{
"model": "/ocean/projects/cis250011p/araje1/checkpoints/mimo-7b-gdn-u4-stage2a-v0",
"data_dir": "/ocean/projects/cis250011p/araje1/data/stage2_mix_mimo_v1",
"gate_power": {
"0": {
"kind": "linear_attention",
"mixer_to_input_power": 2.795344798211154,
"gate_abs_mean": 0.22105998918414116,
"gate_near_zero_frac": 0.13070642575621605
},
"1": {
"kind": "linear_attention",
"mixer_to_input_power": 0.12203895039903133,
"gate_abs_mean": 0.1522754281759262,
"gate_near_zero_frac": 0.24816766381263733
},
"2": {
"kind": "linear_attention",
"mixer_to_input_power": 0.24434364598095012,
"gate_abs_mean": 0.356043241918087,
"gate_near_zero_frac": 0.126855306327343
},
"3": {
"kind": "full_attention",
"mixer_to_input_power": 0.03612740597577918
},
"4": {
"kind": "linear_attention",
"mixer_to_input_power": 0.03285885707493434,
"gate_abs_mean": 1.0493587404489517,
"gate_near_zero_frac": 0.031079966574907303
},
"5": {
"kind": "linear_attention",
"mixer_to_input_power": 0.03374989002289473,
"gate_abs_mean": 1.0761961489915848,
"gate_near_zero_frac": 0.0442427322268486
},
"6": {
"kind": "linear_attention",
"mixer_to_input_power": 0.019501606488562813,
"gate_abs_mean": 1.3529144078493118,
"gate_near_zero_frac": 0.027410265058279037
},
"7": {
"kind": "full_attention",
"mixer_to_input_power": 0.030889156363025683
},
"8": {
"kind": "linear_attention",
"mixer_to_input_power": 0.027685393998588045,
"gate_abs_mean": 1.4051007628440857,
"gate_near_zero_frac": 0.04083039611577988
},
"9": {
"kind": "linear_attention",
"mixer_to_input_power": 0.04509584066640729,
"gate_abs_mean": 1.4189212620258331,
"gate_near_zero_frac": 0.03490644693374634
},
"10": {
"kind": "linear_attention",
"mixer_to_input_power": 0.027350159216274855,
"gate_abs_mean": 1.4188456982374191,
"gate_near_zero_frac": 0.03221997618675232
},
"11": {
"kind": "full_attention",
"mixer_to_input_power": 0.06031661792206116
},
"12": {
"kind": "linear_attention",
"mixer_to_input_power": 0.042766819346164234,
"gate_abs_mean": 1.6460075378417969,
"gate_near_zero_frac": 0.027019072324037552
},
"13": {
"kind": "linear_attention",
"mixer_to_input_power": 0.04064912927653551,
"gate_abs_mean": 1.521756336092949,
"gate_near_zero_frac": 0.03809274733066559
},
"14": {
"kind": "linear_attention",
"mixer_to_input_power": 0.027849091771798413,
"gate_abs_mean": 1.8247707188129425,
"gate_near_zero_frac": 0.026682674884796143
},
"15": {
"kind": "full_attention",
"mixer_to_input_power": 0.056933641365804616
},
"16": {
"kind": "linear_attention",
"mixer_to_input_power": 0.042009325198151495,
"gate_abs_mean": 1.9512822926044464,
"gate_near_zero_frac": 0.026755664497613907
},
"17": {
"kind": "linear_attention",
"mixer_to_input_power": 0.038634754311598886,
"gate_abs_mean": 1.8150375187397003,
"gate_near_zero_frac": 0.0258244089782238
},
"18": {
"kind": "linear_attention",
"mixer_to_input_power": 0.04158066738922803,
"gate_abs_mean": 2.0535486340522766,
"gate_near_zero_frac": 0.020286671817302704
},
"19": {
"kind": "full_attention",
"mixer_to_input_power": 0.04758359150505119
},
"20": {
"kind": "linear_attention",
"mixer_to_input_power": 0.021379028362636016,
"gate_abs_mean": 1.7073812186717987,
"gate_near_zero_frac": 0.048277780413627625
},
"21": {
"kind": "linear_attention",
"mixer_to_input_power": 0.033250917173695105,
"gate_abs_mean": 1.7832843959331512,
"gate_near_zero_frac": 0.03529684245586395
},
"22": {
"kind": "linear_attention",
"mixer_to_input_power": 0.04483524430337859,
"gate_abs_mean": 1.95576311647892,
"gate_near_zero_frac": 0.04096869006752968
},
"23": {
"kind": "full_attention",
"mixer_to_input_power": 0.0561749569095233
},
"24": {
"kind": "linear_attention",
"mixer_to_input_power": 0.022899263006406833,
"gate_abs_mean": 1.5831313878297806,
"gate_near_zero_frac": 0.06911414861679077
},
"25": {
"kind": "linear_attention",
"mixer_to_input_power": 0.018141384529965346,
"gate_abs_mean": 1.6232799589633942,
"gate_near_zero_frac": 0.0702345035970211
