Upload dpo_metrics.jsonl with huggingface_hub
Browse files- dpo_metrics.jsonl +74 -0
dpo_metrics.jsonl
CHANGED
|
@@ -72,3 +72,77 @@
|
|
| 72 |
{"timestamp": 1787715288.8790207, "elapsed_hours": 0.08355418761571248, "event": "dpo_step", "step": 680, "loss": 0.6966081142425538, "pref_accuracy": 0.48, "chosen_reward": -0.06880950927734375, "rejected_reward": -0.03595123440027237, "lr": 1.972340638499592e-06, "tokens_per_sec": 152988.4497760965, "vram_gb": 4.3943352699279785}
|
| 73 |
{"timestamp": 1787715292.4914114, "elapsed_hours": 0.08455762942632039, "event": "dpo_step", "step": 690, "loss": 0.6973476332426071, "pref_accuracy": 0.51, "chosen_reward": 0.03323822095990181, "rejected_reward": 0.018894575536251068, "lr": 1.971636329899089e-06, "tokens_per_sec": 153336.70554277452, "vram_gb": 3.7759509086608887}
|
| 74 |
{"timestamp": 1787715296.549209, "elapsed_hours": 0.08568479544586606, "event": "dpo_step", "step": 700, "loss": 0.7031182646751404, "pref_accuracy": 0.5, "chosen_reward": -0.13089600205421448, "rejected_reward": -0.17291259765625, "lr": 1.970923310049664e-06, "tokens_per_sec": 153447.6330623252, "vram_gb": 4.955141067504883}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
{"timestamp": 1787715288.8790207, "elapsed_hours": 0.08355418761571248, "event": "dpo_step", "step": 680, "loss": 0.6966081142425538, "pref_accuracy": 0.48, "chosen_reward": -0.06880950927734375, "rejected_reward": -0.03595123440027237, "lr": 1.972340638499592e-06, "tokens_per_sec": 152988.4497760965, "vram_gb": 4.3943352699279785}
|
| 73 |
{"timestamp": 1787715292.4914114, "elapsed_hours": 0.08455762942632039, "event": "dpo_step", "step": 690, "loss": 0.6973476332426071, "pref_accuracy": 0.51, "chosen_reward": 0.03323822095990181, "rejected_reward": 0.018894575536251068, "lr": 1.971636329899089e-06, "tokens_per_sec": 153336.70554277452, "vram_gb": 3.7759509086608887}
|
| 74 |
{"timestamp": 1787715296.549209, "elapsed_hours": 0.08568479544586606, "event": "dpo_step", "step": 700, "loss": 0.7031182646751404, "pref_accuracy": 0.5, "chosen_reward": -0.13089600205421448, "rejected_reward": -0.17291259765625, "lr": 1.970923310049664e-06, "tokens_per_sec": 153447.6330623252, "vram_gb": 4.955141067504883}
|
| 75 |
+
{"timestamp": 1787715300.7219472, "elapsed_hours": 0.08684388942188687, "event": "dpo_step", "step": 710, "loss": 0.7056275296211243, "pref_accuracy": 0.45, "chosen_reward": 0.01327819749712944, "rejected_reward": 0.1604301482439041, "lr": 1.9702015860773335e-06, "tokens_per_sec": 153497.2894678143, "vram_gb": 4.9622626304626465}
|
| 76 |
+
{"timestamp": 1787715305.394714, "elapsed_hours": 0.08814188023408254, "event": "dpo_step", "step": 720, "loss": 0.7122172939777375, "pref_accuracy": 0.44, "chosen_reward": -0.0023681651800870895, "rejected_reward": -0.16202391684055328, "lr": 1.96873205470289e-06, "tokens_per_sec": 153296.19328020373, "vram_gb": 4.5285258293151855}
|
| 77 |
+
{"timestamp": 1787715308.3610969, "elapsed_hours": 0.08896587550640106, "event": "dpo_step", "step": 730, "loss": 0.7088728046417236, "pref_accuracy": 0.47, "chosen_reward": 0.1673683226108551, "rejected_reward": -0.00890503078699112, "lr": 1.9679842619874685e-06, "tokens_per_sec": 153941.75956765475, "vram_gb": 3.9603891372680664}
|
| 78 |
+
{"timestamp": 1787715311.9946914, "elapsed_hours": 0.08997520718309615, "event": "dpo_step", "step": 740, "loss": 0.7295868539810181, "pref_accuracy": 0.38, "chosen_reward": -0.21967774629592896, "rejected_reward": -0.06901855766773224, "lr": 1.9672277945223756e-06, "tokens_per_sec": 154247.0996263668, "vram_gb": 4.956125259399414}
