{ "model_dir": "models/prompt_tuning/llama-13b-code_easy", "distribution_id": "code_easy", "timestamp": "2023-10-23 23:25:14", "eval_loss": 0.41796875, "eval_score": -0.10723876953125, "eval_brier_score": 0.10723876953125, "eval_average_probability": 0.8271484375, "eval_accuracy": 0.856, "eval_probabilities": [ 0.96630859375, 1.0, 0.9990234375, 1.0, 0.99853515625, 1.0, 0.388671875, 1.0, 0.99951171875, 0.85693359375, 0.8330078125, 0.8056640625, 0.043365478515625, 1.0, 0.9912109375, 0.307373046875, 0.388671875, 0.99951171875, 0.974609375, 0.39599609375, 0.71240234375, 0.98974609375, 0.984375, 1.0, 1.0, 0.55810546875, 1.0, 0.9912109375, 0.98876953125, 0.99951171875, 0.95703125, 0.078369140625, 0.669921875, 0.9111328125, 0.861328125, 0.90478515625, 1.0, 0.9853515625, 0.99169921875, 0.998046875, 0.953125, 0.796875, 0.9970703125, 0.9873046875, 0.99658203125, 1.0, 0.484375, 0.994140625, 0.7548828125, 0.79296875, 0.9208984375, 0.60009765625, 1.0, 1.0, 0.99853515625, 1.0, 1.0, 0.83203125, 0.552734375, 0.99853515625, 0.73095703125, 0.96728515625, 0.9619140625, 1.0, 1.0, 1.0, 0.64404296875, 0.958984375, 0.97314453125, 0.533203125, 0.019866943359375, 0.035675048828125, 1.0, 1.0, 1.0, 0.64794921875, 0.383056640625, 0.94677734375, 0.004467010498046875, 0.0023593902587890625, 0.076416015625, 0.64404296875, 0.56982421875, 0.4765625, 0.99169921875, 0.99853515625, 0.98974609375, 0.7138671875, 0.9248046875, 0.9921875, 0.99462890625, 0.81298828125, 0.0987548828125, 0.998046875, 0.9990234375, 1.0, 0.76611328125, 0.9931640625, 0.99072265625, 0.80810546875, 0.77197265625, 0.9990234375, 0.99755859375, 0.9990234375, 0.98876953125, 0.98974609375, 1.0, 0.986328125, 0.91845703125, 0.544921875, 0.99365234375, 1.0, 1.0, 1.0, 0.90625, 0.2069091796875, 0.986328125, 0.352294921875, 0.99853515625, 0.9951171875, 0.175537109375, 1.0, 0.640625, 1.0, 1.0, 1.0, 0.87255859375, 0.982421875, 0.96923828125, 1.0, 0.9990234375, 0.99853515625, 0.990234375, 0.97998046875, 1.0, 0.85791015625, 0.9990234375, 0.89404296875, 0.98095703125, 0.974609375, 0.99365234375, 1.0, 0.99951171875, 1.0, 1.0, 0.98193359375, 0.9794921875, 0.9423828125, 1.0, 1.0, 0.865234375, 0.47265625, 0.90185546875, 0.86865234375, 1.0, 1.0, 1.0, 0.97412109375, 0.95166015625, 0.998046875, 0.90966796875, 0.9833984375, 0.67578125, 0.8740234375, 0.8671875, 0.36669921875, 0.4072265625, 0.3486328125, 0.9951171875, 0.9970703125, 1.0, 0.99169921875, 1.0, 0.9990234375, 0.89501953125, 0.85400390625, 0.43408203125, 0.9990234375, 0.99951171875, 1.0, 0.615234375, 0.9990234375, 1.0, 0.89013671875, 0.98291015625, 0.99560546875, 1.0, 0.62255859375, 1.0, 0.99951171875, 0.99951171875, 0.9990234375, 0.99609375, 0.96142578125, 0.861328125, 0.9951171875, 1.0, 0.91259765625, 1.0, 1.0, 0.99951171875, 1.0, 0.08038330078125, 0.9453125, 0.79833984375, 0.96875, 0.8056640625, 0.900390625, 0.9833984375, 0.92626953125, 1.0, 0.6513671875, 0.96435546875, 1.0, 0.96337890625, 1.0, 0.403564453125, 0.607421875, 0.99951171875, 0.99951171875, 0.9990234375, 0.7607421875, 0.310791015625, 0.94482421875, 0.99951171875, 0.97705078125, 0.1480712890625, 0.931640625, 0.94091796875, 0.99951171875, 0.138427734375, 