Add files using upload-large-folder tool

Area/checkpoint-350/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb6462d333dbc5bb5e497ea9b0adb960f7616f79e6eea63222de6d5bd559516
+size 15984

Area/checkpoint-350/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a0ac63696d065e3a433642d355f584d8d203b0491ffbda8feebea742a096cc
+size 1064

Area/checkpoint-400/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7891ffa7c7dae99113aa986d67278b52b8c57db55001dc3547a61f24569a34ee
+size 15984

Area/checkpoint-400/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b92875cb04deec367605433847d1bda444b178b643d2da7ed9aaf738d232b4
+size 15984

Area/checkpoint-400/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f5f3338a05e325b5408a1cd0b6f5e5b10fad05fe479d63f44bec4cf18107d6
+size 15984

Area/checkpoint-400/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be749fea477a3867d44010631937e0d8f071ca5f9614f9795c92c7fa68833a6
+size 15984

Area/checkpoint-400/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc4a5ea4532c621f4c8e9891117b2e597a7f005001e8b4f2a1b4da8c82bf964
+size 15984

Area/checkpoint-400/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480f9fe7dd71b54d915b46162e34b780ba2467d5542115cc809dbca60b394c0e
+size 15984

Area/checkpoint-400/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11d982dcd813e82c2d97a5491ce9624cff2dd22e8655ea617ccef1fc1474470
+size 15984

Area/checkpoint-400/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73494fac3a001cba7cedd097b97f028d4c1d136ee6709214b0a7fe305e5b9089
+size 15984

Area/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b06b3faa61578a09d2f6b68679e7fd51d8d191703edc2524c8658dd1149ada0
+size 1064

Area/checkpoint-400/trainer_state.json

@@ -0,0 +1,633 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.389121338912133,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 0.4676998555660248,
+      "learning_rate": 8.620689655172415e-07,
+      "logits/chosen": 1.7077701091766357,
+      "logits/rejected": 1.8646482229232788,
+      "logps/chosen": -85.7728271484375,
+      "logps/rejected": -88.1952896118164,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": -0.004770822823047638,
+      "rewards/margins": -0.007881464436650276,
+      "rewards/rejected": 0.0031106427777558565,
+      "step": 10
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 0.43230223655700684,
+      "learning_rate": 1.724137931034483e-06,
+      "logits/chosen": 1.8023220300674438,
+      "logits/rejected": 1.8210970163345337,
+      "logps/chosen": -78.37618255615234,
+      "logps/rejected": -75.44720458984375,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.0056939031928777695,
+      "rewards/margins": -0.003848772030323744,
+      "rewards/rejected": -0.001845130929723382,
+      "step": 20
+    },
+    {
+      "epoch": 1.00418410041841,
+      "grad_norm": 2.431753396987915,
+      "learning_rate": 2.5862068965517246e-06,
+      "logits/chosen": 1.8643144369125366,
+      "logits/rejected": 1.8500900268554688,
+      "logps/chosen": -86.84412384033203,
+      "logps/rejected": -90.78925323486328,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.0008674233104102314,
+      "rewards/margins": -0.008064134046435356,
+      "rewards/rejected": 0.0071967123076319695,
+      "step": 30
+    },
+    {
+      "epoch": 1.3389121338912133,
+      "grad_norm": 0.5327289700508118,
+      "learning_rate": 3.448275862068966e-06,
+      "logits/chosen": 1.7701479196548462,
+      "logits/rejected": 1.7749736309051514,
+      "logps/chosen": -83.61552429199219,
+      "logps/rejected": -72.89176177978516,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -0.0019066383829340339,
+      "rewards/margins": -0.0035008196718990803,
+      "rewards/rejected": 0.0015941811725497246,
+      "step": 40
+    },
+    {
+      "epoch": 1.6736401673640167,
+      "grad_norm": 0.5017096996307373,
+      "learning_rate": 4.310344827586207e-06,
+      "logits/chosen": 1.7465788125991821,
+      "logits/rejected": 1.7925498485565186,
+      "logps/chosen": -84.85249328613281,
+      "logps/rejected": -88.79469299316406,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 0.0003656863118521869,
+      "rewards/margins": 0.00012080222222721204,
+      "rewards/rejected": 0.00024488387862220407,
+      "step": 50
+    },
+    {
+      "epoch": 2.00836820083682,
+      "grad_norm": 0.4994066059589386,
+      "learning_rate": 4.999818897894192e-06,
+      "logits/chosen": 1.8359416723251343,
+      "logits/rejected": 1.814234733581543,
+      "logps/chosen": -79.98396301269531,
+      "logps/rejected": -66.29866027832031,
+      "loss": 0.6952,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.00456579215824604,
+      "rewards/margins": -0.002460189163684845,
+      "rewards/rejected": 0.007025980856269598,
+      "step": 60
+    },
+    {
+      "epoch": 2.3430962343096233,
+      "grad_norm": 0.6425362825393677,
+      "learning_rate": 4.9934830787948756e-06,
+      "logits/chosen": 1.7550818920135498,
+      "logits/rejected": 1.7802051305770874,
+      "logps/chosen": -83.60951232910156,
+      "logps/rejected": -70.81080627441406,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.004059882368892431,
+      "rewards/margins": 0.00932090263813734,
+      "rewards/rejected": -0.005261021666228771,
+      "step": 70
+    },
+    {
+      "epoch": 2.6778242677824267,
+      "grad_norm": 0.5591297149658203,
+      "learning_rate": 4.978118375700895e-06,
+      "logits/chosen": 1.7742525339126587,
+      "logits/rejected": 1.8790937662124634,
+      "logps/chosen": -86.7696533203125,
+      "logps/rejected": -84.90727233886719,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 0.0033963967580348253,
+      "rewards/margins": 0.005500240251421928,
+      "rewards/rejected": -0.0021038432605564594,
+      "step": 80
+    },
+    {
+      "epoch": 3.01255230125523,
+      "grad_norm": 0.6774541735649109,
+      "learning_rate": 4.953780424089803e-06,
+      "logits/chosen": 1.8815631866455078,
+      "logits/rejected": 1.911620855331421,
+      "logps/chosen": -92.14398193359375,
+      "logps/rejected": -82.83556365966797,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.007645039353519678,
+      "rewards/margins": 0.005134005565196276,
+      "rewards/rejected": 0.0025110342539846897,
+      "step": 90
+    },
+    {
+      "epoch": 3.3472803347280333,
+      "grad_norm": 0.6908814907073975,
+      "learning_rate": 4.920557351506409e-06,
+      "logits/chosen": 1.7718560695648193,
+      "logits/rejected": 1.8823477029800415,
+      "logps/chosen": -91.2622299194336,
+      "logps/rejected": -96.467529296875,
+      "loss": 0.6894,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.004941435065120459,
+      "rewards/margins": 0.01582186669111252,
+      "rewards/rejected": -0.010880433022975922,
+      "step": 100
+    },
+    {
+      "epoch": 3.6820083682008367,
+      "grad_norm": 0.6954344511032104,
+      "learning_rate": 4.878569458453592e-06,
+      "logits/chosen": 1.6916942596435547,
+      "logits/rejected": 1.7603965997695923,
+      "logps/chosen": -84.66748046875,
+      "logps/rejected": -103.5328369140625,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.003184904810041189,
+      "rewards/margins": 0.007628746330738068,
+      "rewards/rejected": -0.01081365067511797,
+      "step": 110
+    },
+    {
+      "epoch": 4.01673640167364,
+      "grad_norm": 0.6846771240234375,
+      "learning_rate": 4.827968782785062e-06,
+      "logits/chosen": 1.8839175701141357,
+      "logits/rejected": 1.956974744796753,
+      "logps/chosen": -76.89198303222656,
+      "logps/rejected": -95.03202056884766,
+      "loss": 0.6886,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.009448022581636906,
+      "rewards/margins": 0.018458742648363113,
+      "rewards/rejected": -0.009010720066726208,
+      "step": 120
+    },
+    {
+      "epoch": 4.351464435146443,
+      "grad_norm": 0.762366771697998,
+      "learning_rate": 4.7689385491773934e-06,
+      "logits/chosen": 1.8294252157211304,
+      "logits/rejected": 1.8144447803497314,
+      "logps/chosen": -87.03471374511719,
+      "logps/rejected": -73.86766052246094,
+      "loss": 0.6847,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.01010747067630291,
+      "rewards/margins": 0.01468165498226881,
+      "rewards/rejected": -0.024789121001958847,
+      "step": 130
+    },
+    {
+      "epoch": 4.686192468619247,
+      "grad_norm": 0.7172746658325195,
+      "learning_rate": 4.70169250567482e-06,
+      "logits/chosen": 1.7118749618530273,
+      "logits/rejected": 1.8259985446929932,
+      "logps/chosen": -68.12081146240234,
+      "logps/rejected": -75.31085205078125,
+      "loss": 0.6809,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.014076923951506615,
+      "rewards/margins": 0.014298361726105213,
+      "rewards/rejected": -0.028375286608934402,
+      "step": 140
+    },
+    {
+      "epoch": 5.02092050209205,
+      "grad_norm": 0.7188512682914734,
+      "learning_rate": 4.626474149709127e-06,
+      "logits/chosen": 1.8864549398422241,
+      "logits/rejected": 1.8488889932632446,
+      "logps/chosen": -101.3166275024414,
+      "logps/rejected": -76.73490905761719,
+      "loss": 0.6773,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.021979983896017075,
+      "rewards/margins": 0.023767748847603798,
+      "rewards/rejected": -0.04574773460626602,
+      "step": 150
+    },
+    {
+      "epoch": 5.355648535564853,
+      "grad_norm": 0.8493714928627014,
+      "learning_rate": 4.54355584639723e-06,
+      "logits/chosen": 1.7861169576644897,
+      "logits/rejected": 1.7927452325820923,
+      "logps/chosen": -83.28593444824219,
+      "logps/rejected": -76.04238891601562,
+      "loss": 0.673,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.0320693664252758,
+      "rewards/margins": 0.04263792932033539,
+      "rewards/rejected": -0.07470729202032089,
+      "step": 160
+    },
+    {
+      "epoch": 5.690376569037657,
+      "grad_norm": 1.1378726959228516,
+      "learning_rate": 4.45323784230908e-06,
+      "logits/chosen": 1.8622329235076904,
+      "logits/rejected": 1.875741958618164,
+      "logps/chosen": -72.01219177246094,
+      "logps/rejected": -77.62818908691406,
+      "loss": 0.6679,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.05134737491607666,
+      "rewards/margins": 0.049249742180109024,
+      "rewards/rejected": -0.10059712082147598,
+      "step": 170
+    },
+    {
+      "epoch": 6.02510460251046,
+      "grad_norm": 0.847227156162262,
+      "learning_rate": 4.355847178277025e-06,
+      "logits/chosen": 1.9445765018463135,
+      "logits/rejected": 2.0065901279449463,
+      "logps/chosen": -76.14964294433594,
+      "logps/rejected": -83.71626281738281,
+      "loss": 0.6621,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.05519520118832588,
+      "rewards/margins": 0.06803703308105469,
+      "rewards/rejected": -0.12323222309350967,
+      "step": 180
+    },
+    {
+      "epoch": 6.359832635983263,
+      "grad_norm": 0.8368040919303894,
+      "learning_rate": 4.2517365051833564e-06,
+      "logits/chosen": 1.8116003274917603,
+      "logits/rejected": 1.8839362859725952,
+      "logps/chosen": -82.7087631225586,
+      "logps/rejected": -67.3785629272461,
+      "loss": 0.6538,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.03855596110224724,
+      "rewards/margins": 0.11562293767929077,
+      "rewards/rejected": -0.15417888760566711,
+      "step": 190
+    },
+    {
+      "epoch": 6.694560669456067,
+      "grad_norm": 0.8636891841888428,
+      "learning_rate": 4.141282807014034e-06,
+      "logits/chosen": 1.7250430583953857,
+      "logits/rejected": 1.775418996810913,
+      "logps/chosen": -68.51094055175781,
+      "logps/rejected": -79.88996124267578,
+      "loss": 0.657,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.11151214689016342,
+      "rewards/margins": 0.07863004505634308,
+      "rewards/rejected": -0.1901421844959259,
+      "step": 200
+    },
+    {
+      "epoch": 7.02928870292887,
+      "grad_norm": 0.945520281791687,
+      "learning_rate": 4.024886035802432e-06,
+      "logits/chosen": 1.7329381704330444,
+      "logits/rejected": 1.799551010131836,
+      "logps/chosen": -81.49295043945312,
+      "logps/rejected": -87.97386169433594,
+      "loss": 0.6462,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.09862186014652252,
+      "rewards/margins": 0.10664049535989761,
+      "rewards/rejected": -0.20526234805583954,
+      "step": 210
+    },
+    {
+      "epoch": 7.364016736401673,
+      "grad_norm": 0.9736716151237488,
+      "learning_rate": 3.9029676634059565e-06,
+      "logits/chosen": 1.8787791728973389,
+      "logits/rejected": 1.8832632303237915,
+      "logps/chosen": -83.21014404296875,
+      "logps/rejected": -76.4449691772461,
+      "loss": 0.6413,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.07923021167516708,
+      "rewards/margins": 0.11194779723882675,
+      "rewards/rejected": -0.19117799401283264,
+      "step": 220
+    },
+    {
+      "epoch": 7.698744769874477,
+      "grad_norm": 0.9238549470901489,
+      "learning_rate": 3.7759691553595214e-06,
+      "logits/chosen": 1.9044986963272095,
+      "logits/rejected": 1.8805242776870728,
+      "logps/chosen": -90.17919158935547,
+      "logps/rejected": -86.05476379394531,
+      "loss": 0.6346,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.0993318110704422,
+      "rewards/margins": 0.12289313971996307,
+      "rewards/rejected": -0.22222498059272766,
+      "step": 230
+    },
+    {
+      "epoch": 8.03347280334728,
+      "grad_norm": 1.0052326917648315,
+      "learning_rate": 3.6443503723320837e-06,
+      "logits/chosen": 1.873815894126892,
+      "logits/rejected": 1.8809674978256226,
+      "logps/chosen": -74.86824035644531,
+      "logps/rejected": -81.79768371582031,
+      "loss": 0.6377,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.17602138221263885,
+      "rewards/margins": 0.09737586975097656,
+      "rewards/rejected": -0.2733972668647766,
+      "step": 240
+    },
+    {
+      "epoch": 8.368200836820083,
+      "grad_norm": 1.0167930126190186,
+      "learning_rate": 3.508587904974522e-06,
+      "logits/chosen": 1.868101716041565,
+      "logits/rejected": 1.8685039281845093,
+      "logps/chosen": -94.48133850097656,
+      "logps/rejected": -94.00556182861328,
+      "loss": 0.6216,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.1260211318731308,
+      "rewards/margins": 0.21002164483070374,
+      "rewards/rejected": -0.3360427916049957,
+      "step": 250
+    },
+    {
+      "epoch": 8.702928870292887,
+      "grad_norm": 0.9955905079841614,
+      "learning_rate": 3.3691733481883693e-06,
+      "logits/chosen": 1.7905946969985962,
+      "logits/rejected": 1.7784850597381592,
+      "logps/chosen": -94.9794921875,
+      "logps/rejected": -84.99113464355469,
+      "loss": 0.6193,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.18853916227817535,
+      "rewards/margins": 0.19185101985931396,
+      "rewards/rejected": -0.3803902268409729,
+      "step": 260
+    },
+    {
+      "epoch": 9.03765690376569,
+      "grad_norm": 0.943289577960968,
+      "learning_rate": 3.226611521064278e-06,
+      "logits/chosen": 1.8119779825210571,
+      "logits/rejected": 1.817567229270935,
+      "logps/chosen": -80.78002166748047,
+      "logps/rejected": -85.42848205566406,
+      "loss": 0.6201,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.16673071682453156,
+      "rewards/margins": 0.19530437886714935,
+      "rewards/rejected": -0.3620350658893585,
+      "step": 270
+    },
+    {
+      "epoch": 9.372384937238493,
+      "grad_norm": 0.9868927597999573,
+      "learning_rate": 3.0814186389357765e-06,
+      "logits/chosen": 1.816300392150879,
+      "logits/rejected": 1.7763961553573608,
+      "logps/chosen": -77.19395446777344,
+      "logps/rejected": -68.16056060791016,
+      "loss": 0.6157,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.21062004566192627,
+      "rewards/margins": 0.19489461183547974,
+      "rewards/rejected": -0.4055147171020508,
+      "step": 280
+    },
+    {
+      "epoch": 9.707112970711297,
+      "grad_norm": 1.0557409524917603,
+      "learning_rate": 2.9341204441673267e-06,
+      "logits/chosen": 1.8154022693634033,
+      "logits/rejected": 1.842792272567749,
+      "logps/chosen": -84.95299530029297,
+      "logps/rejected": -82.22926330566406,
+      "loss": 0.5972,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25716403126716614,
+      "rewards/margins": 0.2636396288871765,
+      "rewards/rejected": -0.5208036303520203,
+      "step": 290
+    },
+    {
+      "epoch": 10.0418410041841,
+      "grad_norm": 1.0787400007247925,
+      "learning_rate": 2.785250302445062e-06,
+      "logits/chosen": 1.8255424499511719,
+      "logits/rejected": 1.8123111724853516,
+      "logps/chosen": -94.89508056640625,
+      "logps/rejected": -99.48709869384766,
+      "loss": 0.6038,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25526899099349976,
+      "rewards/margins": 0.24981728196144104,
+      "rewards/rejected": -0.5050862431526184,
+      "step": 300
+    },
+    {
+      "epoch": 10.376569037656903,
+      "grad_norm": 0.9934303164482117,
+      "learning_rate": 2.6353472714635443e-06,
+      "logits/chosen": 1.6809011697769165,
+      "logits/rejected": 1.6883894205093384,
+      "logps/chosen": -83.52108001708984,
+      "logps/rejected": -89.83765411376953,
+      "loss": 0.5897,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.20843425393104553,
+      "rewards/margins": 0.2531076967716217,
+      "rewards/rejected": -0.46154195070266724,
+      "step": 310
+    },
+    {
+      "epoch": 10.711297071129707,
+      "grad_norm": 1.0989857912063599,
+      "learning_rate": 2.4849541490017868e-06,
+      "logits/chosen": 1.8184492588043213,
+      "logits/rejected": 1.8702239990234375,
+      "logps/chosen": -76.5416030883789,
+      "logps/rejected": -87.98771667480469,
+      "loss": 0.5951,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.26176151633262634,
+      "rewards/margins": 0.17908410727977753,
+      "rewards/rejected": -0.44084563851356506,
+      "step": 320
+    },
+    {
+      "epoch": 11.04602510460251,
+      "grad_norm": 1.1377506256103516,
+      "learning_rate": 2.3346155074564712e-06,
+      "logits/chosen": 1.7781150341033936,
+      "logits/rejected": 1.7945045232772827,
+      "logps/chosen": -94.21954345703125,
+      "logps/rejected": -87.9439926147461,
+      "loss": 0.5895,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.3070668578147888,
+      "rewards/margins": 0.26864537596702576,
+      "rewards/rejected": -0.5757122039794922,
+      "step": 330
+    },
+    {
+      "epoch": 11.380753138075313,
+      "grad_norm": 1.1378768682479858,
+      "learning_rate": 2.184875721949277e-06,
+      "logits/chosen": 1.7889184951782227,
+      "logits/rejected": 1.7863588333129883,
+      "logps/chosen": -77.19974517822266,
+      "logps/rejected": -74.92039489746094,
+      "loss": 0.577,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.2269454449415207,
+      "rewards/margins": 0.3004661798477173,
+      "rewards/rejected": -0.5274116396903992,
+      "step": 340
+    },
+    {
+      "epoch": 11.715481171548117,
+      "grad_norm": 1.0102859735488892,
+      "learning_rate": 2.0362769991485514e-06,
+      "logits/chosen": 1.6868798732757568,
+      "logits/rejected": 1.743287444114685,
+      "logps/chosen": -80.24299621582031,
+      "logps/rejected": -91.3736343383789,
+      "loss": 0.5825,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2850210964679718,
+      "rewards/margins": 0.30632922053337097,
+      "rewards/rejected": -0.5913503170013428,
+      "step": 350
+    },
+    {
+      "epoch": 12.05020920502092,
+      "grad_norm": 1.0598143339157104,
+      "learning_rate": 1.8893574139429226e-06,
+      "logits/chosen": 1.6859172582626343,
+      "logits/rejected": 1.7635313272476196,
+      "logps/chosen": -88.87372589111328,
+      "logps/rejected": -93.02122497558594,
+      "loss": 0.5819,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.317017138004303,
+      "rewards/margins": 0.2608889639377594,
+      "rewards/rejected": -0.5779060125350952,
+      "step": 360
+    },
+    {
+      "epoch": 12.384937238493723,
+      "grad_norm": 1.0845669507980347,
+      "learning_rate": 1.744648961076068e-06,
+      "logits/chosen": 1.7980632781982422,
+      "logits/rejected": 1.8205795288085938,
+      "logps/chosen": -83.31995391845703,
+      "logps/rejected": -87.28046417236328,
+      "loss": 0.5737,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.3205794394016266,
+      "rewards/margins": 0.24214692413806915,
+      "rewards/rejected": -0.5627263784408569,
+      "step": 370
+    },
+    {
+      "epoch": 12.719665271966527,
+      "grad_norm": 1.180468201637268,
+      "learning_rate": 1.602675628797636e-06,
+      "logits/chosen": 1.8093292713165283,
+      "logits/rejected": 1.8195394277572632,
+      "logps/chosen": -99.64051055908203,
+      "logps/rejected": -82.13116455078125,
+      "loss": 0.5655,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.28717803955078125,
+      "rewards/margins": 0.355060875415802,
+      "rewards/rejected": -0.6422389149665833,
+      "step": 380
+    },
+    {
+      "epoch": 13.05439330543933,
+      "grad_norm": 1.0443357229232788,
+      "learning_rate": 1.4639515015056205e-06,
+      "logits/chosen": 1.7365925312042236,
+      "logits/rejected": 1.7514903545379639,
+      "logps/chosen": -96.92813110351562,
+      "logps/rejected": -83.5425796508789,
+      "loss": 0.5654,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3064219653606415,
+      "rewards/margins": 0.38930463790893555,
+      "rewards/rejected": -0.6957265138626099,
+      "step": 390
+    },
+    {
+      "epoch": 13.389121338912133,
+      "grad_norm": 1.2010602951049805,
+      "learning_rate": 1.328978898250525e-06,
+      "logits/chosen": 1.7649974822998047,
+      "logits/rejected": 1.7864068746566772,
+      "logps/chosen": -78.26787567138672,
+      "logps/rejected": -82.81205749511719,
+      "loss": 0.5713,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.32541388273239136,
+      "rewards/margins": 0.34498968720436096,
+      "rewards/rejected": -0.6704035997390747,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 580,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3630116273345004e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Area/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fdbb84546d398ee1e74a571d23f6402145ae8ee37528e7a681ffd688b001a68
+size 5368