|
| 79 |
+
{"timestamp": 1787715315.051028, "elapsed_hours": 0.09082418964968787, "event": "dpo_step", "step": 750, "loss": 0.733932477235794, "pref_accuracy": 0.35, "chosen_reward": -0.14458924531936646, "rejected_reward": 0.07909240573644638, "lr": 1.9664626598678487e-06, "tokens_per_sec": 154826.46949158362, "vram_gb": 4.2895121574401855}
|
| 80 |
+
{"timestamp": 1787715318.8567133, "elapsed_hours": 0.09188132438394758, "event": "dpo_step", "step": 760, "loss": 0.7281871855258941, "pref_accuracy": 0.4, "chosen_reward": 0.08825378865003586, "rejected_reward": 0.028540801256895065, "lr": 1.964906419664462e-06, "tokens_per_sec": 155032.32217558997, "vram_gb": 3.451991081237793}
|
| 81 |
+
{"timestamp": 1787715323.694388, "elapsed_hours": 0.09322512295511033, "event": "dpo_step", "step": 770, "loss": 0.7305298638343811, "pref_accuracy": 0.41, "chosen_reward": -0.019329838454723358, "rejected_reward": -0.17604294419288635, "lr": 1.9641153296688735e-06, "tokens_per_sec": 154742.16917139592, "vram_gb": 4.067758083343506}
|
| 82 |
+
{"timestamp": 1787715326.817198, "elapsed_hours": 0.09409257021215227, "event": "dpo_step", "step": 780, "loss": 0.7203198516368866, "pref_accuracy": 0.45, "chosen_reward": 0.171295166015625, "rejected_reward": -0.19083252549171448, "lr": 1.9633156035902357e-06, "tokens_per_sec": 155264.96534860664, "vram_gb": 4.937917232513428}
|
| 83 |
+
{"timestamp": 1787715330.6951368, "elapsed_hours": 0.09516977535353767, "event": "dpo_step", "step": 790, "loss": 0.7126754665374756, "pref_accuracy": 0.49, "chosen_reward": -0.05547638237476349, "rejected_reward": 0.24145430326461792, "lr": 1.9625072494211175e-06, "tokens_per_sec": 155424.85257226176, "vram_gb": 4.771301746368408}
|
| 84 |
+
{"timestamp": 1787715334.4157052, "elapsed_hours": 0.09620326658089956, "event": "dpo_step", "step": 800, "loss": 0.707347446680069, "pref_accuracy": 0.53, "chosen_reward": -0.12669678032398224, "rejected_reward": 0.06192474439740181, "lr": 1.9608646892127834e-06, "tokens_per_sec": 155653.68803714204, "vram_gb": 3.490973472595215}
|
| 85 |
+
{"timestamp": 1787715337.682028, "elapsed_hours": 0.0971105784840054, "event": "sample", "step": 800, "sample_text": "Here is a Python function that returns the nth Fibonacci number:\n\n```python\ndef fibonacci(n):\n if n == 0:\n return 0\n else:\n return fibonacci(n-1) + fibonacci(n-2)\n\nn = int(input(\"Enter the value of n: \"))\nprint(fibonacci(n))\n```\n\nThis function first checks if the input is a positive integer. If it is, the function returns 0 because there are no multiples of 0 in the input. If the input is a negative integer,"}
|
| 86 |
+
{"timestamp": 1787715341.6846611, "elapsed_hours": 0.09822242107656266, "event": "dpo_step", "step": 810, "loss": 0.713603800535202, "pref_accuracy": 0.51, "chosen_reward": 0.046862032264471054, "rejected_reward": 0.005551147740334272, "lr": 1.960030499589531e-06, "tokens_per_sec": 154270.1371139455, "vram_gb": 3.7815661430358887}
|
| 87 |
+
{"timestamp": 1787715345.0507615, "elapsed_hours": 0.09915744887457953, "event": "dpo_step", "step": 820, "loss": 0.7127104151248932, "pref_accuracy": 0.47, "chosen_reward": 0.001361846923828125, "rejected_reward": 0.02308960072696209, "lr": 1.9591877147075634e-06, "tokens_per_sec": 154661.74759766835, "vram_gb": 3.7267465591430664}
|
| 88 |
+
{"timestamp": 1787715348.0038965, "elapsed_hours": 0.09997776428858439, "event": "dpo_step", "step": 830, "loss": 0.7208830165863037, "pref_accuracy": 0.42, "chosen_reward": 0.006979372352361679, "rejected_reward": -0.1441650390625, "lr": 1.958336342989783e-06, "tokens_per_sec": 155228.58392313778, "vram_gb": 4.060384273529053}