1.0, 1.0, 0.92919921875, 0.0022258758544921875, 0.96533203125, 0.00036406517028808594, 1.0, 0.9990234375, 0.99951171875, 0.46875, 0.0014104843139648438, 0.420654296875, 0.99853515625, 0.71533203125, 0.385009765625, 0.98486328125, 1.0, 0.99853515625, 0.2783203125, 0.437744140625, 0.12420654296875, 1.0, 1.0, 1.0, 0.99853515625, 0.99609375, 0.994140625, 0.86865234375, 0.86865234375, 0.615234375, 1.0, 1.0, 0.982421875, 0.0994873046875, 0.50390625, 0.57373046875, 0.97314453125, 0.94189453125, 0.9580078125, 1.0, 0.99755859375, 0.02801513671875, 0.200439453125, 0.146484375, 0.22509765625, 0.74609375, 0.78515625, 0.3310546875, 0.9970703125, 0.9638671875, 0.96728515625, 0.318359375, 0.09466552734375, 0.284912109375, 0.1422119140625, 0.69091796875, 1.0, 1.0, 0.998046875, 1.0, 0.66357421875, 1.0, 0.94189453125, 0.99951171875, 1.0, 1.0, 0.9921875, 0.96435546875, 0.294189453125, 0.99609375, 0.935546875, 0.99951171875, 0.986328125, 0.98779296875, 1.0, 0.9345703125, 0.96630859375, 0.962890625, 1.0, 1.0, 1.0, 1.0, 0.9990234375, 1.0, 0.99951171875, 0.9990234375, 1.0, 0.48828125, 0.90966796875, 0.9951171875, 0.98583984375, 0.98095703125, 1.0, 0.58154296875, 0.017181396484375, 0.982421875, 0.6279296875, 0.06463623046875, 0.5, 0.97607421875, 0.9970703125, 0.9921875, 0.99853515625, 0.9990234375, 0.978515625, 0.49609375, 0.46484375, 0.315673828125, 0.68603515625, 0.9638671875, 0.82421875, 1.0, 1.0, 1.0, 1.0, 1.0, 0.99951171875, 0.93017578125, 0.99755859375, 0.58544921875, 1.0, 0.99267578125, 0.99658203125, 0.99951171875, 1.0, 1.0, 0.71240234375, 0.87744140625, 0.89892578125, 0.98779296875, 0.994140625, 0.99462890625, 0.3408203125, 0.87548828125, 0.81396484375, 0.62451171875, 0.77880859375, 0.978515625, 0.33447265625, 0.521484375, 0.67236328125, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9755859375, 0.99658203125, 0.99267578125, 0.490234375, 0.99951171875, 1.0, 1.0, 0.65478515625, 0.81884765625, 0.90966796875, 0.9365234375, 1.0, 0.99853515625, 0.99853515625, 0.99853515625, 1.0, 1.0, 1.0, 1.0, 0.00022423267364501953, 0.0169830322265625, 0.1019287109375, 0.955078125, 0.414794921875, 0.8291015625, 0.1422119140625, 0.98828125, 0.89501953125, 0.71533203125, 0.1883544921875, 0.036773681640625, 0.1365966796875, 0.76904296875, 0.9326171875, 0.90576171875, 1.0, 1.0, 0.9990234375, 0.9423828125, 1.0, 0.98193359375, 0.99951171875, 0.99951171875, 0.381103515625, 1.0, 0.99462890625, 0.82763671875, 0.42431640625, 0.69580078125, 1.0, 0.9990234375, 0.998046875, 0.63330078125, 0.63330078125, 0.673828125, 0.6220703125, 0.82958984375, 0.95263671875, 0.9873046875, 1.0, 0.80322265625, 1.0, 0.6513671875, 1.0, 0.9833984375, 0.99951171875, 0.9990234375, 1.0, 1.0, 1.0, 1.0, 0.9365234375, 0.99951171875, 0.99951171875, 0.99951171875, 0.9775390625, 0.99951171875, 0.2254638671875, 0.845703125, 1.0, 0.99951171875, 0.935546875, 0.63330078125, 0.716796875, 0.38671875, 0.87060546875, 1.0, 1.0, 0.9990234375, 1.0, 0.984375, 0.9755859375, 0.88232421875, 0.96533203125, 0.7578125, 0.9990234375, 0.998046875, 0.437744140625, 0.6689453125, 0.85400390625, 0.99853515625, 1.0, 0.90283203125, 0.958984375, 0.98388671875, 0.74169921875, 0.763671875, 