{ "model_dir": "models/prompt_tuning/llama-7b-code_easy", "distribution_id": "code_hard", "timestamp": "2023-10-19 22:48:13", "eval_loss": 1.5830078125, "eval_score": -0.31005859375, "eval_brier_score": 0.3100222175404487, "eval_average_probability": 0.5784499011834463, "eval_accuracy": 0.62, "eval_probabilities": [ 1.0, 0.408203125, 0.173828125, 1.0, 1.0, 0.9990234375, 0.0313720703125, 0.034881591796875, 0.004398345947265625, 0.06805419921875, 0.06768798828125, 0.0755615234375, 1.0, 0.9931640625, 0.99853515625, 0.01337432861328125, 0.303955078125, 0.63525390625, 0.99951171875, 0.66796875, 0.08251953125, 0.458984375, 0.34521484375, 0.517578125, 0.8798828125, 0.9189453125, 0.5888671875, 0.0, 0.003376007080078125, 0.0006384849548339844, 0.350341796875, 0.445556640625, 0.611328125, 0.021453857421875, 0.77197265625, 0.37744140625, 0.0030040740966796875, 0.0006413459777832031, 0.120849609375, 0.0618896484375, 0.1561279296875, 0.275146484375, 0.16943359375, 0.0638427734375, 0.031463623046875, 0.99560546875, 0.7607421875, 0.01214599609375, 0.98193359375, 1.0, 0.99951171875, 0.1744384765625, 0.004364013671875, 0.00051116943359375, 0.0167694091796875, 0.0123748779296875, 0.025054931640625, 0.50634765625, 0.72412109375, 0.60302734375, 1.0, 1.0, 1.0, 0.85302734375, 0.95654296875, 1.0, 0.289306640625, 1.0, 0.61767578125, 0.48828125, 0.61669921875, 0.810546875, 0.732421875, 0.951171875, 0.611328125, 0.71875, 0.265869140625, 0.29736328125, 0.85400390625, 0.7607421875, 0.71533203125, 0.451416015625, 0.401611328125, 0.42822265625, 0.9052734375, 0.94580078125, 0.83544921875, 0.5830078125, 0.56005859375, 0.37939453125, 0.99658203125, 0.99609375, 0.99609375, 0.7373046875, 0.69580078125, 0.11126708984375, 0.43408203125, 0.818359375, 0.21728515625, 0.99951171875, 0.5830078125, 0.84814453125, 0.01090240478515625, 0.00971221923828125, 0.0035648345947265625, 0.0033740997314453125, 0.99609375, 0.003452301025390625, 0.22607421875, 0.7373046875, 0.939453125, 1.0, 1.0, 1.0, 0.00035834312438964844, 0.04083251953125, 0.0025501251220703125, 0.9765625, 0.267333984375, 0.9658203125, 0.966796875, 0.95654296875, 0.96435546875, 0.91796875, 0.85302734375, 1.0, 0.83642578125, 0.7431640625, 0.1312255859375, 0.00015926361083984375, 0.84130859375, 0.260498046875, 0.23388671875, 0.29736328125, 0.234619140625, 1.0, 1.0, 1.0, 0.9990234375, 0.99853515625, 0.9990234375, 0.943359375, 0.8408203125, 0.7744140625, 0.9990234375, 0.98291015625, 0.4814453125, 0.943359375, 0.08038330078125, 0.036773681640625, 0.2254638671875, 0.12249755859375, 0.441650390625, 0.0144500732421875, 0.005130767822265625, 0.0015611648559570312, 0.52734375, 0.75048828125, 0.060516357421875, 1.0, 0.99951171875, 1.0, 0.66455078125, 0.5703125, 0.73486328125, 0.484375, 0.7431640625, 0.662109375, 0.74755859375, 0.921875, 0.438720703125, 0.447509765625, 0.78125, 0.7880859375, 1.0, 1.0, 1.0, 0.72021484375, 0.9267578125, 0.94287109375, 0.95703125, 0.95849609375, 0.81005859375, 0.99560546875, 0.80419921875, 0.86083984375, 0.740234375, 0.81982421875, 0.8857421875, 0.32763671875, 0.662109375, 0.6689453125, 0.744140625, 0.53857421875, 0.5146484375, 0.00812530517578125, 0.99560546875, 0.043701171875, 2.950429916381836e-05, 0.0001538991928100586, 0.0009622573852539062, 0.0193634033203125, 0.99951171875, 0.99951171875, 0.4111328125, 0.498046875, 0.5888671875, 0.99853515625, 0.92919921875, 0.73583984375, 1.0, 1.0, 1.0, 0.6376953125, 0.7177734375, 0.39892578125, 0.75146484375, 0.67724609375, 0.57763671875, 0.81982421875, 0.53515625, 0.83544921875, 0.319091796875, 0.515625, 0.486328125, 0.927734375, 0.654296875, 1.0, 0.9814453125, 0.51123046875, 0.68017578125, 0.96240234375, 0.6826171875, 0.763671875, 0.85302734375, 0.7646484375, 0.77587890625, 0.8564453125, 0.7109375, 0.9755859375, 0.51953125, 