|
| 89 |
+
{"timestamp": 1787715352.3057337, "elapsed_hours": 0.10117271893554264, "event": "dpo_step", "step": 840, "loss": 0.7123148548603058, "pref_accuracy": 0.44, "chosen_reward": 0.14483031630516052, "rejected_reward": -0.06658020615577698, "lr": 1.956607873167405e-06, "tokens_per_sec": 155193.58681600698, "vram_gb": 4.5285258293151855}
|
| 90 |
+
{"timestamp": 1787715355.2736778, "elapsed_hours": 0.10199714793099297, "event": "dpo_step", "step": 850, "loss": 0.7189644658565522, "pref_accuracy": 0.4, "chosen_reward": 0.185760498046875, "rejected_reward": 0.18185652792453766, "lr": 1.9557307923373636e-06, "tokens_per_sec": 155738.07546852864, "vram_gb": 4.222131252288818}
|
| 91 |
+
{"timestamp": 1787715358.8250883, "elapsed_hours": 0.10298365076382955, "event": "dpo_step", "step": 860, "loss": 0.7035667681694031, "pref_accuracy": 0.47, "chosen_reward": 0.21843568980693817, "rejected_reward": -0.21685791015625, "lr": 1.9548451592204496e-06, "tokens_per_sec": 156021.17378027408, "vram_gb": 4.956125259399414}
|
| 92 |
+
{"timestamp": 1787715361.7234776, "elapsed_hours": 0.10378875897990333, "event": "dpo_step", "step": 870, "loss": 0.6999275600910186, "pref_accuracy": 0.51, "chosen_reward": 0.08061523735523224, "rejected_reward": 0.0011230465024709702, "lr": 1.953950982667798e-06, "tokens_per_sec": 156579.0679648296, "vram_gb": 4.956369400024414}
|
| 93 |
+
{"timestamp": 1787715366.5049906, "elapsed_hours": 0.10511695702870687, "event": "dpo_step", "step": 880, "loss": 0.6870066291093826, "pref_accuracy": 0.55, "chosen_reward": 0.21968384087085724, "rejected_reward": 0.012339785695075989, "lr": 1.9521370350866516e-06, "tokens_per_sec": 156326.09124138433, "vram_gb": 4.5285258293151855}
|
| 94 |
+
{"timestamp": 1787715371.0236669, "elapsed_hours": 0.10637214488453335, "event": "dpo_step", "step": 890, "loss": 0.6940598636865616, "pref_accuracy": 0.53, "chosen_reward": 0.20348358154296875, "rejected_reward": 0.029119491577148438, "lr": 1.951217282186989e-06, "tokens_per_sec": 156189.46565563415, "vram_gb": 4.877913475036621}
|
| 95 |
+
{"timestamp": 1787715374.4967847, "elapsed_hours": 0.10733689970440334, "event": "dpo_step", "step": 900, "loss": 0.6821020025014878, "pref_accuracy": 0.59, "chosen_reward": -0.2681030333042145, "rejected_reward": -0.2462158203125, "lr": 1.9502890221090733e-06, "tokens_per_sec": 156488.98456192075, "vram_gb": 4.956369400024414}
|
| 96 |
+
{"timestamp": 1787715376.9626007, "elapsed_hours": 0.1080218486653434, "event": "dpo_step", "step": 910, "loss": 0.6886112540960312, "pref_accuracy": 0.57, "chosen_reward": 0.024883270263671875, "rejected_reward": 0.007684327661991119, "lr": 1.9493522641300564e-06, "tokens_per_sec": 157199.35062130782, "vram_gb": 3.929718017578125}
|
| 97 |
+
{"timestamp": 1787715381.3367708, "elapsed_hours": 0.10923689590560065, "event": "dpo_step", "step": 920, "loss": 0.6867042571306229, "pref_accuracy": 0.58, "chosen_reward": -0.21773681044578552, "rejected_reward": 0.042724609375, "lr": 1.9474532920018922e-06, "tokens_per_sec": 157115.26283437965, "vram_gb": 3.8590664863586426}
|
| 98 |
+
{"timestamp": 1787715385.2604947, "elapsed_hours": 0.11032681922117869, "event": "dpo_step", "step": 930, "loss": 0.6930978119373321, "pref_accuracy": 0.6, "chosen_reward": 0.0850982666015625, "rejected_reward": -0.1837310791015625, "lr": 1.9464910968313237e-06, "tokens_per_sec": 157215.58003088337, "vram_gb": 4.948031902313232}
|
| 99 |
+