0.7373046875, 0.822265625, 0.5244140625, 0.546875, 0.2401123046875, 0.732421875, 0.99267578125, 0.1441650390625, 0.05340576171875, 0.1749267578125, 0.388671875, 1.0, 1.0, 1.0, 0.1710205078125, 0.85400390625, 1.0, 1.0, 1.0, 1.0, 0.7548828125, 0.99853515625, 1.8477439880371094e-06, 1.0, 0.99609375, 0.77734375, 0.1500244140625, 0.06854248046875, 0.99853515625, 1.0, 0.8173828125, 1.0, 0.79833984375, 1.0, 1.0, 0.9951171875, 0.98486328125, 1.0, 0.99267578125, 0.96337890625, 0.97607421875, 0.83349609375, 0.990234375, 0.99951171875, 1.0, 0.99951171875, 1.0, 0.99951171875, 0.9921875, 0.99609375, 0.47265625, 0.998046875, 0.64404296875, 0.99658203125, 1.0, 1.0, 1.0, 0.9921875, 1.0, 0.9912109375, 0.998046875, 1.0, 1.0, 1.0, 0.99951171875, 1.0, 1.0, 1.0, 0.9990234375, 0.99951171875, 1.0, 0.9638671875, 0.99365234375, 0.9794921875, 1.0, 1.0, 0.99462890625, 0.9951171875, 0.98681640625, 1.0, 1.0, 1.0, 1.0, 0.9677734375, 0.91748046875, 0.99609375, 1.0, 1.0, 1.0, 0.94677734375, 0.9755859375, 0.98583984375, 0.0014104843139648438, 0.9951171875, 0.43017578125, 1.0, 1.0, 0.99658203125, 0.9423828125, 0.99951171875, 1.0, 0.55810546875, 1.0, 0.99755859375, 0.07586669921875, 1.0, 1.0, 0.80078125, 1.0, 1.0, 0.9150390625, 0.94970703125, 0.67236328125, 1.0, 1.0, 0.99853515625, 0.83544921875, 1.0, 0.99658203125, 0.9990234375, 0.58154296875, 0.615234375, 0.810546875, 0.72802734375, 0.67236328125, 0.994140625, 0.994140625, 0.962890625, 1.0, 0.96484375, 1.0, 0.304931640625, 0.1871337890625, 0.25244140625, 0.00012886524200439453, 1.2516975402832031e-06, 0.998046875, 0.99365234375, 0.99951171875, 0.99951171875, 1.0, 0.998046875, 1.0, 1.0, 0.71533203125, 1.0, 0.98095703125, 0.1268310546875, 0.93505859375, 1.0, 0.9990234375, 0.91943359375, 0.59619140625, 0.79833984375, 0.67236328125, 0.8154296875, 0.9677734375, 1.0, 1.0, 1.0, 0.99853515625, 0.9814453125, 0.9765625, 0.8017578125, 0.91357421875, 0.93359375, 0.970703125, 0.0071563720703125, 0.90478515625, 2.9206275939941406e-06, 1.0, 1.0, 0.994140625, 0.73095703125, 0.67236328125, 0.437744140625, 1.0, 0.99951171875, 1.0, 1.0, 1.0, 1.0, 0.99365234375, 0.59619140625, 0.9990234375, 0.138427734375, 0.175537109375, 0.013427734375, 0.7216796875, 0.96484375, 0.98291015625, 1.0, 0.658203125, 1.0, 0.0953369140625, 0.33447265625, 0.642578125, 1.0, 1.0, 1.0, 0.982421875, 0.92724609375, 0.708984375, 0.85693359375, 0.841796875, 0.6513671875, 0.6494140625, 0.744140625, 0.87890625, 0.8671875, 1.0, 1.0, 1.0, 0.994140625, 1.0, 0.07666015625, 0.091064453125, 0.23583984375, 0.751953125, 0.7880859375, 0.98486328125, 0.83349609375, 0.53125, 0.99951171875, 0.95068359375, 0.9443359375, 0.6318359375, 1.0, 0.9453125, 1.0, 0.900390625, 0.96044921875, 0.998046875, 0.18359375, 0.42431640625, 0.1895751953125, 0.5888671875, 0.69287109375, 0.62255859375, 0.55810546875, 0.25390625, 0.7373046875, 1.0, 1.0, 1.0, 0.414794921875, 0.9111328125, 0.80810546875, 0.219970703125, 0.132080078125, 0.441650390625, 1.0, 1.0, 1.0, 0.81982421875, 0.98876953125, 0.9990234375, 1.0, 1.0, 1.0, 1.0, 0.99951171875, 0.99951171875, 1.0, 1.0, 1.0 ], "eval_runtime": 22.9165, "eval_samples_per_second": 32.728, "eval_steps_per_second": 1.047 }