Area/checkpoint-450/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Area/checkpoint-450/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Area/checkpoint-450/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e571d57a85eb2cdabf3f46c86e446bdb7d26aba8b1467b5e4b5bbe29ad42a7
+size 15984

Area/checkpoint-450/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489e5542988617525a395c45dc83ec6bf25b473812e139122f0a3f3d92f031d0
+size 15984

Area/checkpoint-450/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cd77682efb711872c5be25e87e87a2726a2e7105422cddd00f04da7be35ca20
+size 15984

Area/checkpoint-450/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44d9e7d535f5fbcd7cfef16ba22d32d5f445aacceba782a05df1f97d47a608a
+size 15984

Area/checkpoint-450/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a107290a0d9898930bc6abe369ee246ef7322541985fc2a5320e7775f5ea5c88
+size 15984

Area/checkpoint-450/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ab49d56ee4079c2a208376064f825918f070addc8f0c58c5c594265f9e8a78
+size 15984

Area/checkpoint-450/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d15033d06420b17d80db45c89544170faa67833d5a0d9c30a51a38a1102b073
+size 15984

Area/checkpoint-450/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Area/checkpoint-450/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Area/checkpoint-450/trainer_state.json

@@ -0,0 +1,708 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.06276150627615,
+  "eval_steps": 500,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 0.4676998555660248,
+      "learning_rate": 8.620689655172415e-07,
+      "logits/chosen": 1.7077701091766357,
+      "logits/rejected": 1.8646482229232788,
+      "logps/chosen": -85.7728271484375,
+      "logps/rejected": -88.1952896118164,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": -0.004770822823047638,
+      "rewards/margins": -0.007881464436650276,
+      "rewards/rejected": 0.0031106427777558565,
+      "step": 10
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 0.43230223655700684,
+      "learning_rate": 1.724137931034483e-06,
+      "logits/chosen": 1.8023220300674438,
+      "logits/rejected": 1.8210970163345337,
+      "logps/chosen": -78.37618255615234,
+      "logps/rejected": -75.44720458984375,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.0056939031928777695,
+      "rewards/margins": -0.003848772030323744,
+      "rewards/rejected": -0.001845130929723382,
+      "step": 20
+    },
+    {
+      "epoch": 1.00418410041841,
+      "grad_norm": 2.431753396987915,
+      "learning_rate": 2.5862068965517246e-06,
+      "logits/chosen": 1.8643144369125366,
+      "logits/rejected": 1.8500900268554688,
+      "logps/chosen": -86.84412384033203,
+      "logps/rejected": -90.78925323486328,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.0008674233104102314,
+      "rewards/margins": -0.008064134046435356,
+      "rewards/rejected": 0.0071967123076319695,
+      "step": 30
+    },
+    {
+      "epoch": 1.3389121338912133,
+      "grad_norm": 0.5327289700508118,
+      "learning_rate": 3.448275862068966e-06,
+      "logits/chosen": 1.7701479196548462,
+      "logits/rejected": 1.7749736309051514,
+      "logps/chosen": -83.61552429199219,
+      "logps/rejected": -72.89176177978516,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -0.0019066383829340339,
+      "rewards/margins": -0.0035008196718990803,
+      "rewards/rejected": 0.0015941811725497246,
+      "step": 40
+    },
+    {
+      "epoch": 1.6736401673640167,
+      "grad_norm": 0.5017096996307373,
+      "learning_rate": 4.310344827586207e-06,
+      "logits/chosen": 1.7465788125991821,
+      "logits/rejected": 1.7925498485565186,
+      "logps/chosen": -84.85249328613281,
+      "logps/rejected": -88.79469299316406,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 0.0003656863118521869,
+      "rewards/margins": 0.00012080222222721204,
+      "rewards/rejected": 0.00024488387862220407,
+      "step": 50
+    },
+    {
+      "epoch": 2.00836820083682,
+      "grad_norm": 0.4994066059589386,
+      "learning_rate": 4.999818897894192e-06,
+      "logits/chosen": 1.8359416723251343,
+      "logits/rejected": 1.814234733581543,
+      "logps/chosen": -79.98396301269531,
+      "logps/rejected": -66.29866027832031,
+      "loss": 0.6952,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.00456579215824604,
+      "rewards/margins": -0.002460189163684845,
+      "rewards/rejected": 0.007025980856269598,
+      "step": 60
+    },
+    {
+      "epoch": 2.3430962343096233,
+      "grad_norm": 0.6425362825393677,
+      "learning_rate": 4.9934830787948756e-06,
+      "logits/chosen": 1.7550818920135498,
+      "logits/rejected": 1.7802051305770874,
+      "logps/chosen": -83.60951232910156,
+      "logps/rejected": -70.81080627441406,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.004059882368892431,
+      "rewards/margins": 0.00932090263813734,
+      "rewards/rejected": -0.005261021666228771,
+      "step": 70
+    },
+    {
+      "epoch": 2.6778242677824267,
+      "grad_norm": 0.5591297149658203,
+      "learning_rate": 4.978118375700895e-06,
+      "logits/chosen": 1.7742525339126587,
+      "logits/rejected": 1.8790937662124634,
+      "logps/chosen": -86.7696533203125,
+      "logps/rejected": -84.90727233886719,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 0.0033963967580348253,
+      "rewards/margins": 0.005500240251421928,
+      "rewards/rejected": -0.0021038432605564594,
+      "step": 80
+    },
+    {
+      "epoch": 3.01255230125523,
+      "grad_norm": 0.6774541735649109,
+      "learning_rate": 4.953780424089803e-06,
+      "logits/chosen": 1.8815631866455078,
+      "logits/rejected": 1.911620855331421,
+      "logps/chosen": -92.14398193359375,
+      "logps/rejected": -82.83556365966797,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.007645039353519678,
+      "rewards/margins": 0.005134005565196276,
+      "rewards/rejected": 0.0025110342539846897,
+      "step": 90
+    },
+    {
+      "epoch": 3.3472803347280333,
+      "grad_norm": 0.6908814907073975,
+      "learning_rate": 4.920557351506409e-06,
+      "logits/chosen": 1.7718560695648193,
+      "logits/rejected": 1.8823477029800415,
+      "logps/chosen": -91.2622299194336,
+      "logps/rejected": -96.467529296875,
+      "loss": 0.6894,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.004941435065120459,
+      "rewards/margins": 0.01582186669111252,
+      "rewards/rejected": -0.010880433022975922,
+      "step": 100
+    },
+    {
+      "epoch": 3.6820083682008367,
+      "grad_norm": 0.6954344511032104,
+      "learning_rate": 4.878569458453592e-06,
+      "logits/chosen": 1.6916942596435547,
+      "logits/rejected": 1.7603965997695923,
+      "logps/chosen": -84.66748046875,
+      "logps/rejected": -103.5328369140625,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.003184904810041189,
+      "rewards/margins": 0.007628746330738068,
+      "rewards/rejected": -0.01081365067511797,
+      "step": 110
+    },
+    {
+      "epoch": 4.01673640167364,
+      "grad_norm": 0.6846771240234375,
+      "learning_rate": 4.827968782785062e-06,
+      "logits/chosen": 1.8839175701141357,
+      "logits/rejected": 1.956974744796753,
+      "logps/chosen": -76.89198303222656,
+      "logps/rejected": -95.03202056884766,
+      "loss": 0.6886,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.009448022581636906,
+      "rewards/margins": 0.018458742648363113,
+      "rewards/rejected": -0.009010720066726208,
+      "step": 120
+    },
+    {
+      "epoch": 4.351464435146443,
+      "grad_norm": 0.762366771697998,
+      "learning_rate": 4.7689385491773934e-06,
+      "logits/chosen": 1.8294252157211304,
+      "logits/rejected": 1.8144447803497314,
+      "logps/chosen": -87.03471374511719,
+      "logps/rejected": -73.86766052246094,
+      "loss": 0.6847,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.01010747067630291,
+      "rewards/margins": 0.01468165498226881,
+      "rewards/rejected": -0.024789121001958847,
+      "step": 130
+    },
+    {
+      "epoch": 4.686192468619247,
+      "grad_norm": 0.7172746658325195,
+      "learning_rate": 4.70169250567482e-06,
+      "logits/chosen": 1.7118749618530273,
+      "logits/rejected": 1.8259985446929932,
+      "logps/chosen": -68.12081146240234,
+      "logps/rejected": -75.31085205078125,
+      "loss": 0.6809,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.014076923951506615,
+      "rewards/margins": 0.014298361726105213,
+      "rewards/rejected": -0.028375286608934402,
+      "step": 140
+    },
+    {
+      "epoch": 5.02092050209205,
+      "grad_norm": 0.7188512682914734,
+      "learning_rate": 4.626474149709127e-06,
+      "logits/chosen": 1.8864549398422241,
+      "logits/rejected": 1.8488889932632446,
+      "logps/chosen": -101.3166275024414,
+      "logps/rejected": -76.73490905761719,
+      "loss": 0.6773,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.021979983896017075,
+      "rewards/margins": 0.023767748847603798,
+      "rewards/rejected": -0.04574773460626602,
+      "step": 150
+    },
+    {
+      "epoch": 5.355648535564853,
+      "grad_norm": 0.8493714928627014,
+      "learning_rate": 4.54355584639723e-06,
+      "logits/chosen": 1.7861169576644897,
+      "logits/rejected": 1.7927452325820923,
+      "logps/chosen": -83.28593444824219,
+      "logps/rejected": -76.04238891601562,
+      "loss": 0.673,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.0320693664252758,
+      "rewards/margins": 0.04263792932033539,
+      "rewards/rejected": -0.07470729202032089,
+      "step": 160
+    },
+    {
+      "epoch": 5.690376569037657,
+      "grad_norm": 1.1378726959228516,
+      "learning_rate": 4.45323784230908e-06,
+      "logits/chosen": 1.8622329235076904,
+      "logits/rejected": 1.875741958618164,
+      "logps/chosen": -72.01219177246094,
+      "logps/rejected": -77.62818908691406,
+      "loss": 0.6679,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.05134737491607666,
+      "rewards/margins": 0.049249742180109024,
+      "rewards/rejected": -0.10059712082147598,
+      "step": 170
+    },
+    {
+      "epoch": 6.02510460251046,
+      "grad_norm": 0.847227156162262,
+      "learning_rate": 4.355847178277025e-06,
+      "logits/chosen": 1.9445765018463135,
+      "logits/rejected": 2.0065901279449463,
+      "logps/chosen": -76.14964294433594,
+      "logps/rejected": -83.71626281738281,
+      "loss": 0.6621,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.05519520118832588,
+      "rewards/margins": 0.06803703308105469,
+      "rewards/rejected": -0.12323222309350967,
+      "step": 180
+    },
+    {
+      "epoch": 6.359832635983263,
+      "grad_norm": 0.8368040919303894,
+      "learning_rate": 4.2517365051833564e-06,
+      "logits/chosen": 1.8116003274917603,
+      "logits/rejected": 1.8839362859725952,
+      "logps/chosen": -82.7087631225586,
+      "logps/rejected": -67.3785629272461,
+      "loss": 0.6538,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.03855596110224724,
+      "rewards/margins": 0.11562293767929077,
+      "rewards/rejected": -0.15417888760566711,
+      "step": 190
+    },
+    {
+      "epoch": 6.694560669456067,
+      "grad_norm": 0.8636891841888428,
+      "learning_rate": 4.141282807014034e-06,
+      "logits/chosen": 1.7250430583953857,
+      "logits/rejected": 1.775418996810913,
+      "logps/chosen": -68.51094055175781,
+      "logps/rejected": -79.88996124267578,
+      "loss": 0.657,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.11151214689016342,
+      "rewards/margins": 0.07863004505634308,
+      "rewards/rejected": -0.1901421844959259,
+      "step": 200
+    },
+    {
+      "epoch": 7.02928870292887,
+      "grad_norm": 0.945520281791687,
+      "learning_rate": 4.024886035802432e-06,
+      "logits/chosen": 1.7329381704330444,
+      "logits/rejected": 1.799551010131836,
+      "logps/chosen": -81.49295043945312,
+      "logps/rejected": -87.97386169433594,
+      "loss": 0.6462,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.09862186014652252,
+      "rewards/margins": 0.10664049535989761,
+      "rewards/rejected": -0.20526234805583954,
+      "step": 210
+    },
+    {
+      "epoch": 7.364016736401673,
+      "grad_norm": 0.9736716151237488,
+      "learning_rate": 3.9029676634059565e-06,
+      "logits/chosen": 1.8787791728973389,
+      "logits/rejected": 1.8832632303237915,
+      "logps/chosen": -83.21014404296875,
+      "logps/rejected": -76.4449691772461,
+      "loss": 0.6413,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.07923021167516708,
+      "rewards/margins": 0.11194779723882675,
+      "rewards/rejected": -0.19117799401283264,
+      "step": 220
+    },
+    {
+      "epoch": 7.698744769874477,
+      "grad_norm": 0.9238549470901489,
+      "learning_rate": 3.7759691553595214e-06,
+      "logits/chosen": 1.9044986963272095,
+      "logits/rejected": 1.8805242776870728,
+      "logps/chosen": -90.17919158935547,
+      "logps/rejected": -86.05476379394531,
+      "loss": 0.6346,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.0993318110704422,
+      "rewards/margins": 0.12289313971996307,
+      "rewards/rejected": -0.22222498059272766,
+      "step": 230
+    },
+    {
+      "epoch": 8.03347280334728,
+      "grad_norm": 1.0052326917648315,
+      "learning_rate": 3.6443503723320837e-06,
+      "logits/chosen": 1.873815894126892,
+      "logits/rejected": 1.8809674978256226,
+      "logps/chosen": -74.86824035644531,
+      "logps/rejected": -81.79768371582031,
+      "loss": 0.6377,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.17602138221263885,
+      "rewards/margins": 0.09737586975097656,
+      "rewards/rejected": -0.2733972668647766,
+      "step": 240
+    },
+    {
+      "epoch": 8.368200836820083,
+      "grad_norm": 1.0167930126190186,
+      "learning_rate": 3.508587904974522e-06,
+      "logits/chosen": 1.868101716041565,
+      "logits/rejected": 1.8685039281845093,
+      "logps/chosen": -94.48133850097656,
+      "logps/rejected": -94.00556182861328,
+      "loss": 0.6216,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.1260211318731308,
+      "rewards/margins": 0.21002164483070374,
+      "rewards/rejected": -0.3360427916049957,
+      "step": 250
+    },
+    {
+      "epoch": 8.702928870292887,
+      "grad_norm": 0.9955905079841614,
+      "learning_rate": 3.3691733481883693e-06,
+      "logits/chosen": 1.7905946969985962,
+      "logits/rejected": 1.7784850597381592,
+      "logps/chosen": -94.9794921875,
+      "logps/rejected": -84.99113464355469,
+      "loss": 0.6193,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.18853916227817535,
+      "rewards/margins": 0.19185101985931396,
+      "rewards/rejected": -0.3803902268409729,
+      "step": 260
+    },
+    {
+      "epoch": 9.03765690376569,
+      "grad_norm": 0.943289577960968,
+      "learning_rate": 3.226611521064278e-06,
+      "logits/chosen": 1.8119779825210571,
+      "logits/rejected": 1.817567229270935,
+      "logps/chosen": -80.78002166748047,
+      "logps/rejected": -85.42848205566406,
+      "loss": 0.6201,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.16673071682453156,
+      "rewards/margins": 0.19530437886714935,
+      "rewards/rejected": -0.3620350658893585,
+      "step": 270
+    },
+    {
+      "epoch": 9.372384937238493,
+      "grad_norm": 0.9868927597999573,
+      "learning_rate": 3.0814186389357765e-06,
+      "logits/chosen": 1.816300392150879,
+      "logits/rejected": 1.7763961553573608,
+      "logps/chosen": -77.19395446777344,
+      "logps/rejected": -68.16056060791016,
+      "loss": 0.6157,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.21062004566192627,
+      "rewards/margins": 0.19489461183547974,
+      "rewards/rejected": -0.4055147171020508,
+      "step": 280
+    },
+    {
+      "epoch": 9.707112970711297,
+      "grad_norm": 1.0557409524917603,
+      "learning_rate": 2.9341204441673267e-06,
+      "logits/chosen": 1.8154022693634033,
+      "logits/rejected": 1.842792272567749,
+      "logps/chosen": -84.95299530029297,
+      "logps/rejected": -82.22926330566406,
+      "loss": 0.5972,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25716403126716614,
+      "rewards/margins": 0.2636396288871765,
+      "rewards/rejected": -0.5208036303520203,
+      "step": 290
+    },
+    {
+      "epoch": 10.0418410041841,
+      "grad_norm": 1.0787400007247925,
+      "learning_rate": 2.785250302445062e-06,
+      "logits/chosen": 1.8255424499511719,
+      "logits/rejected": 1.8123111724853516,
+      "logps/chosen": -94.89508056640625,
+      "logps/rejected": -99.48709869384766,
+      "loss": 0.6038,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25526899099349976,
+      "rewards/margins": 0.24981728196144104,
+      "rewards/rejected": -0.5050862431526184,
+      "step": 300
+    },
+    {
+      "epoch": 10.376569037656903,
+      "grad_norm": 0.9934303164482117,
+      "learning_rate": 2.6353472714635443e-06,
+      "logits/chosen": 1.6809011697769165,
+      "logits/rejected": 1.6883894205093384,
+      "logps/chosen": -83.52108001708984,
+      "logps/rejected": -89.83765411376953,
+      "loss": 0.5897,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.20843425393104553,
+      "rewards/margins": 0.2531076967716217,
+      "rewards/rejected": -0.46154195070266724,
+      "step": 310
+    },
+    {
+      "epoch": 10.711297071129707,
+      "grad_norm": 1.0989857912063599,
+      "learning_rate": 2.4849541490017868e-06,
+      "logits/chosen": 1.8184492588043213,
+      "logits/rejected": 1.8702239990234375,
+      "logps/chosen": -76.5416030883789,
+      "logps/rejected": -87.98771667480469,
+      "loss": 0.5951,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.26176151633262634,
+      "rewards/margins": 0.17908410727977753,
+      "rewards/rejected": -0.44084563851356506,
+      "step": 320
+    },
+    {
+      "epoch": 11.04602510460251,
+      "grad_norm": 1.1377506256103516,
+      "learning_rate": 2.3346155074564712e-06,
+      "logits/chosen": 1.7781150341033936,
+      "logits/rejected": 1.7945045232772827,
+      "logps/chosen": -94.21954345703125,
+      "logps/rejected": -87.9439926147461,
+      "loss": 0.5895,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.3070668578147888,
+      "rewards/margins": 0.26864537596702576,
+      "rewards/rejected": -0.5757122039794922,
+      "step": 330
+    },
+    {
+      "epoch": 11.380753138075313,
+      "grad_norm": 1.1378768682479858,
+      "learning_rate": 2.184875721949277e-06,
+      "logits/chosen": 1.7889184951782227,
+      "logits/rejected": 1.7863588333129883,
+      "logps/chosen": -77.19974517822266,
+      "logps/rejected": -74.92039489746094,
+      "loss": 0.577,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.2269454449415207,
+      "rewards/margins": 0.3004661798477173,
+      "rewards/rejected": -0.5274116396903992,
+      "step": 340
+    },
+    {
+      "epoch": 11.715481171548117,
+      "grad_norm": 1.0102859735488892,
+      "learning_rate": 2.0362769991485514e-06,
+      "logits/chosen": 1.6868798732757568,
+      "logits/rejected": 1.743287444114685,
+      "logps/chosen": -80.24299621582031,
+      "logps/rejected": -91.3736343383789,
+      "loss": 0.5825,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2850210964679718,
+      "rewards/margins": 0.30632922053337097,
+      "rewards/rejected": -0.5913503170013428,
+      "step": 350
+    },
+    {
+      "epoch": 12.05020920502092,
+      "grad_norm": 1.0598143339157104,
+      "learning_rate": 1.8893574139429226e-06,
+      "logits/chosen": 1.6859172582626343,
+      "logits/rejected": 1.7635313272476196,
+      "logps/chosen": -88.87372589111328,
+      "logps/rejected": -93.02122497558594,
+      "loss": 0.5819,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.317017138004303,
+      "rewards/margins": 0.2608889639377594,
+      "rewards/rejected": -0.5779060125350952,
+      "step": 360
+    },
+    {
+      "epoch": 12.384937238493723,
+      "grad_norm": 1.0845669507980347,
+      "learning_rate": 1.744648961076068e-06,
+      "logits/chosen": 1.7980632781982422,
+      "logits/rejected": 1.8205795288085938,
+      "logps/chosen": -83.31995391845703,
+      "logps/rejected": -87.28046417236328,
+      "loss": 0.5737,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.3205794394016266,
+      "rewards/margins": 0.24214692413806915,
+      "rewards/rejected": -0.5627263784408569,
+      "step": 370
+    },
+    {
+      "epoch": 12.719665271966527,
+      "grad_norm": 1.180468201637268,
+      "learning_rate": 1.602675628797636e-06,
+      "logits/chosen": 1.8093292713165283,
+      "logits/rejected": 1.8195394277572632,
+      "logps/chosen": -99.64051055908203,
+      "logps/rejected": -82.13116455078125,
+      "loss": 0.5655,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.28717803955078125,
+      "rewards/margins": 0.355060875415802,
+      "rewards/rejected": -0.6422389149665833,
+      "step": 380
+    },
+    {
+      "epoch": 13.05439330543933,
+      "grad_norm": 1.0443357229232788,
+      "learning_rate": 1.4639515015056205e-06,
+      "logits/chosen": 1.7365925312042236,
+      "logits/rejected": 1.7514903545379639,
+      "logps/chosen": -96.92813110351562,
+      "logps/rejected": -83.5425796508789,
+      "loss": 0.5654,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3064219653606415,
+      "rewards/margins": 0.38930463790893555,
+      "rewards/rejected": -0.6957265138626099,
+      "step": 390
+    },
+    {
+      "epoch": 13.389121338912133,
+      "grad_norm": 1.2010602951049805,
+      "learning_rate": 1.328978898250525e-06,
+      "logits/chosen": 1.7649974822998047,
+      "logits/rejected": 1.7864068746566772,
+      "logps/chosen": -78.26787567138672,
+      "logps/rejected": -82.81205749511719,
+      "loss": 0.5713,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.32541388273239136,
+      "rewards/margins": 0.34498968720436096,
+      "rewards/rejected": -0.6704035997390747,
+      "step": 400
+    },
+    {
+      "epoch": 13.723849372384937,
+      "grad_norm": 1.656805396080017,
+      "learning_rate": 1.198246553841744e-06,
+      "logits/chosen": 1.6543798446655273,
+      "logits/rejected": 1.700377106666565,
+      "logps/chosen": -88.14425659179688,
+      "logps/rejected": -86.7034912109375,
+      "loss": 0.5569,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.307409405708313,
+      "rewards/margins": 0.346424400806427,
+      "rewards/rejected": -0.65383380651474,
+      "step": 410
+    },
+    {
+      "epoch": 14.05857740585774,
+      "grad_norm": 1.3017597198486328,
+      "learning_rate": 1.0722278491423998e-06,
+      "logits/chosen": 1.861400842666626,
+      "logits/rejected": 1.7919048070907593,
+      "logps/chosen": -101.43531036376953,
+      "logps/rejected": -77.99034881591797,
+      "loss": 0.567,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.34600889682769775,
+      "rewards/margins": 0.2590746283531189,
+      "rewards/rejected": -0.6050835251808167,
+      "step": 420
+    },
+    {
+      "epoch": 14.393305439330543,
+      "grad_norm": 1.0269688367843628,
+      "learning_rate": 9.513790969606926e-07,
+      "logits/chosen": 1.809483289718628,
+      "logits/rejected": 1.8456366062164307,
+      "logps/chosen": -102.51566314697266,
+      "logps/rejected": -104.2486343383789,
+      "loss": 0.5605,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.33636271953582764,
+      "rewards/margins": 0.3720197379589081,
+      "rewards/rejected": -0.7083825469017029,
+      "step": 430
+    },
+    {
+      "epoch": 14.728033472803347,
+      "grad_norm": 1.0176596641540527,
+      "learning_rate": 8.361378897445643e-07,
+      "logits/chosen": 1.8125699758529663,
+      "logits/rejected": 1.819248914718628,
+      "logps/chosen": -83.56723022460938,
+      "logps/rejected": -81.31576538085938,
+      "loss": 0.5549,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.321399986743927,
+      "rewards/margins": 0.2679772973060608,
+      "rewards/rejected": -0.5893772840499878,
+      "step": 440
+    },
+    {
+      "epoch": 15.06276150627615,
+      "grad_norm": 1.1313916444778442,
+      "learning_rate": 7.269215150626391e-07,
+      "logits/chosen": 1.7356494665145874,
+      "logits/rejected": 1.793581247329712,
+      "logps/chosen": -80.0768051147461,
+      "logps/rejected": -79.23683166503906,
+      "loss": 0.5606,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.34324222803115845,
+      "rewards/margins": 0.3662562370300293,
+      "rewards/rejected": -0.7094983458518982,
+      "step": 450
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 580,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5322688624714056e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Area/checkpoint-450/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fdbb84546d398ee1e74a571d23f6402145ae8ee37528e7a681ffd688b001a68
+size 5368

Area/checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Area/checkpoint-500/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Area/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Area/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Area/checkpoint-500/trainer_state.json