{"timestamp": 1787715389.910171, "elapsed_hours": 0.11161839604377746, "event": "dpo_step", "step": 940, "loss": 0.715511931180954, "pref_accuracy": 0.55, "chosen_reward": 0.05459289625287056, "rejected_reward": 0.14537353813648224, "lr": 1.945520441716623e-06, "tokens_per_sec": 157022.77538505106, "vram_gb": 4.956125259399414}
|
| 100 |
+
{"timestamp": 1787715393.8631196, "elapsed_hours": 0.11271643724706437, "event": "dpo_step", "step": 950, "loss": 0.7291505962610245, "pref_accuracy": 0.52, "chosen_reward": -0.15678711235523224, "rejected_reward": 0.10839538276195526, "lr": 1.9445413363586462e-06, "tokens_per_sec": 157110.2246802519, "vram_gb": 3.8486552238464355}
|
| 101 |
+
{"timestamp": 1787715397.4922197, "elapsed_hours": 0.11372452060381572, "event": "dpo_step", "step": 960, "loss": 0.7239556902647019, "pref_accuracy": 0.51, "chosen_reward": 0.10059509426355362, "rejected_reward": -0.006008720491081476, "lr": 1.9425578141384546e-06, "tokens_per_sec": 157323.25313288404, "vram_gb": 4.5285258293151855}
|
| 102 |
+
{"timestamp": 1787715401.4912558, "elapsed_hours": 0.11483536389138964, "event": "dpo_step", "step": 970, "loss": 0.7290557664632797, "pref_accuracy": 0.49, "chosen_reward": -0.1147613525390625, "rejected_reward": 0.3401245176792145, "lr": 1.941553417099823e-06, "tokens_per_sec": 157388.16261117946, "vram_gb": 4.956308364868164}
|
| 103 |
+
{"timestamp": 1787715405.6069298, "elapsed_hours": 0.11597860674063365, "event": "dpo_step", "step": 980, "loss": 0.7426980370283127, "pref_accuracy": 0.44, "chosen_reward": -0.05803222954273224, "rejected_reward": -0.09595947712659836, "lr": 1.940540609464885e-06, "tokens_per_sec": 157406.796312458, "vram_gb": 4.952441692352295}
|
| 104 |
+
{"timestamp": 1787715409.7530744, "elapsed_hours": 0.1171303136481179, "event": "dpo_step", "step": 990, "loss": 0.7229859882593155, "pref_accuracy": 0.48, "chosen_reward": 0.0038269050419330597, "rejected_reward": -0.20434875786304474, "lr": 1.9395194013557735e-06, "tokens_per_sec": 157413.422681092, "vram_gb": 4.079492092132568}
|
| 105 |
+
{"timestamp": 1787715413.9957912, "elapsed_hours": 0.11830884602334764, "event": "dpo_step", "step": 1000, "loss": 0.7261935639381408, "pref_accuracy": 0.46, "chosen_reward": -0.2610740661621094, "rejected_reward": 0.17536696791648865, "lr": 1.937451824623242e-06, "tokens_per_sec": 157383.39695018347, "vram_gb": 4.5285258293151855}
|
| 106 |
+
{"timestamp": 1787715417.2068088, "elapsed_hours": 0.1192007953590817, "event": "sample", "step": 1000, "sample_text": "Here is a Python function that returns the nth Fibonacci number:\n\n```python\ndef fibonacci(n):\n if n <= 1:\n return n\n else:\n return fibonacci(n-1) + fibonacci(n-2)\n```\n\nExplanation:\n1. The function takes an integer `n` as input.\n2. It initializes an empty list `fibonacci` to store the Fibonacci numbers.\n3. It iterates `n` from 1 to `n-1` (inclusive) and checks if `"}
|
| 107 |
+
{"timestamp": 1787715427.399787, "elapsed_hours": 0.12203217817677392, "event": "dpo_step", "step": 1010, "loss": 0.736992963552475, "pref_accuracy": 0.41, "chosen_reward": -0.2077942043542862, "rejected_reward": 0.0750732496380806, "lr": 1.9364054766634578e-06, "tokens_per_sec": 154000.0542783811, "vram_gb": 4.935922145843506}
|
| 108 |
+
{"timestamp": 1787715431.3720748, "elapsed_hours": 0.12313559154669444, "event": "dpo_step", "step": 1020, "loss": 0.7202029633522034, "pref_accuracy": 0.43, "chosen_reward": 0.250396728515625, "rejected_reward": 0.0531768798828125, "lr": 1.9353507695565648e-06, "tokens_per_sec": 154100.62604465004, "vram_gb": 4.943937301635742}