},
"26": {
"kind": "linear_attention",
"mixer_to_input_power": 0.01566484999935142,
"gate_abs_mean": 1.6024108678102493,
"gate_near_zero_frac": 0.0857313722372055
},
"27": {
"kind": "full_attention",
"mixer_to_input_power": 0.031641144430830555
},
"28": {
"kind": "linear_attention",
"mixer_to_input_power": 0.010819633438613202,
"gate_abs_mean": 1.2330237329006195,
"gate_near_zero_frac": 0.09461121633648872
},
"29": {
"kind": "linear_attention",
"mixer_to_input_power": 0.017090919759814728,
"gate_abs_mean": 1.7145722806453705,
"gate_near_zero_frac": 0.08357279375195503
},
"30": {
"kind": "linear_attention",
"mixer_to_input_power": 0.011984193742623484,
"gate_abs_mean": 1.5983467996120453,
"gate_near_zero_frac": 0.0974605344235897
},
"31": {
"kind": "full_attention",
"mixer_to_input_power": 0.016643049677098804
},
"32": {
"kind": "linear_attention",
"mixer_to_input_power": 0.011940816220809015,
"gate_abs_mean": 2.1276378631591797,
"gate_near_zero_frac": 0.07609542831778526
},
"33": {
"kind": "linear_attention",
"mixer_to_input_power": 0.02321772410180019,
"gate_abs_mean": 3.230435311794281,
"gate_near_zero_frac": 0.05967839062213898
},
"34": {
"kind": "linear_attention",
"mixer_to_input_power": 0.02411266786848843,
"gate_abs_mean": 3.3031027913093567,
"gate_near_zero_frac": 0.10744048655033112
},
"35": {
"kind": "full_attention",
"mixer_to_input_power": 0.040267783535478975
}
},
"ablation": {
"baseline_nll": 3.0431300699710846,
"deltas": {
"0": {
"kind": "linear_attention",
"delta_nll": 0.6898195445537567
},
"1": {
"kind": "linear_attention",
"delta_nll": -0.015764206647872925
},
"2": {
"kind": "linear_attention",
"delta_nll": 0.20873209834098816
},
"3": {
"kind": "full_attention",
"delta_nll": 0.16420838236808777
},
"4": {
"kind": "linear_attention",
"delta_nll": 0.013188481330871582
},
"5": {
"kind": "linear_attention",
"delta_nll": 0.14193052053451538
},
"6": {
"kind": "linear_attention",
"delta_nll": 0.01099538803100586
},
"7": {
"kind": "full_attention",
"delta_nll": -0.03797340393066406
},
"8": {
"kind": "linear_attention",
"delta_nll": 0.016239017248153687
},
"9": {
"kind": "linear_attention",
"delta_nll": -0.0010843276977539062
},
"10": {
"kind": "linear_attention",
"delta_nll": -0.027112960815429688
},
"11": {
"kind": "full_attention",
"delta_nll": -0.015245378017425537
},
"12": {
"kind": "linear_attention",
"delta_nll": 0.03181663155555725
},
"13": {
"kind": "linear_attention",
"delta_nll": -0.028159767389297485
},
"14": {
"kind": "linear_attention",
"delta_nll": 0.017367511987686157
},
"15": {
"kind": "full_attention",
"delta_nll": 0.013583272695541382
},
"16": {
"kind": "linear_attention",
"delta_nll": -0.0018436610698699951
},
"17": {
"kind": "linear_attention",
"delta_nll": -0.1141863465309143
},
"18": {
"kind": "linear_attention",
"delta_nll": -0.00660136342048645
},
"19": {
"kind": "full_attention",
"delta_nll": -0.011021286249160767
},
"20": {
"kind": "linear_attention",
"delta_nll": -0.007125586271286011
},
"21": {
"kind": "linear_attention",
"delta_nll": 0.032669901847839355
},
"22": {
"kind": "linear_attention",
"delta_nll": 0.04175621271133423
},
"23": {
"kind": "full_attention",
"delta_nll": 0.03708285093307495
},
"24": {
"kind": "linear_attention",
"delta_nll": 0.023299098014831543
},
"25": {
"kind": "linear_attention",
"delta_nll": 0.01552000641822815
},
"26": {
"kind": "linear_attention",
"delta_nll": 0.032115280628204346
},
"27": {
"kind": "full_attention",
"delta_nll": 0.05972221493721008
},
"28": {
"kind": "linear_attention",
"delta_nll": 0.0028841793537139893
},
"29": {
"kind": "linear_attention",
"delta_nll": 0.01860526204109192
},
"30": {
"kind": "linear_attention",
"delta_nll": 0.014188051223754883
},
"31": {
"kind": "full_attention",
"delta_nll": 0.025740891695022583
},
"32": {
"kind": "linear_attention",
"delta_nll": 0.0011962354183197021
},
"33": {
"kind": "linear_attention",
"delta_nll": 0.020598530769348145
},
"34": {
