625, 0.5537109375, 0.52490234375, 0.494140625, 0.8974609375, 0.962890625, 0.9091796875, 0.56494140625, 0.185302734375, 0.60693359375, 0.7294921875, 0.69091796875, 0.57568359375, 0.990234375, 0.99755859375, 0.99462890625, 0.43017578125, 0.67919921875, 0.59814453125, 0.94970703125, 0.94873046875, 0.94921875, 0.9990234375, 0.87060546875, 0.97412109375, 0.96533203125, 0.98583984375, 0.439697265625, 0.97265625, 0.8662109375, 0.77685546875, 0.626953125, 0.70556640625, 0.71337890625, 0.11279296875, 0.0953369140625, 0.5, 0.56103515625, 0.6142578125, 0.515625, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.9306640625, 0.90966796875, 0.9111328125, 0.49609375, 0.51171875, 0.99072265625, 0.301513671875, 0.318359375, 0.447509765625, 0.7080078125, 0.92431640625, 0.99951171875, 0.3251953125, 0.2337646484375, 0.43212890625, 1.0, 1.0, 1.0, 0.8037109375, 0.658203125, 0.455078125, 0.69677734375, 0.436767578125, 0.54296875, 0.79931640625, 0.978515625, 0.66552734375, 1.0, 0.99951171875, 0.9404296875, 0.2978515625, 0.297119140625, 0.33935546875, 0.0, 0.0, 0.0, 0.8955078125, 0.94384765625, 0.83349609375, 0.496826171875, 0.37451171875, 0.14794921875, 0.1375732421875, 0.70751953125, 0.884765625, 0.0, 0.0, 9.590387344360352e-05, 0.73046875, 0.64599609375, 0.78125, 0.6337890625, 0.6044921875, 0.69482421875, 0.7841796875, 0.72802734375, 0.48046875, 0.0164031982421875, 0.041473388671875, 0.06585693359375, 0.58056640625, 0.401123046875, 0.50830078125, 0.0001442432403564453, 5.960464477539063e-08, 5.960464477539063e-08, 0.72802734375, 0.63720703125, 0.96728515625, 0.28466796875, 0.02001953125, 0.28466796875, 0.0144500732421875, 8.541345596313477e-05, 6.74128532409668e-05, 0.09576416015625, 0.10302734375, 0.09765625, 0.5126953125, 0.247314453125, 0.382080078125, 0.1312255859375, 0.281494140625, 0.1859130859375, 0.01142120361328125, 0.01384735107421875, 0.016021728515625, 0.039337158203125, 0.02886962890625, 0.033843994140625, 0.341552734375, 0.99560546875, 0.99609375, 0.061431884765625, 0.07342529296875, 0.06304931640625, 0.67041015625, 0.59521484375, 0.52099609375, 2.205371856689453e-06, 2.086162567138672e-06, 8.344650268554688e-07, 0.86083984375, 0.6259765625, 0.5244140625, 0.8134765625, 0.79541015625, 0.80029296875, 0.9951171875, 0.99267578125, 0.99462890625, 0.56591796875, 0.58154296875, 0.9296875, 0.406494140625, 0.345947265625, 0.46875, 0.97900390625, 0.99755859375, 0.99853515625, 0.5322265625, 0.145751953125, 0.1510009765625, 0.99853515625, 0.9990234375, 0.99169921875, 0.1500244140625, 0.55078125, 0.484375, 0.64794921875, 0.57666015625, 0.98095703125, 0.8603515625, 0.8994140625, 0.79931640625, 1.0, 1.0, 1.0, 0.892578125, 0.99462890625, 0.9970703125, 0.0, 0.0, 0.00017464160919189453, 0.64794921875, 0.93212890625, 0.97119140625, 0.8564453125, 0.92822265625, 0.86865234375, 1.0, 1.0, 1.0, 0.33203125, 0.062103271484375, 0.0191192626953125, 0.5, 0.99853515625, 0.5927734375, 0.974609375, 0.39794921875, 0.62255859375, 0.9951171875, 0.982421875, 0.99951171875, 0.033599853515625, 0.053009033203125, 0.035675048828125, 1.7881393432617188e-07, 5.960464477539063e-08, 3.5762786865234375e-07, 0.873046875, 0.98828125, 0.9365234375, 0.35302734375, 0.2281494140625, 0.3115234375, 0.0, 0.0, 0.0, 0.93994140625, 0.5234375, 0.92626953125, 0.662109375, 0.71142578125, 0.67529296875, 0.837890625, 0.607421875, 0.50634765625, 0.763671875, 0.92431640625, 0.86865234375, 0.45703125, 0.454345703125, 0.54150390625, 0.276611328125, 0.5927734375, 0.48046875, 0.39599609375, 0.81591796875, 0.5927734375, 0.73291015625, 0.54931640625, 0.78076171875, 0.8125, 0.8017578125, 0.845703125, 0.8564453125, 0.1763916015625, 0.85546875, 0.0, 0.0, 0.0, 0.118408203125, 0.044677734375, 0.9150390625, 0.99462890625, 0.92626953125, 0.9052734375, 0.5830078125, 0.59716796875, 0.94482421875, 0.5234375, 0.71875, 0.87060546875, 8.64267349243164e-06, 3.820657730102539e-05, 0.00019562244415283203, 0.41357421875, 0.446044921875, 0.57177734375, 0.61865234375, 