@@ -0,0 +1,783 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 16.736401673640167,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 0.4676998555660248,
+      "learning_rate": 8.620689655172415e-07,
+      "logits/chosen": 1.7077701091766357,
+      "logits/rejected": 1.8646482229232788,
+      "logps/chosen": -85.7728271484375,
+      "logps/rejected": -88.1952896118164,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": -0.004770822823047638,
+      "rewards/margins": -0.007881464436650276,
+      "rewards/rejected": 0.0031106427777558565,
+      "step": 10
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 0.43230223655700684,
+      "learning_rate": 1.724137931034483e-06,
+      "logits/chosen": 1.8023220300674438,
+      "logits/rejected": 1.8210970163345337,
+      "logps/chosen": -78.37618255615234,
+      "logps/rejected": -75.44720458984375,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.0056939031928777695,
+      "rewards/margins": -0.003848772030323744,
+      "rewards/rejected": -0.001845130929723382,
+      "step": 20
+    },
+    {
+      "epoch": 1.00418410041841,
+      "grad_norm": 2.431753396987915,
+      "learning_rate": 2.5862068965517246e-06,
+      "logits/chosen": 1.8643144369125366,
+      "logits/rejected": 1.8500900268554688,
+      "logps/chosen": -86.84412384033203,
+      "logps/rejected": -90.78925323486328,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.0008674233104102314,
+      "rewards/margins": -0.008064134046435356,
+      "rewards/rejected": 0.0071967123076319695,
+      "step": 30
+    },
+    {
+      "epoch": 1.3389121338912133,
+      "grad_norm": 0.5327289700508118,
+      "learning_rate": 3.448275862068966e-06,
+      "logits/chosen": 1.7701479196548462,
+      "logits/rejected": 1.7749736309051514,
+      "logps/chosen": -83.61552429199219,
+      "logps/rejected": -72.89176177978516,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -0.0019066383829340339,
+      "rewards/margins": -0.0035008196718990803,
+      "rewards/rejected": 0.0015941811725497246,
+      "step": 40
+    },
+    {
+      "epoch": 1.6736401673640167,
+      "grad_norm": 0.5017096996307373,
+      "learning_rate": 4.310344827586207e-06,
+      "logits/chosen": 1.7465788125991821,
+      "logits/rejected": 1.7925498485565186,
+      "logps/chosen": -84.85249328613281,
+      "logps/rejected": -88.79469299316406,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 0.0003656863118521869,
+      "rewards/margins": 0.00012080222222721204,
+      "rewards/rejected": 0.00024488387862220407,
+      "step": 50
+    },
+    {
+      "epoch": 2.00836820083682,
+      "grad_norm": 0.4994066059589386,
+      "learning_rate": 4.999818897894192e-06,
+      "logits/chosen": 1.8359416723251343,
+      "logits/rejected": 1.814234733581543,
+      "logps/chosen": -79.98396301269531,
+      "logps/rejected": -66.29866027832031,
+      "loss": 0.6952,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.00456579215824604,
+      "rewards/margins": -0.002460189163684845,
+      "rewards/rejected": 0.007025980856269598,
+      "step": 60
+    },
+    {
+      "epoch": 2.3430962343096233,
+      "grad_norm": 0.6425362825393677,
+      "learning_rate": 4.9934830787948756e-06,
+      "logits/chosen": 1.7550818920135498,
+      "logits/rejected": 1.7802051305770874,
+      "logps/chosen": -83.60951232910156,
+      "logps/rejected": -70.81080627441406,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.004059882368892431,
+      "rewards/margins": 0.00932090263813734,
+      "rewards/rejected": -0.005261021666228771,
+      "step": 70
+    },
+    {
+      "epoch": 2.6778242677824267,
+      "grad_norm": 0.5591297149658203,
+      "learning_rate": 4.978118375700895e-06,
+      "logits/chosen": 1.7742525339126587,
+      "logits/rejected": 1.8790937662124634,
+      "logps/chosen": -86.7696533203125,
+      "logps/rejected": -84.90727233886719,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 0.0033963967580348253,
+      "rewards/margins": 0.005500240251421928,
+      "rewards/rejected": -0.0021038432605564594,
+      "step": 80
+    },
+    {
+      "epoch": 3.01255230125523,
+      "grad_norm": 0.6774541735649109,
+      "learning_rate": 4.953780424089803e-06,
+      "logits/chosen": 1.8815631866455078,
+      "logits/rejected": 1.911620855331421,
+      "logps/chosen": -92.14398193359375,
+      "logps/rejected": -82.83556365966797,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.007645039353519678,
+      "rewards/margins": 0.005134005565196276,
+      "rewards/rejected": 0.0025110342539846897,
+      "step": 90
+    },
+    {
+      "epoch": 3.3472803347280333,
+      "grad_norm": 0.6908814907073975,
+      "learning_rate": 4.920557351506409e-06,
+      "logits/chosen": 1.7718560695648193,
+      "logits/rejected": 1.8823477029800415,
+      "logps/chosen": -91.2622299194336,
+      "logps/rejected": -96.467529296875,
+      "loss": 0.6894,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.004941435065120459,
+      "rewards/margins": 0.01582186669111252,
+      "rewards/rejected": -0.010880433022975922,
+      "step": 100
+    },
+    {
+      "epoch": 3.6820083682008367,
+      "grad_norm": 0.6954344511032104,
+      "learning_rate": 4.878569458453592e-06,
+      "logits/chosen": 1.6916942596435547,
+      "logits/rejected": 1.7603965997695923,
+      "logps/chosen": -84.66748046875,
+      "logps/rejected": -103.5328369140625,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.003184904810041189,
+      "rewards/margins": 0.007628746330738068,
+      "rewards/rejected": -0.01081365067511797,
+      "step": 110
+    },
+    {
+      "epoch": 4.01673640167364,
+      "grad_norm": 0.6846771240234375,
+      "learning_rate": 4.827968782785062e-06,
+      "logits/chosen": 1.8839175701141357,
+      "logits/rejected": 1.956974744796753,
+      "logps/chosen": -76.89198303222656,
+      "logps/rejected": -95.03202056884766,
+      "loss": 0.6886,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.009448022581636906,
+      "rewards/margins": 0.018458742648363113,
+      "rewards/rejected": -0.009010720066726208,
+      "step": 120
+    },
+    {
+      "epoch": 4.351464435146443,
+      "grad_norm": 0.762366771697998,
+      "learning_rate": 4.7689385491773934e-06,
+      "logits/chosen": 1.8294252157211304,
+      "logits/rejected": 1.8144447803497314,
+      "logps/chosen": -87.03471374511719,
+      "logps/rejected": -73.86766052246094,
+      "loss": 0.6847,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.01010747067630291,
+      "rewards/margins": 0.01468165498226881,
+      "rewards/rejected": -0.024789121001958847,
+      "step": 130
+    },
+    {
+      "epoch": 4.686192468619247,
+      "grad_norm": 0.7172746658325195,
+      "learning_rate": 4.70169250567482e-06,
+      "logits/chosen": 1.7118749618530273,
+      "logits/rejected": 1.8259985446929932,
+      "logps/chosen": -68.12081146240234,
+      "logps/rejected": -75.31085205078125,
+      "loss": 0.6809,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.014076923951506615,
+      "rewards/margins": 0.014298361726105213,
+      "rewards/rejected": -0.028375286608934402,
+      "step": 140
+    },
+    {
+      "epoch": 5.02092050209205,
+      "grad_norm": 0.7188512682914734,
+      "learning_rate": 4.626474149709127e-06,
+      "logits/chosen": 1.8864549398422241,
+      "logits/rejected": 1.8488889932632446,
+      "logps/chosen": -101.3166275024414,
+      "logps/rejected": -76.73490905761719,
+      "loss": 0.6773,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.021979983896017075,
+      "rewards/margins": 0.023767748847603798,
+      "rewards/rejected": -0.04574773460626602,
+      "step": 150
+    },
+    {
+      "epoch": 5.355648535564853,
+      "grad_norm": 0.8493714928627014,
+      "learning_rate": 4.54355584639723e-06,
+      "logits/chosen": 1.7861169576644897,
+      "logits/rejected": 1.7927452325820923,
+      "logps/chosen": -83.28593444824219,
+      "logps/rejected": -76.04238891601562,
+      "loss": 0.673,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.0320693664252758,
+      "rewards/margins": 0.04263792932033539,
+      "rewards/rejected": -0.07470729202032089,
+      "step": 160
+    },
+    {
+      "epoch": 5.690376569037657,
+      "grad_norm": 1.1378726959228516,
+      "learning_rate": 4.45323784230908e-06,
+      "logits/chosen": 1.8622329235076904,
+      "logits/rejected": 1.875741958618164,
+      "logps/chosen": -72.01219177246094,
+      "logps/rejected": -77.62818908691406,
+      "loss": 0.6679,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.05134737491607666,
+      "rewards/margins": 0.049249742180109024,
+      "rewards/rejected": -0.10059712082147598,
+      "step": 170
+    },
+    {
+      "epoch": 6.02510460251046,
+      "grad_norm": 0.847227156162262,
+      "learning_rate": 4.355847178277025e-06,
+      "logits/chosen": 1.9445765018463135,
+      "logits/rejected": 2.0065901279449463,
+      "logps/chosen": -76.14964294433594,
+      "logps/rejected": -83.71626281738281,
+      "loss": 0.6621,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.05519520118832588,
+      "rewards/margins": 0.06803703308105469,
+      "rewards/rejected": -0.12323222309350967,
+      "step": 180
+    },
+    {
+      "epoch": 6.359832635983263,
+      "grad_norm": 0.8368040919303894,
+      "learning_rate": 4.2517365051833564e-06,
+      "logits/chosen": 1.8116003274917603,
+      "logits/rejected": 1.8839362859725952,
+      "logps/chosen": -82.7087631225586,
+      "logps/rejected": -67.3785629272461,
+      "loss": 0.6538,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.03855596110224724,
+      "rewards/margins": 0.11562293767929077,
+      "rewards/rejected": -0.15417888760566711,
+      "step": 190
+    },
+    {
+      "epoch": 6.694560669456067,
+      "grad_norm": 0.8636891841888428,
+      "learning_rate": 4.141282807014034e-06,
+      "logits/chosen": 1.7250430583953857,
+      "logits/rejected": 1.775418996810913,
+      "logps/chosen": -68.51094055175781,
+      "logps/rejected": -79.88996124267578,
+      "loss": 0.657,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.11151214689016342,
+      "rewards/margins": 0.07863004505634308,
+      "rewards/rejected": -0.1901421844959259,
+      "step": 200
+    },
+    {
+      "epoch": 7.02928870292887,
+      "grad_norm": 0.945520281791687,
+      "learning_rate": 4.024886035802432e-06,
+      "logits/chosen": 1.7329381704330444,
+      "logits/rejected": 1.799551010131836,
+      "logps/chosen": -81.49295043945312,
+      "logps/rejected": -87.97386169433594,
+      "loss": 0.6462,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.09862186014652252,
+      "rewards/margins": 0.10664049535989761,
+      "rewards/rejected": -0.20526234805583954,
+      "step": 210
+    },
+    {
+      "epoch": 7.364016736401673,
+      "grad_norm": 0.9736716151237488,
+      "learning_rate": 3.9029676634059565e-06,
+      "logits/chosen": 1.8787791728973389,
+      "logits/rejected": 1.8832632303237915,
+      "logps/chosen": -83.21014404296875,
+      "logps/rejected": -76.4449691772461,
+      "loss": 0.6413,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.07923021167516708,
+      "rewards/margins": 0.11194779723882675,
+      "rewards/rejected": -0.19117799401283264,
+      "step": 220
+    },
+    {
+      "epoch": 7.698744769874477,
+      "grad_norm": 0.9238549470901489,
+      "learning_rate": 3.7759691553595214e-06,
+      "logits/chosen": 1.9044986963272095,
+      "logits/rejected": 1.8805242776870728,
+      "logps/chosen": -90.17919158935547,
+      "logps/rejected": -86.05476379394531,
+      "loss": 0.6346,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.0993318110704422,
+      "rewards/margins": 0.12289313971996307,
+      "rewards/rejected": -0.22222498059272766,
+      "step": 230
+    },
+    {
+      "epoch": 8.03347280334728,
+      "grad_norm": 1.0052326917648315,
+      "learning_rate": 3.6443503723320837e-06,
+      "logits/chosen": 1.873815894126892,
+      "logits/rejected": 1.8809674978256226,
+      "logps/chosen": -74.86824035644531,
+      "logps/rejected": -81.79768371582031,
+      "loss": 0.6377,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.17602138221263885,
+      "rewards/margins": 0.09737586975097656,
+      "rewards/rejected": -0.2733972668647766,
+      "step": 240
+    },
+    {
+      "epoch": 8.368200836820083,
+      "grad_norm": 1.0167930126190186,
+      "learning_rate": 3.508587904974522e-06,
+      "logits/chosen": 1.868101716041565,
+      "logits/rejected": 1.8685039281845093,
+      "logps/chosen": -94.48133850097656,
+      "logps/rejected": -94.00556182861328,
+      "loss": 0.6216,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.1260211318731308,
+      "rewards/margins": 0.21002164483070374,
+      "rewards/rejected": -0.3360427916049957,
+      "step": 250
+    },
+    {
+      "epoch": 8.702928870292887,
+      "grad_norm": 0.9955905079841614,
+      "learning_rate": 3.3691733481883693e-06,
+      "logits/chosen": 1.7905946969985962,
+      "logits/rejected": 1.7784850597381592,
+      "logps/chosen": -94.9794921875,