|
| 109 |
+
{"timestamp": 1787715436.3337886, "elapsed_hours": 0.12451384524504344, "event": "dpo_step", "step": 1030, "loss": 0.7104087924957275, "pref_accuracy": 0.45, "chosen_reward": -0.10151519626379013, "rejected_reward": 0.1305694580078125, "lr": 1.9342877138434467e-06, "tokens_per_sec": 153851.64024760545, "vram_gb": 4.956308364868164}
|
| 110 |
+
{"timestamp": 1787715439.8552454, "elapsed_hours": 0.12549202779928842, "event": "dpo_step", "step": 1040, "loss": 0.7058577585220337, "pref_accuracy": 0.48, "chosen_reward": 0.11116944253444672, "rejected_reward": 0.12285766750574112, "lr": 1.9321365991791424e-06, "tokens_per_sec": 154108.47622041305, "vram_gb": 4.5285258293151855}
|
| 111 |
+
{"timestamp": 1787715443.6032443, "elapsed_hours": 0.1265331386195289, "event": "dpo_step", "step": 1050, "loss": 0.6916181647777557, "pref_accuracy": 0.53, "chosen_reward": 0.019124602898955345, "rejected_reward": -0.007781601510941982, "lr": 1.9310485617264816e-06, "tokens_per_sec": 154282.79940248636, "vram_gb": 4.064759731292725}
|
| 112 |
+
{"timestamp": 1787715447.7355347, "elapsed_hours": 0.12768099705378214, "event": "dpo_step", "step": 1060, "loss": 0.675290549993515, "pref_accuracy": 0.6, "chosen_reward": 0.02728271484375, "rejected_reward": 0.01706542819738388, "lr": 1.92995221866443e-06, "tokens_per_sec": 154322.38893742335, "vram_gb": 4.956033229827881}
|
| 113 |
+
{"timestamp": 1787715451.8730843, "elapsed_hours": 0.12883031639787887, "event": "dpo_step", "step": 1070, "loss": 0.6779828143119812, "pref_accuracy": 0.62, "chosen_reward": 0.04228973761200905, "rejected_reward": -0.07038193196058273, "lr": 1.928847580949985e-06, "tokens_per_sec": 154359.4555644303, "vram_gb": 4.213380336761475}
|
| 114 |
+
{"timestamp": 1787715456.0204566, "elapsed_hours": 0.12998236417770387, "event": "dpo_step", "step": 1080, "loss": 0.6793077564239502, "pref_accuracy": 0.62, "chosen_reward": 0.16329346597194672, "rejected_reward": -0.08740234375, "lr": 1.9266134658062868e-06, "tokens_per_sec": 154392.56389177951, "vram_gb": 4.5285258293151855}
|
| 115 |
+
{"timestamp": 1787715459.369876, "elapsed_hours": 0.13091275844309064, "event": "dpo_step", "step": 1090, "loss": 0.6804685151576996, "pref_accuracy": 0.59, "chosen_reward": -0.05195312947034836, "rejected_reward": -0.09776001423597336, "lr": 1.925484010705075e-06, "tokens_per_sec": 154691.9033066077, "vram_gb": 4.93966817855835}
|
| 116 |
+
{"timestamp": 1787715463.3070438, "elapsed_hours": 0.13200641618834602, "event": "dpo_step", "step": 1100, "loss": 0.699943186044693, "pref_accuracy": 0.53, "chosen_reward": -0.06141815334558487, "rejected_reward": 0.19184112548828125, "lr": 1.9243463056073333e-06, "tokens_per_sec": 154791.34670589535, "vram_gb": 4.955843925476074}
|
| 117 |
+
{"timestamp": 1787715467.364015, "elapsed_hours": 0.13313335273000929, "event": "dpo_step", "step": 1110, "loss": 0.6967700219154358, "pref_accuracy": 0.51, "chosen_reward": -0.09503479301929474, "rejected_reward": 0.02462158165872097, "lr": 1.9232003618834363e-06, "tokens_per_sec": 154849.62594499992, "vram_gb": 4.203103542327881}
|
| 118 |
+
{"timestamp": 1787715471.452695, "elapsed_hours": 0.13426909705003104, "event": "dpo_step", "step": 1120, "loss": 0.7101216411590576, "pref_accuracy": 0.47, "chosen_reward": 0.14584961533546448, "rejected_reward": 0.067657470703125, "lr": 1.9208838044502516e-06, "tokens_per_sec": 154896.5304998058, "vram_gb": 4.5285258293151855}
|
| 119 |
+