0.89697265625, 0.25537109375, 0.9921875, 0.98828125, 0.875, 0.52734375, 0.5927734375, 0.63720703125, 0.0271759033203125, 0.022796630859375, 0.0048675537109375, 0.57763671875, 0.5234375, 0.5234375, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.529296875, 0.6396484375, 0.1014404296875, 0.689453125, 0.69287109375, 0.90380859375, 0.5048828125, 0.402587890625, 0.927734375, 0.0047149658203125, 1.0, 1.0, 0.69921875, 0.94921875, 0.755859375, 0.99609375, 0.99755859375, 0.99658203125, 0.9541015625, 0.94677734375, 0.65478515625, 0.9833984375, 0.9736328125, 0.9892578125, 0.0293121337890625, 0.763671875, 0.8623046875, 0.94384765625, 0.96484375, 0.98828125, 0.52734375, 0.607421875, 0.3486328125, 1.0, 0.9970703125, 1.0, 0.367431640625, 0.59716796875, 0.259033203125, 0.83544921875, 0.6689453125, 0.01384735107421875, 0.0850830078125, 0.267333984375, 0.1688232421875, 0.01227569580078125, 0.0299530029296875, 0.049713134765625, 0.80029296875, 0.923828125, 0.98486328125, 0.97705078125, 0.65234375, 0.72802734375, 0.92431640625, 0.060089111328125, 0.42626953125, 0.97412109375, 0.06903076171875, 0.005695343017578125, 0.83984375, 0.451416015625, 0.546875, 1.0, 0.99951171875, 0.99951171875, 0.994140625, 0.60595703125, 0.6513671875, 0.5234375, 0.7607421875, 0.46875, 1.0, 1.0, 1.0, 0.77197265625, 0.7607421875, 0.73388671875, 0.69921875, 0.8388671875, 0.763671875, 0.85498046875, 0.97705078125, 0.9755859375, 0.049591064453125, 0.044342041015625, 0.0460205078125, 0.9609375, 0.88427734375, 0.845703125, 0.06256103515625, 0.57177734375, 0.5830078125, 0.1683349609375, 0.067626953125, 0.227783203125, 0.998046875, 0.958984375, 0.99072265625, 1.0, 1.0, 1.0, 0.99658203125, 0.413330078125, 0.73291015625, 0.00128173828125, 0.0022869110107421875, 0.01763916015625, 0.443603515625, 0.60400390625, 0.873046875, 0.93408203125, 0.994140625, 0.99365234375, 0.51171875, 0.5546875, 0.689453125, 0.0006093978881835938, 0.0018892288208007812, 0.0007891654968261719, 8.749961853027344e-05, 0.998046875, 0.99365234375, 0.0218505859375, 0.0005040168762207031, 0.0377197265625, 0.85009765625, 0.6318359375, 0.609375, 0.78125, 0.7646484375, 0.99267578125, 0.77197265625, 0.403564453125, 0.56591796875, 0.98388671875, 0.99267578125, 1.0, 0.56005859375, 0.31396484375, 0.65478515625, 1.0, 1.0, 1.0, 0.02886962890625, 0.9638671875, 0.57958984375, 0.94873046875, 0.9638671875, 0.96044921875, 0.96142578125, 0.99853515625, 0.99853515625, 0.9873046875, 0.89501953125, 0.96630859375, 0.287841796875, 0.9951171875, 0.1519775390625, 0.546875, 0.86083984375, 0.7734375, 0.4111328125, 0.87060546875, 0.6513671875, 0.9951171875, 0.99560546875, 0.99609375, 0.09375, 0.145263671875, 0.261474609375, 0.6474609375, 0.77392578125, 0.71240234375, 0.607421875, 0.7138671875, 0.99951171875, 0.0792236328125, 0.0156707763671875, 0.06951904296875, 0.068603515625, 0.42138671875, 0.10601806640625, 0.65087890625, 0.63916015625, 0.69091796875, 0.69921875, 0.47265625, 0.515625, 0.021392822265625, 0.01336669921875, 0.170654296875, 0.501953125, 0.426025390625, 0.814453125, 0.99951171875, 0.669921875, 0.418701171875, 0.607421875, 0.55810546875, 0.5390625, 0.50390625, 0.5849609375, 0.441650390625, 0.60595703125, 0.75341796875, 0.60205078125, 0.66015625, 1.0, 0.01036834716796875, 1.0, 1.0, 1.0, 0.62890625, 0.67919921875, 1.0, 0.7919921875, 0.765625, 0.751953125, 0.2958984375, 0.34326171875, 0.51953125, 0.81005859375, 0.99169921875, 0.99169921875, 1.0, 1.0, 1.0, 0.8935546875, 0.408203125, 0.90966796875, 0.73291015625, 0.9111328125, 0.446533203125, 0.63330078125, 0.405517578125, 0.830078125, 0.00023055076599121094, 0.0001493692398071289, 0.00012826919555664062, 0.82275390625, 0.383056640625, 0.8984375, 1.0, 0.9521484375, 0.79833984375, 3.24249267578125e-05, 1.7881393432617188e-07, 0.0006880760192871094, 