+      "logps/rejected": -84.99113464355469,
+      "loss": 0.6193,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.18853916227817535,
+      "rewards/margins": 0.19185101985931396,
+      "rewards/rejected": -0.3803902268409729,
+      "step": 260
+    },
+    {
+      "epoch": 9.03765690376569,
+      "grad_norm": 0.943289577960968,
+      "learning_rate": 3.226611521064278e-06,
+      "logits/chosen": 1.8119779825210571,
+      "logits/rejected": 1.817567229270935,
+      "logps/chosen": -80.78002166748047,
+      "logps/rejected": -85.42848205566406,
+      "loss": 0.6201,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.16673071682453156,
+      "rewards/margins": 0.19530437886714935,
+      "rewards/rejected": -0.3620350658893585,
+      "step": 270
+    },
+    {
+      "epoch": 9.372384937238493,
+      "grad_norm": 0.9868927597999573,
+      "learning_rate": 3.0814186389357765e-06,
+      "logits/chosen": 1.816300392150879,
+      "logits/rejected": 1.7763961553573608,
+      "logps/chosen": -77.19395446777344,
+      "logps/rejected": -68.16056060791016,
+      "loss": 0.6157,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.21062004566192627,
+      "rewards/margins": 0.19489461183547974,
+      "rewards/rejected": -0.4055147171020508,
+      "step": 280
+    },
+    {
+      "epoch": 9.707112970711297,
+      "grad_norm": 1.0557409524917603,
+      "learning_rate": 2.9341204441673267e-06,
+      "logits/chosen": 1.8154022693634033,
+      "logits/rejected": 1.842792272567749,
+      "logps/chosen": -84.95299530029297,
+      "logps/rejected": -82.22926330566406,
+      "loss": 0.5972,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25716403126716614,
+      "rewards/margins": 0.2636396288871765,
+      "rewards/rejected": -0.5208036303520203,
+      "step": 290
+    },
+    {
+      "epoch": 10.0418410041841,
+      "grad_norm": 1.0787400007247925,
+      "learning_rate": 2.785250302445062e-06,
+      "logits/chosen": 1.8255424499511719,
+      "logits/rejected": 1.8123111724853516,
+      "logps/chosen": -94.89508056640625,
+      "logps/rejected": -99.48709869384766,
+      "loss": 0.6038,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25526899099349976,
+      "rewards/margins": 0.24981728196144104,
+      "rewards/rejected": -0.5050862431526184,
+      "step": 300
+    },
+    {
+      "epoch": 10.376569037656903,
+      "grad_norm": 0.9934303164482117,
+      "learning_rate": 2.6353472714635443e-06,
+      "logits/chosen": 1.6809011697769165,
+      "logits/rejected": 1.6883894205093384,
+      "logps/chosen": -83.52108001708984,
+      "logps/rejected": -89.83765411376953,
+      "loss": 0.5897,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.20843425393104553,
+      "rewards/margins": 0.2531076967716217,
+      "rewards/rejected": -0.46154195070266724,
+      "step": 310
+    },
+    {
+      "epoch": 10.711297071129707,
+      "grad_norm": 1.0989857912063599,
+      "learning_rate": 2.4849541490017868e-06,
+      "logits/chosen": 1.8184492588043213,
+      "logits/rejected": 1.8702239990234375,
+      "logps/chosen": -76.5416030883789,
+      "logps/rejected": -87.98771667480469,
+      "loss": 0.5951,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.26176151633262634,
+      "rewards/margins": 0.17908410727977753,
+      "rewards/rejected": -0.44084563851356506,
+      "step": 320
+    },
+    {
+      "epoch": 11.04602510460251,
+      "grad_norm": 1.1377506256103516,
+      "learning_rate": 2.3346155074564712e-06,
+      "logits/chosen": 1.7781150341033936,
+      "logits/rejected": 1.7945045232772827,
+      "logps/chosen": -94.21954345703125,
+      "logps/rejected": -87.9439926147461,
+      "loss": 0.5895,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.3070668578147888,
+      "rewards/margins": 0.26864537596702576,
+      "rewards/rejected": -0.5757122039794922,
+      "step": 330
+    },
+    {
+      "epoch": 11.380753138075313,
+      "grad_norm": 1.1378768682479858,
+      "learning_rate": 2.184875721949277e-06,
+      "logits/chosen": 1.7889184951782227,
+      "logits/rejected": 1.7863588333129883,
+      "logps/chosen": -77.19974517822266,
+      "logps/rejected": -74.92039489746094,
+      "loss": 0.577,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.2269454449415207,
+      "rewards/margins": 0.3004661798477173,
+      "rewards/rejected": -0.5274116396903992,
+      "step": 340
+    },
+    {
+      "epoch": 11.715481171548117,
+      "grad_norm": 1.0102859735488892,
+      "learning_rate": 2.0362769991485514e-06,
+      "logits/chosen": 1.6868798732757568,
+      "logits/rejected": 1.743287444114685,
+      "logps/chosen": -80.24299621582031,
+      "logps/rejected": -91.3736343383789,
+      "loss": 0.5825,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2850210964679718,
+      "rewards/margins": 0.30632922053337097,
+      "rewards/rejected": -0.5913503170013428,
+      "step": 350
+    },
+    {
+      "epoch": 12.05020920502092,
+      "grad_norm": 1.0598143339157104,
+      "learning_rate": 1.8893574139429226e-06,
+      "logits/chosen": 1.6859172582626343,
+      "logits/rejected": 1.7635313272476196,
+      "logps/chosen": -88.87372589111328,
+      "logps/rejected": -93.02122497558594,
+      "loss": 0.5819,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.317017138004303,
+      "rewards/margins": 0.2608889639377594,
+      "rewards/rejected": -0.5779060125350952,
+      "step": 360
+    },
+    {
+      "epoch": 12.384937238493723,
+      "grad_norm": 1.0845669507980347,
+      "learning_rate": 1.744648961076068e-06,
+      "logits/chosen": 1.7980632781982422,
+      "logits/rejected": 1.8205795288085938,
+      "logps/chosen": -83.31995391845703,
+      "logps/rejected": -87.28046417236328,
+      "loss": 0.5737,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.3205794394016266,
+      "rewards/margins": 0.24214692413806915,
+      "rewards/rejected": -0.5627263784408569,
+      "step": 370
+    },
+    {
+      "epoch": 12.719665271966527,
+      "grad_norm": 1.180468201637268,
+      "learning_rate": 1.602675628797636e-06,
+      "logits/chosen": 1.8093292713165283,
+      "logits/rejected": 1.8195394277572632,
+      "logps/chosen": -99.64051055908203,
+      "logps/rejected": -82.13116455078125,
+      "loss": 0.5655,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.28717803955078125,
+      "rewards/margins": 0.355060875415802,
+      "rewards/rejected": -0.6422389149665833,
+      "step": 380
+    },
+    {
+      "epoch": 13.05439330543933,
+      "grad_norm": 1.0443357229232788,
+      "learning_rate": 1.4639515015056205e-06,
+      "logits/chosen": 1.7365925312042236,
+      "logits/rejected": 1.7514903545379639,
+      "logps/chosen": -96.92813110351562,
+      "logps/rejected": -83.5425796508789,
+      "loss": 0.5654,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3064219653606415,
+      "rewards/margins": 0.38930463790893555,
+      "rewards/rejected": -0.6957265138626099,
+      "step": 390
+    },
+    {
+      "epoch": 13.389121338912133,
+      "grad_norm": 1.2010602951049805,
+      "learning_rate": 1.328978898250525e-06,
+      "logits/chosen": 1.7649974822998047,
+      "logits/rejected": 1.7864068746566772,
+      "logps/chosen": -78.26787567138672,
+      "logps/rejected": -82.81205749511719,
+      "loss": 0.5713,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.32541388273239136,
+      "rewards/margins": 0.34498968720436096,
+      "rewards/rejected": -0.6704035997390747,
+      "step": 400
+    },
+    {
+      "epoch": 13.723849372384937,
+      "grad_norm": 1.656805396080017,
+      "learning_rate": 1.198246553841744e-06,
+      "logits/chosen": 1.6543798446655273,
+      "logits/rejected": 1.700377106666565,
+      "logps/chosen": -88.14425659179688,
+      "logps/rejected": -86.7034912109375,
+      "loss": 0.5569,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.307409405708313,
+      "rewards/margins": 0.346424400806427,
+      "rewards/rejected": -0.65383380651474,
+      "step": 410
+    },
+    {
+      "epoch": 14.05857740585774,
+      "grad_norm": 1.3017597198486328,
+      "learning_rate": 1.0722278491423998e-06,
+      "logits/chosen": 1.861400842666626,
+      "logits/rejected": 1.7919048070907593,
+      "logps/chosen": -101.43531036376953,
+      "logps/rejected": -77.99034881591797,
+      "loss": 0.567,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.34600889682769775,
+      "rewards/margins": 0.2590746283531189,
+      "rewards/rejected": -0.6050835251808167,
+      "step": 420
+    },
+    {
+      "epoch": 14.393305439330543,
+      "grad_norm": 1.0269688367843628,
+      "learning_rate": 9.513790969606926e-07,
+      "logits/chosen": 1.809483289718628,
+      "logits/rejected": 1.8456366062164307,
+      "logps/chosen": -102.51566314697266,
+      "logps/rejected": -104.2486343383789,
+      "loss": 0.5605,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.33636271953582764,
+      "rewards/margins": 0.3720197379589081,
+      "rewards/rejected": -0.7083825469017029,
+      "step": 430
+    },
+    {
+      "epoch": 14.728033472803347,
+      "grad_norm": 1.0176596641540527,
+      "learning_rate": 8.361378897445643e-07,
+      "logits/chosen": 1.8125699758529663,
+      "logits/rejected": 1.819248914718628,
+      "logps/chosen": -83.56723022460938,
+      "logps/rejected": -81.31576538085938,
+      "loss": 0.5549,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.321399986743927,
+      "rewards/margins": 0.2679772973060608,
+      "rewards/rejected": -0.5893772840499878,
+      "step": 440
+    },
+    {
+      "epoch": 15.06276150627615,
+      "grad_norm": 1.1313916444778442,
+      "learning_rate": 7.269215150626391e-07,
+      "logits/chosen": 1.7356494665145874,
+      "logits/rejected": 1.793581247329712,
+      "logps/chosen": -80.0768051147461,
+      "logps/rejected": -79.23683166503906,
+      "loss": 0.5606,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.34324222803115845,
+      "rewards/margins": 0.3662562370300293,
+      "rewards/rejected": -0.7094983458518982,
+      "step": 450
+    },
+    {
+      "epoch": 15.397489539748953,
+      "grad_norm": 1.1418852806091309,
+      "learning_rate": 6.241254446089942e-07,
+      "logits/chosen": 1.7430709600448608,
+      "logits/rejected": 1.7953869104385376,
+      "logps/chosen": -82.4347152709961,
+      "logps/rejected": -82.4286880493164,
+      "loss": 0.5545,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.3615425229072571,
+      "rewards/margins": 0.35559993982315063,
+      "rewards/rejected": -0.7171424031257629,
+      "step": 460
+    },
+    {
+      "epoch": 15.732217573221757,
+      "grad_norm": 1.1025134325027466,
+      "learning_rate": 5.281219022030423e-07,
+      "logits/chosen": 1.655470848083496,
+      "logits/rejected": 1.692399024963379,
+      "logps/chosen": -101.62381744384766,
+      "logps/rejected": -96.6092300415039,
+      "loss": 0.5525,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.29976749420166016,
+      "rewards/margins": 0.3946015238761902,
+      "rewards/rejected": -0.6943690776824951,
+      "step": 470
+    },
+    {
+      "epoch": 16.06694560669456,
+      "grad_norm": 1.2202156782150269,
+      "learning_rate": 4.392585159698087e-07,
+      "logits/chosen": 1.7376701831817627,
+      "logits/rejected": 1.793471097946167,
+      "logps/chosen": -89.61154174804688,
+      "logps/rejected": -94.71632385253906,
+      "loss": 0.5499,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.31332069635391235,
+      "rewards/margins": 0.4189217984676361,
+      "rewards/rejected": -0.7322424650192261,
+      "step": 480
+    },
+    {
+      "epoch": 16.401673640167363,
+      "grad_norm": 1.1149810552597046,
+      "learning_rate": 3.578570595810274e-07,
+      "logits/chosen": 1.7718391418457031,
+      "logits/rejected": 1.8273475170135498,
+      "logps/chosen": -83.96971130371094,
+      "logps/rejected": -92.80200958251953,
+      "loss": 0.5471,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.2852213978767395,
+      "rewards/margins": 0.3351207673549652,
+      "rewards/rejected": -0.6203421354293823,
+      "step": 490
+    },
+    {
+      "epoch": 16.736401673640167,
+      "grad_norm": 1.0757339000701904,
+      "learning_rate": 2.8421228711503127e-07,
+      "logits/chosen": 1.7726856470108032,
+      "logits/rejected": 1.836022973060608,
+      "logps/chosen": -78.27845764160156,
+      "logps/rejected": -83.48805236816406,
+      "loss": 0.5539,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.34817034006118774,
+      "rewards/margins": 0.2852809429168701,
+      "rewards/rejected": -0.6334512829780579,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 580,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7029183778293023e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Area/checkpoint-550/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Area/checkpoint-550/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Area/checkpoint-550/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Area/checkpoint-550/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Area/checkpoint-550/trainer_state.json