{"timestamp": 1787715475.836777, "elapsed_hours": 0.13548689769374, "event": "dpo_step", "step": 1130, "loss": 0.7128936219215393, "pref_accuracy": 0.44, "chosen_reward": 0.09666748344898224, "rejected_reward": 0.009101866744458675, "lr": 1.9197132138929464e-06, "tokens_per_sec": 154846.93697995885, "vram_gb": 3.9691672325134277}
|
| 120 |
+
{"timestamp": 1787715480.8291304, "elapsed_hours": 0.136873662604226, "event": "dpo_step", "step": 1140, "loss": 0.7088520109653473, "pref_accuracy": 0.49, "chosen_reward": -0.2283584624528885, "rejected_reward": 0.03844146803021431, "lr": 1.9185344310132184e-06, "tokens_per_sec": 154603.3963647102, "vram_gb": 4.956125259399414}
|
| 121 |
+
{"timestamp": 1787715485.4741285, "elapsed_hours": 0.13816393978065913, "event": "dpo_step", "step": 1150, "loss": 0.6888461434841155, "pref_accuracy": 0.55, "chosen_reward": 0.3318542540073395, "rejected_reward": 0.08058471977710724, "lr": 1.917347467591979e-06, "tokens_per_sec": 154474.73906323744, "vram_gb": 4.955942153930664}
|
| 122 |
+
{"timestamp": 1787715489.7339666, "elapsed_hours": 0.1393472280767229, "event": "dpo_step", "step": 1160, "loss": 0.7067936301231384, "pref_accuracy": 0.52, "chosen_reward": 0.24290771782398224, "rejected_reward": -0.04038086161017418, "lr": 1.914949046657284e-06, "tokens_per_sec": 154469.28465345054, "vram_gb": 4.484297275543213}
|
| 123 |
+
{"timestamp": 1787715494.132179, "elapsed_hours": 0.1405689537525177, "event": "dpo_step", "step": 1170, "loss": 0.7147906661033631, "pref_accuracy": 0.51, "chosen_reward": 0.23182372748851776, "rejected_reward": 0.01591797173023224, "lr": 1.9137376131139653e-06, "tokens_per_sec": 154420.91399147722, "vram_gb": 4.952402114868164}
|
| 124 |
+
{"timestamp": 1787715498.7007456, "elapsed_hours": 0.14183800008561875, "event": "dpo_step", "step": 1180, "loss": 0.7161052131652832, "pref_accuracy": 0.53, "chosen_reward": -0.2266792356967926, "rejected_reward": -0.17036743462085724, "lr": 1.912518046969169e-06, "tokens_per_sec": 154320.87389800692, "vram_gb": 4.956125259399414}
|
| 125 |
+
{"timestamp": 1787715503.4245875, "elapsed_hours": 0.1431501783265008, "event": "dpo_step", "step": 1190, "loss": 0.7149574673175811, "pref_accuracy": 0.49, "chosen_reward": 0.24003906548023224, "rejected_reward": 0.19692383706569672, "lr": 1.911290360411401e-06, "tokens_per_sec": 154175.32894951987, "vram_gb": 4.956308364868164}
|
| 126 |
+
{"timestamp": 1787715507.8070571, "elapsed_hours": 0.14436753107441797, "event": "dpo_step", "step": 1200, "loss": 0.6978575080633164, "pref_accuracy": 0.53, "chosen_reward": 0.05468139797449112, "rejected_reward": -0.22212524712085724, "lr": 1.9088106752166296e-06, "tokens_per_sec": 154135.5191754614, "vram_gb": 4.5285258293151855}
|
| 127 |
+
{"timestamp": 1787715511.1213348, "elapsed_hours": 0.14528816362222036, "event": "sample", "step": 1200, "sample_text": "Here is a Python function that returns the nth Fibonacci number:\n\n```python\ndef fibonacci(n):\n if n <= 1:\n return n\n else:\n return fibonacci(n-1)\n```\n\nThis function takes an integer `n` as input and returns the nth Fibonacci number. It first checks if `n` is equal to 1. If it is, it returns the nth Fibonacci number. If not, it returns the nth Fibonacci number.\n\nThe function uses a loop to iterate from 1 to `n-"}
|
| 128 |
+
{"timestamp": 1787715513.6699383, "elapsed_hours": 0.14599610924720763, "event": "dpo_step", "step": 1210, "loss": 0.6906495851278305, "pref_accuracy": 0.53, "chosen_reward": 0.17765046656131744, "rejected_reward": -0.000957489013671875, "lr": 1.9075587013619297e-06, "tokens_per_sec": 153654.3731250558, "vram_gb": 4.274075508117676}
|