0.018798828125, 0.003795623779296875, 0.001461029052734375, 0.0994873046875, 0.08038330078125, 0.09136962890625, 0.00023734569549560547, 0.00153350830078125, 8.696317672729492e-05, 0.958984375, 0.368408203125, 0.1629638671875, 0.08160400390625, 0.06353759765625, 0.101318359375, 0.97705078125, 0.9697265625, 1.0, 0.11676025390625, 0.1480712890625, 0.2294921875, 1.0, 0.888671875, 0.900390625, 9.655952453613281e-06, 7.510185241699219e-06, 4.76837158203125e-06, 0.00945281982421875, 0.0003311634063720703, 0.009429931640625, 0.441650390625, 0.35400390625, 0.57470703125, 0.5029296875, 0.1446533203125, 0.6689453125, 0.401611328125, 0.537109375, 0.332763671875, 0.437744140625, 0.71240234375, 0.57373046875, 0.68701171875, 0.955078125, 0.76220703125, 0.86328125, 0.91845703125, 0.89306640625, 1.0, 0.71533203125, 0.18994140625, 1.0, 0.998046875, 1.0, 0.5927734375, 0.79296875, 0.962890625, 0.00031638145446777344, 0.0017824172973632812, 0.184814453125, 0.287841796875, 0.2421875, 0.25390625, 0.966796875, 1.0, 1.0, 0.12939453125, 0.07586669921875, 0.10968017578125, 0.87744140625, 1.1324882507324219e-06, 0.533203125, 0.0052337646484375, 1.0, 0.99365234375, 0.912109375, 0.91064453125, 0.8583984375, 0.0030517578125, 0.26123046875, 0.07476806640625, 0.83984375, 0.447509765625, 0.970703125, 0.9345703125, 0.8837890625, 0.943359375, 0.53515625, 0.363037109375, 0.39990234375, 0.2568359375, 0.5234375, 0.1895751953125, 0.63330078125, 0.1602783203125, 0.8173828125, 0.37744140625, 0.73095703125, 1.0, 0.349609375, 0.66357421875, 0.337158203125, 0.275146484375, 0.26123046875, 0.319091796875, 0.005405426025390625, 0.006717681884765625, 0.005218505859375, 0.69287109375, 0.7734375, 0.97900390625, 0.5302734375, 0.303955078125, 0.509765625, 0.98193359375, 0.98974609375, 0.335693359375, 0.9990234375, 0.63330078125, 0.56005859375, 0.39990234375, 0.6298828125, 0.45703125, 2.384185791015625e-07, 2.384185791015625e-07, 2.980232238769531e-07, 0.55078125, 0.640625, 0.76220703125, 0.36474609375, 0.56103515625, 0.6376953125, 0.80810546875, 0.4921875, 0.484375, 0.19677734375, 0.0546875, 0.71044921875, 0.9287109375, 0.8310546875, 0.1412353515625, 0.6416015625, 0.9638671875, 0.9638671875, 0.1302490234375, 0.1688232421875, 0.303955078125, 0.9990234375, 0.99951171875, 0.99951171875, 0.99951171875, 0.6875, 0.96728515625, 0.99072265625, 0.99267578125, 0.9736328125, 0.56396484375, 0.383056640625, 0.1571044921875, 0.890625, 0.951171875, 0.95166015625, 0.394287109375, 0.414794921875, 0.55810546875, 0.64599609375, 0.1451416015625, 0.89697265625, 0.302490234375, 0.346923828125, 0.36474609375, 0.1859130859375, 0.1883544921875, 0.35400390625, 0.078125, 0.08447265625, 0.986328125, 0.92529296875, 0.003429412841796875, 0.09271240234375, 0.0005507469177246094, 0.0001971721649169922, 0.0023975372314453125, 0.99609375, 0.998046875, 0.986328125, 0.712890625, 0.377197265625, 0.58154296875, 0.0, 0.0, 0.0, 0.093994140625, 0.030914306640625, 0.03759765625, 0.6494140625, 0.50927734375, 0.7548828125, 0.546875, 0.509765625, 0.2568359375, 0.9794921875, 0.99755859375, 0.9736328125, 0.505859375, 0.42431640625, 0.482421875, 0.5927734375, 0.64794921875, 0.7578125, 0.089111328125, 0.1688232421875, 0.20556640625, 0.99951171875, 0.99951171875, 1.0, 0.054595947265625, 0.1519775390625, 0.167724609375, 1.0, 1.7285346984863281e-06, 1.1920928955078125e-07, 0.75732421875, 0.8203125, 1.0, 0.83837890625, 0.0118255615234375, 0.00563812255859375, 0.0010042190551757812, 0.0020313262939453125, 0.0016775131225585938, 0.002216339111328125, 0.0207977294921875, 5.960464477539063e-08, 1.0, 1.0, 1.0, 0.99951171875, 0.99951171875, 0.99951171875 ], "eval_runtime": 46.6818, "eval_samples_per_second": 16.066, "eval_steps_per_second": 0.514, "eval_rms_calibration_error": 0.30992766765122487 }