@@ -0,0 +1,858 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 18.410041841004183,
+  "eval_steps": 500,
+  "global_step": 550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 0.4676998555660248,
+      "learning_rate": 8.620689655172415e-07,
+      "logits/chosen": 1.7077701091766357,
+      "logits/rejected": 1.8646482229232788,
+      "logps/chosen": -85.7728271484375,
+      "logps/rejected": -88.1952896118164,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": -0.004770822823047638,
+      "rewards/margins": -0.007881464436650276,
+      "rewards/rejected": 0.0031106427777558565,
+      "step": 10
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 0.43230223655700684,
+      "learning_rate": 1.724137931034483e-06,
+      "logits/chosen": 1.8023220300674438,
+      "logits/rejected": 1.8210970163345337,
+      "logps/chosen": -78.37618255615234,
+      "logps/rejected": -75.44720458984375,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.0056939031928777695,
+      "rewards/margins": -0.003848772030323744,
+      "rewards/rejected": -0.001845130929723382,
+      "step": 20
+    },
+    {
+      "epoch": 1.00418410041841,
+      "grad_norm": 2.431753396987915,
+      "learning_rate": 2.5862068965517246e-06,
+      "logits/chosen": 1.8643144369125366,
+      "logits/rejected": 1.8500900268554688,
+      "logps/chosen": -86.84412384033203,
+      "logps/rejected": -90.78925323486328,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.0008674233104102314,
+      "rewards/margins": -0.008064134046435356,
+      "rewards/rejected": 0.0071967123076319695,
+      "step": 30
+    },
+    {
+      "epoch": 1.3389121338912133,
+      "grad_norm": 0.5327289700508118,
+      "learning_rate": 3.448275862068966e-06,
+      "logits/chosen": 1.7701479196548462,
+      "logits/rejected": 1.7749736309051514,
+      "logps/chosen": -83.61552429199219,
+      "logps/rejected": -72.89176177978516,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -0.0019066383829340339,
+      "rewards/margins": -0.0035008196718990803,
+      "rewards/rejected": 0.0015941811725497246,
+      "step": 40
+    },
+    {
+      "epoch": 1.6736401673640167,
+      "grad_norm": 0.5017096996307373,
+      "learning_rate": 4.310344827586207e-06,
+      "logits/chosen": 1.7465788125991821,
+      "logits/rejected": 1.7925498485565186,
+      "logps/chosen": -84.85249328613281,
+      "logps/rejected": -88.79469299316406,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 0.0003656863118521869,
+      "rewards/margins": 0.00012080222222721204,
+      "rewards/rejected": 0.00024488387862220407,
+      "step": 50
+    },
+    {
+      "epoch": 2.00836820083682,
+      "grad_norm": 0.4994066059589386,
+      "learning_rate": 4.999818897894192e-06,
+      "logits/chosen": 1.8359416723251343,
+      "logits/rejected": 1.814234733581543,
+      "logps/chosen": -79.98396301269531,
+      "logps/rejected": -66.29866027832031,
+      "loss": 0.6952,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.00456579215824604,
+      "rewards/margins": -0.002460189163684845,
+      "rewards/rejected": 0.007025980856269598,
+      "step": 60
+    },
+    {
+      "epoch": 2.3430962343096233,
+      "grad_norm": 0.6425362825393677,
+      "learning_rate": 4.9934830787948756e-06,
+      "logits/chosen": 1.7550818920135498,
+      "logits/rejected": 1.7802051305770874,
+      "logps/chosen": -83.60951232910156,
+      "logps/rejected": -70.81080627441406,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.004059882368892431,
+      "rewards/margins": 0.00932090263813734,
+      "rewards/rejected": -0.005261021666228771,
+      "step": 70
+    },
+    {
+      "epoch": 2.6778242677824267,
+      "grad_norm": 0.5591297149658203,
+      "learning_rate": 4.978118375700895e-06,
+      "logits/chosen": 1.7742525339126587,
+      "logits/rejected": 1.8790937662124634,
+      "logps/chosen": -86.7696533203125,
+      "logps/rejected": -84.90727233886719,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 0.0033963967580348253,
+      "rewards/margins": 0.005500240251421928,
+      "rewards/rejected": -0.0021038432605564594,
+      "step": 80
+    },
+    {
+      "epoch": 3.01255230125523,
+      "grad_norm": 0.6774541735649109,
+      "learning_rate": 4.953780424089803e-06,
+      "logits/chosen": 1.8815631866455078,
+      "logits/rejected": 1.911620855331421,
+      "logps/chosen": -92.14398193359375,
+      "logps/rejected": -82.83556365966797,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.007645039353519678,
+      "rewards/margins": 0.005134005565196276,
+      "rewards/rejected": 0.0025110342539846897,
+      "step": 90
+    },
+    {
+      "epoch": 3.3472803347280333,
+      "grad_norm": 0.6908814907073975,
+      "learning_rate": 4.920557351506409e-06,
+      "logits/chosen": 1.7718560695648193,
+      "logits/rejected": 1.8823477029800415,
+      "logps/chosen": -91.2622299194336,
+      "logps/rejected": -96.467529296875,
+      "loss": 0.6894,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.004941435065120459,
+      "rewards/margins": 0.01582186669111252,
+      "rewards/rejected": -0.010880433022975922,
+      "step": 100
+    },
+    {
+      "epoch": 3.6820083682008367,
+      "grad_norm": 0.6954344511032104,
+      "learning_rate": 4.878569458453592e-06,
+      "logits/chosen": 1.6916942596435547,
+      "logits/rejected": 1.7603965997695923,
+      "logps/chosen": -84.66748046875,
+      "logps/rejected": -103.5328369140625,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.003184904810041189,
+      "rewards/margins": 0.007628746330738068,
+      "rewards/rejected": -0.01081365067511797,
+      "step": 110
+    },
+    {
+      "epoch": 4.01673640167364,
+      "grad_norm": 0.6846771240234375,
+      "learning_rate": 4.827968782785062e-06,
+      "logits/chosen": 1.8839175701141357,
+      "logits/rejected": 1.956974744796753,
+      "logps/chosen": -76.89198303222656,
+      "logps/rejected": -95.03202056884766,
+      "loss": 0.6886,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.009448022581636906,
+      "rewards/margins": 0.018458742648363113,
+      "rewards/rejected": -0.009010720066726208,
+      "step": 120
+    },
+    {
+      "epoch": 4.351464435146443,
+      "grad_norm": 0.762366771697998,
+      "learning_rate": 4.7689385491773934e-06,
+      "logits/chosen": 1.8294252157211304,
+      "logits/rejected": 1.8144447803497314,
+      "logps/chosen": -87.03471374511719,
+      "logps/rejected": -73.86766052246094,
+      "loss": 0.6847,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.01010747067630291,
+      "rewards/margins": 0.01468165498226881,
+      "rewards/rejected": -0.024789121001958847,
+      "step": 130
+    },
+    {
+      "epoch": 4.686192468619247,
+      "grad_norm": 0.7172746658325195,
+      "learning_rate": 4.70169250567482e-06,
+      "logits/chosen": 1.7118749618530273,
+      "logits/rejected": 1.8259985446929932,
+      "logps/chosen": -68.12081146240234,
+      "logps/rejected": -75.31085205078125,
+      "loss": 0.6809,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.014076923951506615,
+      "rewards/margins": 0.014298361726105213,
+      "rewards/rejected": -0.028375286608934402,
+      "step": 140
+    },
+    {
+      "epoch": 5.02092050209205,
+      "grad_norm": 0.7188512682914734,
+      "learning_rate": 4.626474149709127e-06,
+      "logits/chosen": 1.8864549398422241,
+      "logits/rejected": 1.8488889932632446,
+      "logps/chosen": -101.3166275024414,
+      "logps/rejected": -76.73490905761719,
+      "loss": 0.6773,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.021979983896017075,
+      "rewards/margins": 0.023767748847603798,
+      "rewards/rejected": -0.04574773460626602,
+      "step": 150
+    },
+    {
+      "epoch": 5.355648535564853,
+      "grad_norm": 0.8493714928627014,
+      "learning_rate": 4.54355584639723e-06,
+      "logits/chosen": 1.7861169576644897,
+      "logits/rejected": 1.7927452325820923,
+      "logps/chosen": -83.28593444824219,
+      "logps/rejected": -76.04238891601562,
+      "loss": 0.673,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.0320693664252758,
+      "rewards/margins": 0.04263792932033539,
+      "rewards/rejected": -0.07470729202032089,
+      "step": 160
+    },
+    {
+      "epoch": 5.690376569037657,
+      "grad_norm": 1.1378726959228516,
+      "learning_rate": 4.45323784230908e-06,
+      "logits/chosen": 1.8622329235076904,
+      "logits/rejected": 1.875741958618164,
+      "logps/chosen": -72.01219177246094,
+      "logps/rejected": -77.62818908691406,
+      "loss": 0.6679,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.05134737491607666,
+      "rewards/margins": 0.049249742180109024,
+      "rewards/rejected": -0.10059712082147598,
+      "step": 170
+    },
+    {
+      "epoch": 6.02510460251046,
+      "grad_norm": 0.847227156162262,
+      "learning_rate": 4.355847178277025e-06,
+      "logits/chosen": 1.9445765018463135,
+      "logits/rejected": 2.0065901279449463,
+      "logps/chosen": -76.14964294433594,
+      "logps/rejected": -83.71626281738281,
+      "loss": 0.6621,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.05519520118832588,
+      "rewards/margins": 0.06803703308105469,
+      "rewards/rejected": -0.12323222309350967,
+      "step": 180
+    },
+    {
+      "epoch": 6.359832635983263,
+      "grad_norm": 0.8368040919303894,
+      "learning_rate": 4.2517365051833564e-06,
+      "logits/chosen": 1.8116003274917603,
+      "logits/rejected": 1.8839362859725952,
+      "logps/chosen": -82.7087631225586,
+      "logps/rejected": -67.3785629272461,
+      "loss": 0.6538,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.03855596110224724,
+      "rewards/margins": 0.11562293767929077,
+      "rewards/rejected": -0.15417888760566711,
+      "step": 190
+    },
+    {
+      "epoch": 6.694560669456067,
+      "grad_norm": 0.8636891841888428,
+      "learning_rate": 4.141282807014034e-06,
+      "logits/chosen": 1.7250430583953857,
+      "logits/rejected": 1.775418996810913,
+      "logps/chosen": -68.51094055175781,
+      "logps/rejected": -79.88996124267578,
+      "loss": 0.657,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.11151214689016342,
+      "rewards/margins": 0.07863004505634308,
+      "rewards/rejected": -0.1901421844959259,
+      "step": 200
+    },
+    {
+      "epoch": 7.02928870292887,
+      "grad_norm": 0.945520281791687,
+      "learning_rate": 4.024886035802432e-06,
+      "logits/chosen": 1.7329381704330444,
+      "logits/rejected": 1.799551010131836,
+      "logps/chosen": -81.49295043945312,
+      "logps/rejected": -87.97386169433594,
+      "loss": 0.6462,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.09862186014652252,
+      "rewards/margins": 0.10664049535989761,
+      "rewards/rejected": -0.20526234805583954,
+      "step": 210
+    },
+    {
+      "epoch": 7.364016736401673,
+      "grad_norm": 0.9736716151237488,
+      "learning_rate": 3.9029676634059565e-06,
+      "logits/chosen": 1.8787791728973389,
+      "logits/rejected": 1.8832632303237915,
+      "logps/chosen": -83.21014404296875,
+      "logps/rejected": -76.4449691772461,
+      "loss": 0.6413,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.07923021167516708,
+      "rewards/margins": 0.11194779723882675,
+      "rewards/rejected": -0.19117799401283264,
+      "step": 220
+    },
+    {
+      "epoch": 7.698744769874477,
+      "grad_norm": 0.9238549470901489,
+      "learning_rate": 3.7759691553595214e-06,
+      "logits/chosen": 1.9044986963272095,
+      "logits/rejected": 1.8805242776870728,
+      "logps/chosen": -90.17919158935547,
+      "logps/rejected": -86.05476379394531,
+      "loss": 0.6346,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.0993318110704422,
+      "rewards/margins": 0.12289313971996307,
+      "rewards/rejected": -0.22222498059272766,
+      "step": 230
+    },
+    {
+      "epoch": 8.03347280334728,
+      "grad_norm": 1.0052326917648315,
+      "learning_rate": 3.6443503723320837e-06,
+      "logits/chosen": 1.873815894126892,
+      "logits/rejected": 1.8809674978256226,
+      "logps/chosen": -74.86824035644531,
+      "logps/rejected": -81.79768371582031,
+      "loss": 0.6377,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.17602138221263885,
+      "rewards/margins": 0.09737586975097656,
+      "rewards/rejected": -0.2733972668647766,
+      "step": 240
+    },
+    {
+      "epoch": 8.368200836820083,
+      "grad_norm": 1.0167930126190186,
+      "learning_rate": 3.508587904974522e-06,
+      "logits/chosen": 1.868101716041565,
+      "logits/rejected": 1.8685039281845093,
+      "logps/chosen": -94.48133850097656,
+      "logps/rejected": -94.00556182861328,
+      "loss": 0.6216,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.1260211318731308,
+      "rewards/margins": 0.21002164483070374,
+      "rewards/rejected": -0.3360427916049957,
+      "step": 250
+    },
+    {
+      "epoch": 8.702928870292887,
+      "grad_norm": 0.9955905079841614,
+      "learning_rate": 3.3691733481883693e-06,
+      "logits/chosen": 1.7905946969985962,
+      "logits/rejected": 1.7784850597381592,
+      "logps/chosen": -94.9794921875,
+      "logps/rejected": -84.99113464355469,
+      "loss": 0.6193,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.18853916227817535,
+      "rewards/margins": 0.19185101985931396,
+      "rewards/rejected": -0.3803902268409729,
+      "step": 260
+    },
+    {
+      "epoch": 9.03765690376569,
+      "grad_norm": 0.943289577960968,
+      "learning_rate": 3.226611521064278e-06,
+      "logits/chosen": 1.8119779825210571,
+      "logits/rejected": 1.817567229270935,
+      "logps/chosen": -80.78002166748047,
+      "logps/rejected": -85.42848205566406,
+      "loss": 0.6201,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.16673071682453156,
+      "rewards/margins": 0.19530437886714935,
+      "rewards/rejected": -0.3620350658893585,
+      "step": 270
+    },
+    {
+      "epoch": 9.372384937238493,
+      "grad_norm": 0.9868927597999573,
+      "learning_rate": 3.0814186389357765e-06,
+      "logits/chosen": 1.816300392150879,
+      "logits/rejected": 1.7763961553573608,
+      "logps/chosen": -77.19395446777344,
+      "logps/rejected": -68.16056060791016,
+      "loss": 0.6157,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.21062004566192627,
+      "rewards/margins": 0.19489461183547974,
+      "rewards/rejected": -0.4055147171020508,
+      "step": 280
+    },