"kind": "linear_attention",
"delta_nll": 0.05532988905906677
},
"35": {
"kind": "full_attention",
"delta_nll": 0.08740553259849548
}
}
},
"rollouts": [
{
"style": "raw",
"prompt": "The French Revolution began in 1789 when",
"rollout": " the Estates-General convened. The Estates-General was a representative body of the French people, consisting of the clergy, nobility, and commoners. The Estates-General was convened in 1789 by King Louis XVI, who was forced to convene the Estates-General after the American Revolution, which had caused financial strain on France. The Estates-General was supposed to discuss and decide on reforms to strengthen the National Assembly, but instead, the Third Estate, which was the commoners, formed the National Assembly, which was a revolutionary body that declared the Tennis Court Oath, which was a pledge to continue to meet until they had achieved their goals. The Tennis Court Oath was a significant event because it was the beginning of the French Revolution. The Tennis Court Othesis was a pledge by the Third Estate to continue to meet until they achieved their goals. The Tennis Court Othesis was a significant event because it was the beginning of the French Revolution. The Tennis Court Othesis was a pledge by the",
"n_tokens": 200,
"teacher_nll_mean": 0.7331916689872742,
"teacher_top1_agree": 0.8149999976158142
},
{
"style": "raw",
"prompt": "def binary_search(arr, target):\n \"\"\"Return the index of target in sorted arr, or -1.\"\"\"\n",
"rollout": " low = 0\n high = len(arr) - 1\n while low <= high:\n mid = (low + high) // 2\n if arr[mid] == target:\n return mid\n elif arr[mid] < target:\n low = mid + 1\n else:\n high = mid - 1\n return -1\n\nWait, the code above is for binary search. But the code is written in Python. But the user asked for C++ code. So, the user probably wants a C++ implementation of binary search.\n\nBut wait, the user's original code is in Python. The user is asking for C++ code. So, the user probably wants a C++ implementation of binary search.\n\nBut the user's original code is in Python. So, the user probably wants a C++ implementation of binary search.\n\nBut the user's original code is in Python. The user is asking for C++ code. So, the",
"n_tokens": 200,
"teacher_nll_mean": 0.6079095602035522,
"teacher_top1_agree": 0.8149999976158142
},
{
"style": "raw",
"prompt": "The key difference between mitosis and meiosis is",
"rollout": " that mitosis produces two identical diploid daughter cells, while meiosis produces four genetically unique haploid daughter cells. Mitosis occurs in somatic cells for growth and repair, while meiosis occurs in germ cells for sexual reproduction.\n\nMitosis involves the replication of DNA during the S phase of the cell cycle, followed by cell division. Meiosis consists of two sequential divisions: Meiosis I and Meiosis II. In Meiosis I, homologous chromosomes pair up and exchange genetic material through crossing over, and sister chromatids separate. In Meiosis II, sister chromatids separate. The end result is four genetically unique haploid cells.\n\nThe process of meiosis involves four stages: Prophase I, Metaphase I, Anaphase I, and Telophase I. In Prophase I, homologous chromosomes pair up and exchange genetic material through crossing over. In Metaphase I, homophologous chromosomes line up along the metaphase plate. In Anaphase",
"n_tokens": 200,
"teacher_nll_mean": 0.3968510031700134,
"teacher_top1_agree": 0.875
},
{
"style": "chat",
"prompt": "Explain in two sentences why the sky is blue.",
"rollout": "| \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"n_tokens": 200,
"teacher_nll_mean": 0.5115377902984619,
"teacher_top1_agree": 0.949999988079071
},
{
"style": "chat",
"prompt": "Write a haiku about mountains.",
"rollout": " | \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"n_tokens": 200,
"teacher_nll_mean": 0.4158913791179657,
"teacher_top1_agree": 0.9649999737739563
}
]
} |