| 129 |
+
{"timestamp": 1787715517.5968988, "elapsed_hours": 0.14708693153328367, "event": "dpo_step", "step": 1220, "loss": 0.6765544611215591, "pref_accuracy": 0.54, "chosen_reward": -0.01492233294993639, "rejected_reward": -0.0812530517578125, "lr": 1.9062986566586141e-06, "tokens_per_sec": 153754.29346368753, "vram_gb": 4.162967205047607}
|
| 130 |
+
{"timestamp": 1787715521.5870438, "elapsed_hours": 0.14819530520174237, "event": "dpo_step", "step": 1230, "loss": 0.6757642304897309, "pref_accuracy": 0.52, "chosen_reward": -0.10951537638902664, "rejected_reward": 0.20025329291820526, "lr": 1.9050305536997368e-06, "tokens_per_sec": 153834.17764413092, "vram_gb": 4.956623077392578}
|
| 131 |
+
{"timestamp": 1787715526.4154363, "elapsed_hours": 0.14953652527597217, "event": "dpo_step", "step": 1240, "loss": 0.6940316736698151, "pref_accuracy": 0.54, "chosen_reward": -0.22416077554225922, "rejected_reward": -0.042473986744880676, "lr": 1.9024702237900622e-06, "tokens_per_sec": 153668.8809496567, "vram_gb": 4.5285258293151855}
|
| 132 |
+
{"timestamp": 1787715530.2466578, "elapsed_hours": 0.1506007534927792, "event": "dpo_step", "step": 1250, "loss": 0.7050663775205612, "pref_accuracy": 0.51, "chosen_reward": -0.14139290153980255, "rejected_reward": -0.1225738525390625, "lr": 1.9011780224275405e-06, "tokens_per_sec": 153793.9941146574, "vram_gb": 4.955352306365967}
|
| 133 |
+
{"timestamp": 1787715534.1663845, "elapsed_hours": 0.15168956637382508, "event": "dpo_step", "step": 1260, "loss": 0.717123686671257, "pref_accuracy": 0.49, "chosen_reward": -0.02555541880428791, "rejected_reward": 0.01826782152056694, "lr": 1.8998778139857542e-06, "tokens_per_sec": 153891.84568379234, "vram_gb": 3.820162296295166}
|
| 134 |
+
{"timestamp": 1787715538.9051092, "elapsed_hours": 0.1530058789253235, "event": "dpo_step", "step": 1270, "loss": 0.7084300631284713, "pref_accuracy": 0.54, "chosen_reward": -0.13425293564796448, "rejected_reward": 0.021655261516571045, "lr": 1.8985696114591582e-06, "tokens_per_sec": 153755.35266986227, "vram_gb": 4.944307327270508}
|
| 135 |
+
{"timestamp": 1787715543.133623, "elapsed_hours": 0.15418046593666077, "event": "dpo_step", "step": 1280, "loss": 0.7077883052825927, "pref_accuracy": 0.54, "chosen_reward": -0.1473388671875, "rejected_reward": 0.15691527724266052, "lr": 1.8959292765286983e-06, "tokens_per_sec": 153764.8826455065, "vram_gb": 4.5285258293151855}
|
| 136 |
+
{"timestamp": 1787715547.9490025, "elapsed_hours": 0.1555180714527766, "event": "dpo_step", "step": 1290, "loss": 0.6983676552772522, "pref_accuracy": 0.54, "chosen_reward": 0.05641479045152664, "rejected_reward": 0.20299072563648224, "lr": 1.8945971705126912e-06, "tokens_per_sec": 153610.30167758014, "vram_gb": 4.956247329711914}
|
| 137 |
+
{"timestamp": 1787715551.6735263, "elapsed_hours": 0.15655266125996908, "event": "dpo_step", "step": 1300, "loss": 0.7005690622329712, "pref_accuracy": 0.53, "chosen_reward": -0.029143525287508965, "rejected_reward": -0.01912079006433487, "lr": 1.8932571231873249e-06, "tokens_per_sec": 153760.52239395856, "vram_gb": 3.637845039367676}
|
| 138 |
+
{"timestamp": 1787715556.3045833, "elapsed_hours": 0.15783906612131332, "event": "dpo_step", "step": 1310, "loss": 0.6963102912902832, "pref_accuracy": 0.56, "chosen_reward": 0.009669497609138489, "rejected_reward": -0.10969695448875427, "lr": 1.8919091479452092e-06, "tokens_per_sec": 153659.02942296152, "vram_gb": 4.956575393676758}
|
| 139 |
+