+    {
+      "epoch": 9.707112970711297,
+      "grad_norm": 1.0557409524917603,
+      "learning_rate": 2.9341204441673267e-06,
+      "logits/chosen": 1.8154022693634033,
+      "logits/rejected": 1.842792272567749,
+      "logps/chosen": -84.95299530029297,
+      "logps/rejected": -82.22926330566406,
+      "loss": 0.5972,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25716403126716614,
+      "rewards/margins": 0.2636396288871765,
+      "rewards/rejected": -0.5208036303520203,
+      "step": 290
+    },
+    {
+      "epoch": 10.0418410041841,
+      "grad_norm": 1.0787400007247925,
+      "learning_rate": 2.785250302445062e-06,
+      "logits/chosen": 1.8255424499511719,
+      "logits/rejected": 1.8123111724853516,
+      "logps/chosen": -94.89508056640625,
+      "logps/rejected": -99.48709869384766,
+      "loss": 0.6038,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25526899099349976,
+      "rewards/margins": 0.24981728196144104,
+      "rewards/rejected": -0.5050862431526184,
+      "step": 300
+    },
+    {
+      "epoch": 10.376569037656903,
+      "grad_norm": 0.9934303164482117,
+      "learning_rate": 2.6353472714635443e-06,
+      "logits/chosen": 1.6809011697769165,
+      "logits/rejected": 1.6883894205093384,
+      "logps/chosen": -83.52108001708984,
+      "logps/rejected": -89.83765411376953,
+      "loss": 0.5897,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.20843425393104553,
+      "rewards/margins": 0.2531076967716217,
+      "rewards/rejected": -0.46154195070266724,
+      "step": 310
+    },
+    {
+      "epoch": 10.711297071129707,
+      "grad_norm": 1.0989857912063599,
+      "learning_rate": 2.4849541490017868e-06,
+      "logits/chosen": 1.8184492588043213,
+      "logits/rejected": 1.8702239990234375,
+      "logps/chosen": -76.5416030883789,
+      "logps/rejected": -87.98771667480469,
+      "loss": 0.5951,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.26176151633262634,
+      "rewards/margins": 0.17908410727977753,
+      "rewards/rejected": -0.44084563851356506,
+      "step": 320
+    },
+    {
+      "epoch": 11.04602510460251,
+      "grad_norm": 1.1377506256103516,
+      "learning_rate": 2.3346155074564712e-06,
+      "logits/chosen": 1.7781150341033936,
+      "logits/rejected": 1.7945045232772827,
+      "logps/chosen": -94.21954345703125,
+      "logps/rejected": -87.9439926147461,
+      "loss": 0.5895,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.3070668578147888,
+      "rewards/margins": 0.26864537596702576,
+      "rewards/rejected": -0.5757122039794922,
+      "step": 330
+    },
+    {
+      "epoch": 11.380753138075313,
+      "grad_norm": 1.1378768682479858,
+      "learning_rate": 2.184875721949277e-06,
+      "logits/chosen": 1.7889184951782227,
+      "logits/rejected": 1.7863588333129883,
+      "logps/chosen": -77.19974517822266,
+      "logps/rejected": -74.92039489746094,
+      "loss": 0.577,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.2269454449415207,
+      "rewards/margins": 0.3004661798477173,
+      "rewards/rejected": -0.5274116396903992,
+      "step": 340
+    },
+    {
+      "epoch": 11.715481171548117,
+      "grad_norm": 1.0102859735488892,
+      "learning_rate": 2.0362769991485514e-06,
+      "logits/chosen": 1.6868798732757568,
+      "logits/rejected": 1.743287444114685,
+      "logps/chosen": -80.24299621582031,
+      "logps/rejected": -91.3736343383789,
+      "loss": 0.5825,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2850210964679718,
+      "rewards/margins": 0.30632922053337097,
+      "rewards/rejected": -0.5913503170013428,
+      "step": 350
+    },
+    {
+      "epoch": 12.05020920502092,
+      "grad_norm": 1.0598143339157104,
+      "learning_rate": 1.8893574139429226e-06,
+      "logits/chosen": 1.6859172582626343,
+      "logits/rejected": 1.7635313272476196,
+      "logps/chosen": -88.87372589111328,
+      "logps/rejected": -93.02122497558594,
+      "loss": 0.5819,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.317017138004303,
+      "rewards/margins": 0.2608889639377594,
+      "rewards/rejected": -0.5779060125350952,
+      "step": 360
+    },
+    {
+      "epoch": 12.384937238493723,
+      "grad_norm": 1.0845669507980347,
+      "learning_rate": 1.744648961076068e-06,
+      "logits/chosen": 1.7980632781982422,
+      "logits/rejected": 1.8205795288085938,
+      "logps/chosen": -83.31995391845703,
+      "logps/rejected": -87.28046417236328,
+      "loss": 0.5737,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.3205794394016266,
+      "rewards/margins": 0.24214692413806915,
+      "rewards/rejected": -0.5627263784408569,
+      "step": 370
+    },
+    {
+      "epoch": 12.719665271966527,
+      "grad_norm": 1.180468201637268,
+      "learning_rate": 1.602675628797636e-06,
+      "logits/chosen": 1.8093292713165283,
+      "logits/rejected": 1.8195394277572632,
+      "logps/chosen": -99.64051055908203,
+      "logps/rejected": -82.13116455078125,
+      "loss": 0.5655,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.28717803955078125,
+      "rewards/margins": 0.355060875415802,
+      "rewards/rejected": -0.6422389149665833,
+      "step": 380
+    },
+    {
+      "epoch": 13.05439330543933,
+      "grad_norm": 1.0443357229232788,
+      "learning_rate": 1.4639515015056205e-06,
+      "logits/chosen": 1.7365925312042236,
+      "logits/rejected": 1.7514903545379639,
+      "logps/chosen": -96.92813110351562,
+      "logps/rejected": -83.5425796508789,
+      "loss": 0.5654,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3064219653606415,
+      "rewards/margins": 0.38930463790893555,
+      "rewards/rejected": -0.6957265138626099,
+      "step": 390
+    },
+    {
+      "epoch": 13.389121338912133,
+      "grad_norm": 1.2010602951049805,
+      "learning_rate": 1.328978898250525e-06,
+      "logits/chosen": 1.7649974822998047,
+      "logits/rejected": 1.7864068746566772,
+      "logps/chosen": -78.26787567138672,
+      "logps/rejected": -82.81205749511719,
+      "loss": 0.5713,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.32541388273239136,
+      "rewards/margins": 0.34498968720436096,
+      "rewards/rejected": -0.6704035997390747,
+      "step": 400
+    },
+    {
+      "epoch": 13.723849372384937,
+      "grad_norm": 1.656805396080017,
+      "learning_rate": 1.198246553841744e-06,
+      "logits/chosen": 1.6543798446655273,
+      "logits/rejected": 1.700377106666565,
+      "logps/chosen": -88.14425659179688,
+      "logps/rejected": -86.7034912109375,
+      "loss": 0.5569,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.307409405708313,
+      "rewards/margins": 0.346424400806427,
+      "rewards/rejected": -0.65383380651474,
+      "step": 410
+    },
+    {
+      "epoch": 14.05857740585774,
+      "grad_norm": 1.3017597198486328,
+      "learning_rate": 1.0722278491423998e-06,
+      "logits/chosen": 1.861400842666626,
+      "logits/rejected": 1.7919048070907593,
+      "logps/chosen": -101.43531036376953,
+      "logps/rejected": -77.99034881591797,
+      "loss": 0.567,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.34600889682769775,
+      "rewards/margins": 0.2590746283531189,
+      "rewards/rejected": -0.6050835251808167,
+      "step": 420
+    },
+    {
+      "epoch": 14.393305439330543,
+      "grad_norm": 1.0269688367843628,
+      "learning_rate": 9.513790969606926e-07,
+      "logits/chosen": 1.809483289718628,
+      "logits/rejected": 1.8456366062164307,
+      "logps/chosen": -102.51566314697266,
+      "logps/rejected": -104.2486343383789,
+      "loss": 0.5605,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.33636271953582764,
+      "rewards/margins": 0.3720197379589081,
+      "rewards/rejected": -0.7083825469017029,
+      "step": 430
+    },
+    {
+      "epoch": 14.728033472803347,
+      "grad_norm": 1.0176596641540527,
+      "learning_rate": 8.361378897445643e-07,
+      "logits/chosen": 1.8125699758529663,
+      "logits/rejected": 1.819248914718628,
+      "logps/chosen": -83.56723022460938,
+      "logps/rejected": -81.31576538085938,
+      "loss": 0.5549,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.321399986743927,
+      "rewards/margins": 0.2679772973060608,
+      "rewards/rejected": -0.5893772840499878,
+      "step": 440
+    },
+    {
+      "epoch": 15.06276150627615,
+      "grad_norm": 1.1313916444778442,
+      "learning_rate": 7.269215150626391e-07,
+      "logits/chosen": 1.7356494665145874,
+      "logits/rejected": 1.793581247329712,
+      "logps/chosen": -80.0768051147461,
+      "logps/rejected": -79.23683166503906,
+      "loss": 0.5606,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.34324222803115845,
+      "rewards/margins": 0.3662562370300293,
+      "rewards/rejected": -0.7094983458518982,
+      "step": 450
+    },
+    {
+      "epoch": 15.397489539748953,
+      "grad_norm": 1.1418852806091309,
+      "learning_rate": 6.241254446089942e-07,
+      "logits/chosen": 1.7430709600448608,
+      "logits/rejected": 1.7953869104385376,
+      "logps/chosen": -82.4347152709961,
+      "logps/rejected": -82.4286880493164,
+      "loss": 0.5545,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.3615425229072571,
+      "rewards/margins": 0.35559993982315063,
+      "rewards/rejected": -0.7171424031257629,
+      "step": 460
+    },
+    {
+      "epoch": 15.732217573221757,
+      "grad_norm": 1.1025134325027466,
+      "learning_rate": 5.281219022030423e-07,
+      "logits/chosen": 1.655470848083496,
+      "logits/rejected": 1.692399024963379,
+      "logps/chosen": -101.62381744384766,
+      "logps/rejected": -96.6092300415039,
+      "loss": 0.5525,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.29976749420166016,
+      "rewards/margins": 0.3946015238761902,
+      "rewards/rejected": -0.6943690776824951,
+      "step": 470
+    },
+    {
+      "epoch": 16.06694560669456,
+      "grad_norm": 1.2202156782150269,
+      "learning_rate": 4.392585159698087e-07,
+      "logits/chosen": 1.7376701831817627,
+      "logits/rejected": 1.793471097946167,
+      "logps/chosen": -89.61154174804688,
+      "logps/rejected": -94.71632385253906,
+      "loss": 0.5499,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.31332069635391235,
+      "rewards/margins": 0.4189217984676361,
+      "rewards/rejected": -0.7322424650192261,
+      "step": 480
+    },
+    {
+      "epoch": 16.401673640167363,
+      "grad_norm": 1.1149810552597046,
+      "learning_rate": 3.578570595810274e-07,
+      "logits/chosen": 1.7718391418457031,
+      "logits/rejected": 1.8273475170135498,
+      "logps/chosen": -83.96971130371094,
+      "logps/rejected": -92.80200958251953,
+      "loss": 0.5471,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.2852213978767395,
+      "rewards/margins": 0.3351207673549652,
+      "rewards/rejected": -0.6203421354293823,
+      "step": 490
+    },
+    {
+      "epoch": 16.736401673640167,
+      "grad_norm": 1.0757339000701904,
+      "learning_rate": 2.8421228711503127e-07,
+      "logits/chosen": 1.7726856470108032,
+      "logits/rejected": 1.836022973060608,
+      "logps/chosen": -78.27845764160156,
+      "logps/rejected": -83.48805236816406,
+      "loss": 0.5539,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.34817034006118774,
+      "rewards/margins": 0.2852809429168701,
+      "rewards/rejected": -0.6334512829780579,
+      "step": 500
+    },
+    {
+      "epoch": 17.07112970711297,
+      "grad_norm": 1.1488370895385742,
+      "learning_rate": 2.1859086575439225e-07,
+      "logits/chosen": 1.7012341022491455,
+      "logits/rejected": 1.78024423122406,
+      "logps/chosen": -84.58718872070312,
+      "logps/rejected": -86.95068359375,
+      "loss": 0.549,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.291012704372406,
+      "rewards/margins": 0.4876977801322937,
+      "rewards/rejected": -0.7787104845046997,
+      "step": 510
+    },
+    {
+      "epoch": 17.405857740585773,
+      "grad_norm": 1.1710774898529053,
+      "learning_rate": 1.6123041018599766e-07,
+      "logits/chosen": 1.7162996530532837,
+      "logits/rejected": 1.7306814193725586,
+      "logps/chosen": -93.86546325683594,
+      "logps/rejected": -84.5029067993164,
+      "loss": 0.5567,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.26384133100509644,
+      "rewards/margins": 0.3909001052379608,
+      "rewards/rejected": -0.6547414064407349,
+      "step": 520
+    },
+    {
+      "epoch": 17.740585774058577,
+      "grad_norm": 1.0457745790481567,
+      "learning_rate": 1.1233862220001168e-07,
+      "logits/chosen": 1.729026436805725,
+      "logits/rejected": 1.7938979864120483,
+      "logps/chosen": -86.14263916015625,
+      "logps/rejected": -109.89949798583984,
+      "loss": 0.555,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.37593385577201843,
+      "rewards/margins": 0.41020965576171875,
+      "rewards/rejected": -0.7861436009407043,
+      "step": 530
+    },
+    {
+      "epoch": 18.07531380753138,
+      "grad_norm": 1.1671756505966187,
+      "learning_rate": 7.209253860320897e-08,
+      "logits/chosen": 1.797410011291504,
+      "logits/rejected": 1.7258751392364502,
+      "logps/chosen": -101.58478546142578,
+      "logps/rejected": -81.59870910644531,
+      "loss": 0.5493,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.36429405212402344,
+      "rewards/margins": 0.3445179760456085,
+      "rewards/rejected": -0.7088119983673096,
+      "step": 540
+    },
+    {
+      "epoch": 18.410041841004183,
+      "grad_norm": 1.0843878984451294,
+      "learning_rate": 4.063789016999331e-08,
+      "logits/chosen": 1.7526544332504272,
+      "logits/rejected": 1.7694238424301147,
+      "logps/chosen": -91.79996490478516,
+      "logps/rejected": -88.14305877685547,
+      "loss": 0.5472,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.432400643825531,
+      "rewards/margins": 0.34698057174682617,
+      "rewards/rejected": -0.7793812155723572,
+      "step": 550
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 580,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8729341192230666e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Area/checkpoint-580/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Area/checkpoint-580/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Area/checkpoint-580/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Area/checkpoint-580/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Area/checkpoint-580/trainer_state.json