0.71533203125, 0.9677734375, 0.71435546875, 0.175537109375, 0.369384765625, 0.904296875, 0.94091796875, 0.9365234375, 0.89013671875, 0.10015869140625, 0.0017004013061523438, 0.88720703125, 0.0330810546875, 0.039642333984375, 0.0, 0.0, 0.0, 0.99853515625, 1.0, 0.9560546875, 0.0391845703125, 0.5869140625, 0.6015625, 1.0, 1.0, 1.0, 0.7890625, 0.93798828125, 0.97412109375, 0.73046875, 0.61328125, 0.81689453125, 0.0, 0.0, 0.0, 0.638671875, 0.67041015625, 0.70263671875, 0.20166015625, 0.82568359375, 0.908203125, 5.960464477539063e-08, 5.960464477539063e-08, 5.960464477539063e-08, 0.99609375, 0.751953125, 0.73779296875, 0.67236328125, 0.9013671875, 0.9814453125, 0.92333984375, 0.63232421875, 0.399658203125, 0.4072265625, 0.34765625, 0.419677734375, 0.277587890625, 0.437744140625, 0.751953125, 0.450439453125, 0.5537109375, 0.515625, 0.93798828125, 0.420654296875, 0.451416015625, 1.0, 0.5, 0.5546875, 0.63720703125, 0.042816162109375, 0.03314208984375, 0.06561279296875, 0.08154296875, 0.085693359375, 0.0222930908203125, 1.0728836059570312e-06, 0.005062103271484375, 0.7578125, 0.56201171875, 0.64794921875, 0.0, 5.960464477539063e-08, 5.960464477539063e-08, 0.2421875, 0.21533203125, 0.234375, 0.5419921875, 0.79931640625, 0.4990234375, 0.0, 0.0008797645568847656, 0.0, 0.99267578125, 0.99560546875, 0.9931640625, 0.01666259765625, 0.00130462646484375, 0.0010166168212890625, 0.7646484375, 0.30078125, 0.2294921875, 0.62060546875, 0.73046875, 0.7373046875, 0.501953125, 0.5068359375, 0.5419921875, 0.91650390625, 0.9833984375, 0.974609375, 0.81591796875, 0.6982421875, 0.681640625, 0.1783447265625, 0.4580078125, 1.0, 0.6376953125, 0.9091796875, 0.5859375, 0.2705078125, 0.2393798828125, 0.2421875, 0.00014317035675048828, 0.0001366138458251953, 0.0001398324966430664, 0.5693359375, 0.394775390625, 0.72607421875, 0.537109375, 0.3779296875, 0.4306640625, 0.99365234375, 0.8486328125, 0.97412109375, 0.33642578125, 0.418212890625, 0.42333984375, 0.52978515625, 0.59423828125, 0.30908203125, 0.0006566047668457031, 0.0006422996520996094, 0.0016546249389648438, 0.556640625, 0.60009765625, 0.74365234375, 0.1981201171875, 0.34375, 0.294921875, 0.57568359375, 0.87646484375, 0.070068359375, 0.74462890625, 0.552734375, 0.19677734375, 0.99853515625, 0.94384765625, 0.9912109375, 0.43017578125, 0.79833984375, 0.79443359375, 0.04400634765625, 0.033721923828125, 0.11322021484375, 0.939453125, 0.56201171875, 0.73583984375, 0.97705078125, 0.97900390625, 0.919921875, 0.99853515625, 0.99951171875, 0.99755859375, 0.767578125, 0.8037109375, 0.7021484375, 0.74609375, 0.86962890625, 0.86376953125, 0.3896484375, 0.3388671875, 0.53125, 0.525390625, 0.64990234375, 0.86865234375, 0.420654296875, 0.43408203125, 0.453369140625, 0.8681640625, 0.90478515625, 0.5927734375, 0.544921875, 0.6533203125, 0.810546875, 0.79443359375, 0.053192138671875, 0.22265625, 0.99853515625, 0.99853515625, 0.9990234375, 0.9951171875, 0.99609375, 0.98388671875, 0.78125, 0.92578125, 0.99365234375, 0.68603515625, 0.654296875, 0.41064453125, 0.99609375, 0.99560546875, 0.73388671875, 0.3896484375, 0.45703125, 0.56396484375, 0.48876953125, 0.5576171875, 0.0869140625, 0.83984375, 0.8916015625, 0.59619140625, 0.455078125, 0.5390625, 0.6767578125, 0.61279296875, 0.6767578125, 0.6513671875, 0.71044921875, 0.830078125, 0.8857421875, 0.0036792755126953125, 0.001495361328125, 0.0034027099609375, 0.0, 1.8656253814697266e-05, 1.7940998077392578e-05, 2.0742416381835938e-05, 2.384185791015625e-07, 5.960464477539063e-08, 0.75439453125, 0.77587890625, 1.0, 0.74072265625, 0.1845703125, 0.2225341796875, 0.7177734375, 0.74755859375, 0.68359375, 0.9921875, 0.64892578125, 0.00394439697265625, 1.1920928955078125e-06, 1.4901161193847656e-06, 3.874301910400391e-06, 4.649162292480469e-06, 5.304813385009766e-06, 2.9981136322021484e-05 ], "eval_runtime": 80.8346, "eval_samples_per_second": 9.278, "eval_steps_per_second": 0.297, "eval_rms_calibration_error": 0.30815004952783964 }