{"timestamp": 1787715558.8342092, "elapsed_hours": 0.15854173991415235, "event": "dpo_step", "step": 1320, "loss": 0.7068523240089416, "pref_accuracy": 0.52, "chosen_reward": 0.06879882514476776, "rejected_reward": -0.05594482272863388, "lr": 1.8891894676772027e-06, "tokens_per_sec": 154134.13159003985, "vram_gb": 4.5285258293151855}
|
| 140 |
+
{"timestamp": 1787715562.9496949, "elapsed_hours": 0.1596849305099911, "event": "dpo_step", "step": 1330, "loss": 0.7012220132350921, "pref_accuracy": 0.57, "chosen_reward": -0.0077125560492277145, "rejected_reward": -0.004755403846502304, "lr": 1.887817789832156e-06, "tokens_per_sec": 154171.34427047728, "vram_gb": 4.295814037322998}
|
| 141 |
+
{"timestamp": 1787715566.648795, "elapsed_hours": 0.16071245816018848, "event": "dpo_step", "step": 1340, "loss": 0.6958359360694886, "pref_accuracy": 0.53, "chosen_reward": -0.12526550889015198, "rejected_reward": -0.04405365139245987, "lr": 1.8864382384317785e-06, "tokens_per_sec": 154320.805298672, "vram_gb": 4.93937349319458}
|
| 142 |
+
{"timestamp": 1787715571.7142992, "elapsed_hours": 0.16211954275767007, "event": "dpo_step", "step": 1350, "loss": 0.6921820938587189, "pref_accuracy": 0.53, "chosen_reward": 0.07501373440027237, "rejected_reward": 0.19433365762233734, "lr": 1.885050827263489e-06, "tokens_per_sec": 154100.73655757122, "vram_gb": 4.043951034545898}
|
| 143 |
+
{"timestamp": 1787715575.66857, "elapsed_hours": 0.16321795125802357, "event": "dpo_step", "step": 1360, "loss": 0.684705970287323, "pref_accuracy": 0.53, "chosen_reward": 0.25602418184280396, "rejected_reward": -0.10745621472597122, "lr": 1.8822524811654735e-06, "tokens_per_sec": 154180.30623872372, "vram_gb": 4.098963260650635}
|
| 144 |
+
{"timestamp": 1787715579.943938, "elapsed_hours": 0.16440555347336663, "event": "dpo_step", "step": 1370, "loss": 0.6684310102462768, "pref_accuracy": 0.57, "chosen_reward": 0.02247009240090847, "rejected_reward": 0.02773742564022541, "lr": 1.880841574202788e-06, "tokens_per_sec": 154173.7513596248, "vram_gb": 4.956308364868164}
|
| 145 |
+
{"timestamp": 1787715584.0258112, "elapsed_hours": 0.16553940726651087, "event": "dpo_step", "step": 1380, "loss": 0.6620006465911865, "pref_accuracy": 0.59, "chosen_reward": -0.19496460258960724, "rejected_reward": 0.02821197360754013, "lr": 1.879422863405995e-06, "tokens_per_sec": 154218.18369967438, "vram_gb": 4.947631359100342}
|
| 146 |
+
{"timestamp": 1787715589.4235928, "elapsed_hours": 0.16703879098097482, "event": "dpo_step", "step": 1390, "loss": 0.6596014487743378, "pref_accuracy": 0.63, "chosen_reward": 0.010083010420203209, "rejected_reward": 0.14625243842601776, "lr": 1.877996362953877e-06, "tokens_per_sec": 153918.9682018877, "vram_gb": 4.956308364868164}
|
| 147 |
+
{"timestamp": 1787715592.8423104, "elapsed_hours": 0.1679884346988466, "event": "dpo_step", "step": 1400, "loss": 0.6682743489742279, "pref_accuracy": 0.63, "chosen_reward": 0.06715889275074005, "rejected_reward": 0.03865242004394531, "lr": 1.8751200501879146e-06, "tokens_per_sec": 154135.93025515217, "vram_gb": 3.751861095428467}
|
| 148 |
+
{"timestamp": 1787715596.0137901, "elapsed_hours": 0.1688694014151891, "event": "sample", "step": 1400, "sample_text": "Here is a Python function that returns the nth Fibonacci number:\n\n```python\ndef fibonacci(n):\n if n <= 1:\n return n\n else:\n return fibonacci(n-1) + fibonacci(n-2)\n```\n\nThis function takes an integer `n` as input and returns the nth Fibonacci number. It uses a recursive approach to find the nth Fibonacci number.\n\nThe function iterates through each number `n` in the range from 2 to the square root of `n`. The `fibonacci"}
|