@@ -0,0 +1,903 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.414225941422593,
+  "eval_steps": 500,
+  "global_step": 580,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 0.4676998555660248,
+      "learning_rate": 8.620689655172415e-07,
+      "logits/chosen": 1.7077701091766357,
+      "logits/rejected": 1.8646482229232788,
+      "logps/chosen": -85.7728271484375,
+      "logps/rejected": -88.1952896118164,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": -0.004770822823047638,
+      "rewards/margins": -0.007881464436650276,
+      "rewards/rejected": 0.0031106427777558565,
+      "step": 10
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 0.43230223655700684,
+      "learning_rate": 1.724137931034483e-06,
+      "logits/chosen": 1.8023220300674438,
+      "logits/rejected": 1.8210970163345337,
+      "logps/chosen": -78.37618255615234,
+      "logps/rejected": -75.44720458984375,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.0056939031928777695,
+      "rewards/margins": -0.003848772030323744,
+      "rewards/rejected": -0.001845130929723382,
+      "step": 20
+    },
+    {
+      "epoch": 1.00418410041841,
+      "grad_norm": 2.431753396987915,
+      "learning_rate": 2.5862068965517246e-06,
+      "logits/chosen": 1.8643144369125366,
+      "logits/rejected": 1.8500900268554688,
+      "logps/chosen": -86.84412384033203,
+      "logps/rejected": -90.78925323486328,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.0008674233104102314,
+      "rewards/margins": -0.008064134046435356,
+      "rewards/rejected": 0.0071967123076319695,
+      "step": 30
+    },
+    {
+      "epoch": 1.3389121338912133,
+      "grad_norm": 0.5327289700508118,
+      "learning_rate": 3.448275862068966e-06,
+      "logits/chosen": 1.7701479196548462,
+      "logits/rejected": 1.7749736309051514,
+      "logps/chosen": -83.61552429199219,
+      "logps/rejected": -72.89176177978516,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -0.0019066383829340339,
+      "rewards/margins": -0.0035008196718990803,
+      "rewards/rejected": 0.0015941811725497246,
+      "step": 40
+    },
+    {
+      "epoch": 1.6736401673640167,
+      "grad_norm": 0.5017096996307373,
+      "learning_rate": 4.310344827586207e-06,
+      "logits/chosen": 1.7465788125991821,
+      "logits/rejected": 1.7925498485565186,
+      "logps/chosen": -84.85249328613281,
+      "logps/rejected": -88.79469299316406,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 0.0003656863118521869,
+      "rewards/margins": 0.00012080222222721204,
+      "rewards/rejected": 0.00024488387862220407,
+      "step": 50
+    },
+    {
+      "epoch": 2.00836820083682,
+      "grad_norm": 0.4994066059589386,
+      "learning_rate": 4.999818897894192e-06,
+      "logits/chosen": 1.8359416723251343,
+      "logits/rejected": 1.814234733581543,
+      "logps/chosen": -79.98396301269531,
+      "logps/rejected": -66.29866027832031,
+      "loss": 0.6952,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.00456579215824604,
+      "rewards/margins": -0.002460189163684845,
+      "rewards/rejected": 0.007025980856269598,
+      "step": 60
+    },
+    {
+      "epoch": 2.3430962343096233,
+      "grad_norm": 0.6425362825393677,
+      "learning_rate": 4.9934830787948756e-06,
+      "logits/chosen": 1.7550818920135498,
+      "logits/rejected": 1.7802051305770874,
+      "logps/chosen": -83.60951232910156,
+      "logps/rejected": -70.81080627441406,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.004059882368892431,
+      "rewards/margins": 0.00932090263813734,
+      "rewards/rejected": -0.005261021666228771,
+      "step": 70
+    },
+    {
+      "epoch": 2.6778242677824267,
+      "grad_norm": 0.5591297149658203,
+      "learning_rate": 4.978118375700895e-06,
+      "logits/chosen": 1.7742525339126587,
+      "logits/rejected": 1.8790937662124634,
+      "logps/chosen": -86.7696533203125,
+      "logps/rejected": -84.90727233886719,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 0.0033963967580348253,
+      "rewards/margins": 0.005500240251421928,
+      "rewards/rejected": -0.0021038432605564594,
+      "step": 80
+    },
+    {
+      "epoch": 3.01255230125523,
+      "grad_norm": 0.6774541735649109,
+      "learning_rate": 4.953780424089803e-06,
+      "logits/chosen": 1.8815631866455078,
+      "logits/rejected": 1.911620855331421,
+      "logps/chosen": -92.14398193359375,
+      "logps/rejected": -82.83556365966797,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.007645039353519678,
+      "rewards/margins": 0.005134005565196276,
+      "rewards/rejected": 0.0025110342539846897,
+      "step": 90
+    },
+    {
+      "epoch": 3.3472803347280333,
+      "grad_norm": 0.6908814907073975,
+      "learning_rate": 4.920557351506409e-06,
+      "logits/chosen": 1.7718560695648193,
+      "logits/rejected": 1.8823477029800415,
+      "logps/chosen": -91.2622299194336,
+      "logps/rejected": -96.467529296875,
+      "loss": 0.6894,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.004941435065120459,
+      "rewards/margins": 0.01582186669111252,
+      "rewards/rejected": -0.010880433022975922,
+      "step": 100
+    },
+    {
+      "epoch": 3.6820083682008367,
+      "grad_norm": 0.6954344511032104,
+      "learning_rate": 4.878569458453592e-06,
+      "logits/chosen": 1.6916942596435547,
+      "logits/rejected": 1.7603965997695923,
+      "logps/chosen": -84.66748046875,
+      "logps/rejected": -103.5328369140625,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.003184904810041189,
+      "rewards/margins": 0.007628746330738068,
+      "rewards/rejected": -0.01081365067511797,
+      "step": 110
+    },
+    {
+      "epoch": 4.01673640167364,
+      "grad_norm": 0.6846771240234375,
+      "learning_rate": 4.827968782785062e-06,
+      "logits/chosen": 1.8839175701141357,
+      "logits/rejected": 1.956974744796753,
+      "logps/chosen": -76.89198303222656,
+      "logps/rejected": -95.03202056884766,
+      "loss": 0.6886,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.009448022581636906,
+      "rewards/margins": 0.018458742648363113,
+      "rewards/rejected": -0.009010720066726208,
+      "step": 120
+    },
+    {
+      "epoch": 4.351464435146443,
+      "grad_norm": 0.762366771697998,
+      "learning_rate": 4.7689385491773934e-06,
+      "logits/chosen": 1.8294252157211304,
+      "logits/rejected": 1.8144447803497314,
+      "logps/chosen": -87.03471374511719,
+      "logps/rejected": -73.86766052246094,
+      "loss": 0.6847,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.01010747067630291,
+      "rewards/margins": 0.01468165498226881,
+      "rewards/rejected": -0.024789121001958847,
+      "step": 130
+    },
+    {
+      "epoch": 4.686192468619247,
+      "grad_norm": 0.7172746658325195,
+      "learning_rate": 4.70169250567482e-06,
+      "logits/chosen": 1.7118749618530273,
+      "logits/rejected": 1.8259985446929932,
+      "logps/chosen": -68.12081146240234,
+      "logps/rejected": -75.31085205078125,
+      "loss": 0.6809,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.014076923951506615,
+      "rewards/margins": 0.014298361726105213,
+      "rewards/rejected": -0.028375286608934402,
+      "step": 140
+    },
+    {
+      "epoch": 5.02092050209205,
+      "grad_norm": 0.7188512682914734,
+      "learning_rate": 4.626474149709127e-06,
+      "logits/chosen": 1.8864549398422241,
+      "logits/rejected": 1.8488889932632446,
+      "logps/chosen": -101.3166275024414,
+      "logps/rejected": -76.73490905761719,
+      "loss": 0.6773,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.021979983896017075,
+      "rewards/margins": 0.023767748847603798,
+      "rewards/rejected": -0.04574773460626602,
+      "step": 150
+    },
+    {
+      "epoch": 5.355648535564853,
+      "grad_norm": 0.8493714928627014,
+      "learning_rate": 4.54355584639723e-06,
+      "logits/chosen": 1.7861169576644897,
+      "logits/rejected": 1.7927452325820923,
+      "logps/chosen": -83.28593444824219,
+      "logps/rejected": -76.04238891601562,
+      "loss": 0.673,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.0320693664252758,
+      "rewards/margins": 0.04263792932033539,
+      "rewards/rejected": -0.07470729202032089,
+      "step": 160
+    },
+    {
+      "epoch": 5.690376569037657,
+      "grad_norm": 1.1378726959228516,
+      "learning_rate": 4.45323784230908e-06,
+      "logits/chosen": 1.8622329235076904,
+      "logits/rejected": 1.875741958618164,
+      "logps/chosen": -72.01219177246094,
+      "logps/rejected": -77.62818908691406,
+      "loss": 0.6679,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.05134737491607666,
+      "rewards/margins": 0.049249742180109024,
+      "rewards/rejected": -0.10059712082147598,
+      "step": 170
+    },
+    {
+      "epoch": 6.02510460251046,
+      "grad_norm": 0.847227156162262,
+      "learning_rate": 4.355847178277025e-06,
+      "logits/chosen": 1.9445765018463135,
+      "logits/rejected": 2.0065901279449463,
+      "logps/chosen": -76.14964294433594,
+      "logps/rejected": -83.71626281738281,
+      "loss": 0.6621,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.05519520118832588,
+      "rewards/margins": 0.06803703308105469,
+      "rewards/rejected": -0.12323222309350967,
+      "step": 180
+    },
+    {
+      "epoch": 6.359832635983263,
+      "grad_norm": 0.8368040919303894,
+      "learning_rate": 4.2517365051833564e-06,
+      "logits/chosen": 1.8116003274917603,
+      "logits/rejected": 1.8839362859725952,
+      "logps/chosen": -82.7087631225586,
+      "logps/rejected": -67.3785629272461,
+      "loss": 0.6538,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.03855596110224724,
+      "rewards/margins": 0.11562293767929077,
+      "rewards/rejected": -0.15417888760566711,
+      "step": 190
+    },
+    {
+      "epoch": 6.694560669456067,
+      "grad_norm": 0.8636891841888428,
+      "learning_rate": 4.141282807014034e-06,
+      "logits/chosen": 1.7250430583953857,
+      "logits/rejected": 1.775418996810913,
+      "logps/chosen": -68.51094055175781,
+      "logps/rejected": -79.88996124267578,
+      "loss": 0.657,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.11151214689016342,
+      "rewards/margins": 0.07863004505634308,
+      "rewards/rejected": -0.1901421844959259,
+      "step": 200
+    },
+    {
+      "epoch": 7.02928870292887,
+      "grad_norm": 0.945520281791687,
+      "learning_rate": 4.024886035802432e-06,
+      "logits/chosen": 1.7329381704330444,
+      "logits/rejected": 1.799551010131836,
+      "logps/chosen": -81.49295043945312,
+      "logps/rejected": -87.97386169433594,
+      "loss": 0.6462,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.09862186014652252,
+      "rewards/margins": 0.10664049535989761,
+      "rewards/rejected": -0.20526234805583954,
+      "step": 210
+    },
+    {
+      "epoch": 7.364016736401673,
+      "grad_norm": 0.9736716151237488,
+      "learning_rate": 3.9029676634059565e-06,
+      "logits/chosen": 1.8787791728973389,
+      "logits/rejected": 1.8832632303237915,
+      "logps/chosen": -83.21014404296875,
+      "logps/rejected": -76.4449691772461,
+      "loss": 0.6413,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.07923021167516708,
+      "rewards/margins": 0.11194779723882675,
+      "rewards/rejected": -0.19117799401283264,
+      "step": 220
+    },
+    {
+      "epoch": 7.698744769874477,
+      "grad_norm": 0.9238549470901489,
+      "learning_rate": 3.7759691553595214e-06,
+      "logits/chosen": 1.9044986963272095,
+      "logits/rejected": 1.8805242776870728,
+      "logps/chosen": -90.17919158935547,
+      "logps/rejected": -86.05476379394531,
+      "loss": 0.6346,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.0993318110704422,
+      "rewards/margins": 0.12289313971996307,
+      "rewards/rejected": -0.22222498059272766,
+      "step": 230
+    },
+    {
+      "epoch": 8.03347280334728,
+      "grad_norm": 1.0052326917648315,
+      "learning_rate": 3.6443503723320837e-06,
+      "logits/chosen": 1.873815894126892,
+      "logits/rejected": 1.8809674978256226,
+      "logps/chosen": -74.86824035644531,
+      "logps/rejected": -81.79768371582031,
+      "loss": 0.6377,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.17602138221263885,
+      "rewards/margins": 0.09737586975097656,
+      "rewards/rejected": -0.2733972668647766,
+      "step": 240
+    },
+    {
+      "epoch": 8.368200836820083,
+      "grad_norm": 1.0167930126190186,
+      "learning_rate": 3.508587904974522e-06,
+      "logits/chosen": 1.868101716041565,
+      "logits/rejected": 1.8685039281845093,
+      "logps/chosen": -94.48133850097656,
+      "logps/rejected": -94.00556182861328,
+      "loss": 0.6216,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.1260211318731308,
+      "rewards/margins": 0.21002164483070374,
+      "rewards/rejected": -0.3360427916049957,
+      "step": 250
+    },
+    {
+      "epoch": 8.702928870292887,
+      "grad_norm": 0.9955905079841614,
+      "learning_rate": 3.3691733481883693e-06,
+      "logits/chosen": 1.7905946969985962,
+      "logits/rejected": 1.7784850597381592,
+      "logps/chosen": -94.9794921875,
+      "logps/rejected": -84.99113464355469,
+      "loss": 0.6193,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.18853916227817535,
+      "rewards/margins": 0.19185101985931396,
+      "rewards/rejected": -0.3803902268409729,
+      "step": 260
+    },
+    {
+      "epoch": 9.03765690376569,
+      "grad_norm": 0.943289577960968,
+      "learning_rate": 3.226611521064278e-06,
+      "logits/chosen": 1.8119779825210571,
+      "logits/rejected": 1.817567229270935,
+      "logps/chosen": -80.78002166748047,
+      "logps/rejected": -85.42848205566406,
+      "loss": 0.6201,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.16673071682453156,
+      "rewards/margins": 0.19530437886714935,
+      "rewards/rejected": -0.3620350658893585,
+      "step": 270
+    },
+    {
+      "epoch": 9.372384937238493,
+      "grad_norm": 0.9868927597999573,
+      "learning_rate": 3.0814186389357765e-06,
+      "logits/chosen": 1.816300392150879,
+      "logits/rejected": 1.7763961553573608,
+      "logps/chosen": -77.19395446777344,
+      "logps/rejected": -68.16056060791016,
+      "loss": 0.6157,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.21062004566192627,
+      "rewards/margins": 0.19489461183547974,
+      "rewards/rejected": -0.4055147171020508,
+      "step": 280
+    },
+    {
+      "epoch": 9.707112970711297,
+      "grad_norm": 1.0557409524917603,
+      "learning_rate": 2.9341204441673267e-06,
+      "logits/chosen": 1.8154022693634033,
+      "logits/rejected": 1.842792272567749,
+      "logps/chosen": -84.95299530029297,
+      "logps/rejected": -82.22926330566406,
+      "loss": 0.5972,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25716403126716614,
+      "rewards/margins": 0.2636396288871765,
+      "rewards/rejected": -0.5208036303520203,
+      "step": 290
+    },
+    {
+      "epoch": 10.0418410041841,
+      "grad_norm": 1.0787400007247925,
+      "learning_rate": 2.785250302445062e-06,
+      "logits/chosen": 1.8255424499511719,
+      "logits/rejected": 1.8123111724853516,
+      "logps/chosen": -94.89508056640625,
+      "logps/rejected": -99.48709869384766,
+      "loss": 0.6038,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.25526899099349976,
+      "rewards/margins": 0.24981728196144104,
+      "rewards/rejected": -0.5050862431526184,
+      "step": 300
+    },
+    {
+      "epoch": 10.376569037656903,
+      "grad_norm": 0.9934303164482117,
+      "learning_rate": 2.6353472714635443e-06,
+      "logits/chosen": 1.6809011697769165,
+      "logits/rejected": 1.6883894205093384,
+      "logps/chosen": -83.52108001708984,
+      "logps/rejected": -89.83765411376953,
+      "loss": 0.5897,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.20843425393104553,
+      "rewards/margins": 0.2531076967716217,
+      "rewards/rejected": -0.46154195070266724,
+      "step": 310
+    },
+    {
+      "epoch": 10.711297071129707,
+      "grad_norm": 1.0989857912063599,
+      "learning_rate": 2.4849541490017868e-06,
+      "logits/chosen": 1.8184492588043213,
+      "logits/rejected": 1.8702239990234375,
+      "logps/chosen": -76.5416030883789,
+      "logps/rejected": -87.98771667480469,
+      "loss": 0.5951,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.26176151633262634,
+      "rewards/margins": 0.17908410727977753,
+      "rewards/rejected": -0.44084563851356506,
+      "step": 320
+    },
+    {
+      "epoch": 11.04602510460251,
+      "grad_norm": 1.1377506256103516,
+      "learning_rate": 2.3346155074564712e-06,
+      "logits/chosen": 1.7781150341033936,
+      "logits/rejected": 1.7945045232772827,
+      "logps/chosen": -94.21954345703125,
+      "logps/rejected": -87.9439926147461,
+      "loss": 0.5895,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.3070668578147888,
+      "rewards/margins": 0.26864537596702576,
+      "rewards/rejected": -0.5757122039794922,
+      "step": 330
+    },
+    {
+      "epoch": 11.380753138075313,
+      "grad_norm": 1.1378768682479858,
+      "learning_rate": 2.184875721949277e-06,
+      "logits/chosen": 1.7889184951782227,
+      "logits/rejected": 1.7863588333129883,
+      "logps/chosen": -77.19974517822266,
+      "logps/rejected": -74.92039489746094,
+      "loss": 0.577,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.2269454449415207,
+      "rewards/margins": 0.3004661798477173,
+      "rewards/rejected": -0.5274116396903992,
+      "step": 340
+    },
+    {
+      "epoch": 11.715481171548117,
+      "grad_norm": 1.0102859735488892,
+      "learning_rate": 2.0362769991485514e-06,
+      "logits/chosen": 1.6868798732757568,
+      "logits/rejected": 1.743287444114685,
+      "logps/chosen": -80.24299621582031,
+      "logps/rejected": -91.3736343383789,
+      "loss": 0.5825,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2850210964679718,
+      "rewards/margins": 0.30632922053337097,
+      "rewards/rejected": -0.5913503170013428,
+      "step": 350
+    },
+    {
+      "epoch": 12.05020920502092,
+      "grad_norm": 1.0598143339157104,
+      "learning_rate": 1.8893574139429226e-06,
+      "logits/chosen": 1.6859172582626343,
+      "logits/rejected": 1.7635313272476196,
+      "logps/chosen": -88.87372589111328,
+      "logps/rejected": -93.02122497558594,
+      "loss": 0.5819,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.317017138004303,
+      "rewards/margins": 0.2608889639377594,
+      "rewards/rejected": -0.5779060125350952,
+      "step": 360
+    },
+    {
+      "epoch": 12.384937238493723,
+      "grad_norm": 1.0845669507980347,
+      "learning_rate": 1.744648961076068e-06,
+      "logits/chosen": 1.7980632781982422,
+      "logits/rejected": 1.8205795288085938,
+      "logps/chosen": -83.31995391845703,
+      "logps/rejected": -87.28046417236328,
+      "loss": 0.5737,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.3205794394016266,
+      "rewards/margins": 0.24214692413806915,
+      "rewards/rejected": -0.5627263784408569,
+      "step": 370
+    },
+    {
+      "epoch": 12.719665271966527,
+      "grad_norm": 1.180468201637268,
+      "learning_rate": 1.602675628797636e-06,
+      "logits/chosen": 1.8093292713165283,
+      "logits/rejected": 1.8195394277572632,
+      "logps/chosen": -99.64051055908203,
+      "logps/rejected": -82.13116455078125,
+      "loss": 0.5655,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.28717803955078125,
+      "rewards/margins": 0.355060875415802,
+      "rewards/rejected": -0.6422389149665833,
+      "step": 380
+    },
+    {
+      "epoch": 13.05439330543933,
+      "grad_norm": 1.0443357229232788,
+      "learning_rate": 1.4639515015056205e-06,
+      "logits/chosen": 1.7365925312042236,
+      "logits/rejected": 1.7514903545379639,
+      "logps/chosen": -96.92813110351562,
+      "logps/rejected": -83.5425796508789,
+      "loss": 0.5654,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3064219653606415,
+      "rewards/margins": 0.38930463790893555,
+      "rewards/rejected": -0.6957265138626099,
+      "step": 390
+    },
+    {
+      "epoch": 13.389121338912133,
+      "grad_norm": 1.2010602951049805,
+      "learning_rate": 1.328978898250525e-06,
+      "logits/chosen": 1.7649974822998047,
+      "logits/rejected": 1.7864068746566772,
+      "logps/chosen": -78.26787567138672,
+      "logps/rejected": -82.81205749511719,
+      "loss": 0.5713,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.32541388273239136,
+      "rewards/margins": 0.34498968720436096,
+      "rewards/rejected": -0.6704035997390747,
+      "step": 400
+    },
+    {
+      "epoch": 13.723849372384937,
+      "grad_norm": 1.656805396080017,
+      "learning_rate": 1.198246553841744e-06,
+      "logits/chosen": 1.6543798446655273,
+      "logits/rejected": 1.700377106666565,
+      "logps/chosen": -88.14425659179688,
+      "logps/rejected": -86.7034912109375,
+      "loss": 0.5569,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.307409405708313,
+      "rewards/margins": 0.346424400806427,
+      "rewards/rejected": -0.65383380651474,
+      "step": 410
+    },
+    {
+      "epoch": 14.05857740585774,
+      "grad_norm": 1.3017597198486328,
+      "learning_rate": 1.0722278491423998e-06,
+      "logits/chosen": 1.861400842666626,
+      "logits/rejected": 1.7919048070907593,
+      "logps/chosen": -101.43531036376953,
+      "logps/rejected": -77.99034881591797,
+      "loss": 0.567,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.34600889682769775,
+      "rewards/margins": 0.2590746283531189,
+      "rewards/rejected": -0.6050835251808167,
+      "step": 420
+    },
+    {
+      "epoch": 14.393305439330543,
+      "grad_norm": 1.0269688367843628,
+      "learning_rate": 9.513790969606926e-07,
+      "logits/chosen": 1.809483289718628,
+      "logits/rejected": 1.8456366062164307,
+      "logps/chosen": -102.51566314697266,
+      "logps/rejected": -104.2486343383789,
+      "loss": 0.5605,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.33636271953582764,
+      "rewards/margins": 0.3720197379589081,
+      "rewards/rejected": -0.7083825469017029,
+      "step": 430
+    },
+    {
+      "epoch": 14.728033472803347,
+      "grad_norm": 1.0176596641540527,
+      "learning_rate": 8.361378897445643e-07,
+      "logits/chosen": 1.8125699758529663,
+      "logits/rejected": 1.819248914718628,
+      "logps/chosen": -83.56723022460938,
+      "logps/rejected": -81.31576538085938,
+      "loss": 0.5549,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.321399986743927,
+      "rewards/margins": 0.2679772973060608,
+      "rewards/rejected": -0.5893772840499878,
+      "step": 440
+    },
+    {
+      "epoch": 15.06276150627615,
+      "grad_norm": 1.1313916444778442,
+      "learning_rate": 7.269215150626391e-07,
+      "logits/chosen": 1.7356494665145874,
+      "logits/rejected": 1.793581247329712,
+      "logps/chosen": -80.0768051147461,
+      "logps/rejected": -79.23683166503906,
+      "loss": 0.5606,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.34324222803115845,
+      "rewards/margins": 0.3662562370300293,
+      "rewards/rejected": -0.7094983458518982,
+      "step": 450
+    },
+    {
+      "epoch": 15.397489539748953,
+      "grad_norm": 1.1418852806091309,
+      "learning_rate": 6.241254446089942e-07,
+      "logits/chosen": 1.7430709600448608,
+      "logits/rejected": 1.7953869104385376,
+      "logps/chosen": -82.4347152709961,
+      "logps/rejected": -82.4286880493164,
+      "loss": 0.5545,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.3615425229072571,
+      "rewards/margins": 0.35559993982315063,
+      "rewards/rejected": -0.7171424031257629,
+      "step": 460
+    },
+    {
+      "epoch": 15.732217573221757,
+      "grad_norm": 1.1025134325027466,
+      "learning_rate": 5.281219022030423e-07,
+      "logits/chosen": 1.655470848083496,
+      "logits/rejected": 1.692399024963379,
+      "logps/chosen": -101.62381744384766,
+      "logps/rejected": -96.6092300415039,
+      "loss": 0.5525,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.29976749420166016,
+      "rewards/margins": 0.3946015238761902,
+      "rewards/rejected": -0.6943690776824951,
+      "step": 470
+    },
+    {
+      "epoch": 16.06694560669456,
+      "grad_norm": 1.2202156782150269,
+      "learning_rate": 4.392585159698087e-07,
+      "logits/chosen": 1.7376701831817627,
+      "logits/rejected": 1.793471097946167,
+      "logps/chosen": -89.61154174804688,
+      "logps/rejected": -94.71632385253906,
+      "loss": 0.5499,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.31332069635391235,
+      "rewards/margins": 0.4189217984676361,
+      "rewards/rejected": -0.7322424650192261,
+      "step": 480
+    },
+    {
+      "epoch": 16.401673640167363,
+      "grad_norm": 1.1149810552597046,
+      "learning_rate": 3.578570595810274e-07,
+      "logits/chosen": 1.7718391418457031,
+      "logits/rejected": 1.8273475170135498,
+      "logps/chosen": -83.96971130371094,
+      "logps/rejected": -92.80200958251953,
+      "loss": 0.5471,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.2852213978767395,
+      "rewards/margins": 0.3351207673549652,
+      "rewards/rejected": -0.6203421354293823,
+      "step": 490
+    },
+    {
+      "epoch": 16.736401673640167,
+      "grad_norm": 1.0757339000701904,
+      "learning_rate": 2.8421228711503127e-07,
+      "logits/chosen": 1.7726856470108032,
+      "logits/rejected": 1.836022973060608,
+      "logps/chosen": -78.27845764160156,
+      "logps/rejected": -83.48805236816406,
+      "loss": 0.5539,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.34817034006118774,
+      "rewards/margins": 0.2852809429168701,
+      "rewards/rejected": -0.6334512829780579,
+      "step": 500
+    },
+    {
+      "epoch": 17.07112970711297,
+      "grad_norm": 1.1488370895385742,
+      "learning_rate": 2.1859086575439225e-07,
+      "logits/chosen": 1.7012341022491455,
+      "logits/rejected": 1.78024423122406,
+      "logps/chosen": -84.58718872070312,
+      "logps/rejected": -86.95068359375,
+      "loss": 0.549,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.291012704372406,
+      "rewards/margins": 0.4876977801322937,
+      "rewards/rejected": -0.7787104845046997,
+      "step": 510
+    },
+    {
+      "epoch": 17.405857740585773,
+      "grad_norm": 1.1710774898529053,
+      "learning_rate": 1.6123041018599766e-07,
+      "logits/chosen": 1.7162996530532837,
+      "logits/rejected": 1.7306814193725586,
+      "logps/chosen": -93.86546325683594,
+      "logps/rejected": -84.5029067993164,
+      "loss": 0.5567,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.26384133100509644,
+      "rewards/margins": 0.3909001052379608,
+      "rewards/rejected": -0.6547414064407349,
+      "step": 520
+    },
+    {
+      "epoch": 17.740585774058577,
+      "grad_norm": 1.0457745790481567,
+      "learning_rate": 1.1233862220001168e-07,
+      "logits/chosen": 1.729026436805725,
+      "logits/rejected": 1.7938979864120483,
+      "logps/chosen": -86.14263916015625,
+      "logps/rejected": -109.89949798583984,
+      "loss": 0.555,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.37593385577201843,
+      "rewards/margins": 0.41020965576171875,
+      "rewards/rejected": -0.7861436009407043,
+      "step": 530
+    },
+    {
+      "epoch": 18.07531380753138,
+      "grad_norm": 1.1671756505966187,
+      "learning_rate": 7.209253860320897e-08,
+      "logits/chosen": 1.797410011291504,
+      "logits/rejected": 1.7258751392364502,
+      "logps/chosen": -101.58478546142578,
+      "logps/rejected": -81.59870910644531,
+      "loss": 0.5493,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.36429405212402344,
+      "rewards/margins": 0.3445179760456085,
+      "rewards/rejected": -0.7088119983673096,
+      "step": 540
+    },
+    {
+      "epoch": 18.410041841004183,
+      "grad_norm": 1.0843878984451294,
+      "learning_rate": 4.063789016999331e-08,
+      "logits/chosen": 1.7526544332504272,
+      "logits/rejected": 1.7694238424301147,
+      "logps/chosen": -91.79996490478516,
+      "logps/rejected": -88.14305877685547,
+      "loss": 0.5472,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.432400643825531,
+      "rewards/margins": 0.34698057174682617,
+      "rewards/rejected": -0.7793812155723572,
+      "step": 550
+    },
+    {
+      "epoch": 18.744769874476987,
+      "grad_norm": 1.1687026023864746,
+      "learning_rate": 1.808857395232788e-08,
+      "logits/chosen": 1.8021119832992554,
+      "logits/rejected": 1.8404823541641235,
+      "logps/chosen": -101.54361724853516,
+      "logps/rejected": -102.21680450439453,
+      "loss": 0.5574,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.32780179381370544,
+      "rewards/margins": 0.34786924719810486,
+      "rewards/rejected": -0.6756710410118103,
+      "step": 560
+    },
+    {
+      "epoch": 19.07949790794979,
+      "grad_norm": 1.3505330085754395,
+      "learning_rate": 4.526240859345499e-09,
+      "logits/chosen": 1.7214359045028687,
+      "logits/rejected": 1.7881813049316406,
+      "logps/chosen": -74.24882507324219,
+      "logps/rejected": -99.3295669555664,
+      "loss": 0.5463,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.4312325417995453,
+      "rewards/margins": 0.3562263250350952,
+      "rewards/rejected": -0.7874588966369629,
+      "step": 570
+    },
+    {
+      "epoch": 19.414225941422593,
+      "grad_norm": 1.1412781476974487,
+      "learning_rate": 0.0,
+      "logits/chosen": 1.8473981618881226,
+      "logits/rejected": 1.784250259399414,
+      "logps/chosen": -86.49626159667969,
+      "logps/rejected": -79.94244384765625,
+      "loss": 0.5464,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.3426724970340729,
+      "rewards/margins": 0.37268632650375366,
+      "rewards/rejected": -0.7153588533401489,
+      "step": 580
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 580,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9755070908268544e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Time/README.md

@@ -0,0 +1,62 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: Time
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Time
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on the time dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.20.0

Time/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}