Add checkpoint-400

checkpoints/checkpoint-400/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c72da1914b81b69b9eef9ba664a51cf8c428ffaa4ebfece1f447bf8d9e8ec447
+oid sha256:d9ad90df4dab19d49cead29b72cec6201adeb662bb40b831a542c015c0dbcdc0
 size 4724960

checkpoints/checkpoint-400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:750452a9c2fd1383c2a6e5ca27221c5a0c15e05cd81f62e17260443572b45af2
+oid sha256:7628d688f5979af115cb0472d0642794f5867c7dc0aedba6f0c2f8ad3a2e8ed2
 size 2455755

checkpoints/checkpoint-400/trainer_state.json

@@ -11,282 +11,282 @@
   "log_history": [
     {
       "epoch": 0.0014276026981690996,
-      "grad_norm": 1.2669798135757446,
+      "grad_norm": 1.2670224905014038,
       "learning_rate": 0.00016,
-      "loss": 2.8988788604736326,
+      "loss": 2.898906135559082,
       "step": 10
     },
     {
       "epoch": 0.0028552053963381992,
-      "grad_norm": 1.254004955291748,
+      "grad_norm": 1.2538419961929321,
       "learning_rate": 0.00019992382766008095,
-      "loss": 2.378495788574219,
+      "loss": 2.378516960144043,
       "step": 20
     },
     {
       "epoch": 0.004282808094507299,
-      "grad_norm": 1.4161536693572998,
+      "grad_norm": 1.409246563911438,
       "learning_rate": 0.0001998286122351821,
-      "loss": 2.475381851196289,
+      "loss": 2.4753650665283202,
       "step": 30
     },
     {
       "epoch": 0.0057104107926763984,
-      "grad_norm": 1.0939087867736816,
+      "grad_norm": 1.094603180885315,
       "learning_rate": 0.00019973339681028326,
-      "loss": 2.2720525741577147,
+      "loss": 2.2721933364868163,
       "step": 40
     },
     {
       "epoch": 0.007138013490845497,
-      "grad_norm": 1.1397730112075806,
+      "grad_norm": 1.1403776407241821,
       "learning_rate": 0.00019963818138538444,
-      "loss": 2.2636650085449217,
+      "loss": 2.263425827026367,
       "step": 50
     },
     {
       "epoch": 0.008565616189014597,
-      "grad_norm": 1.16526198387146,
+      "grad_norm": 1.1656428575515747,
       "learning_rate": 0.0001995429659604856,
-      "loss": 2.362977981567383,
+      "loss": 2.363163185119629,
       "step": 60
     },
     {
       "epoch": 0.009993218887183696,
-      "grad_norm": 1.192640781402588,
+      "grad_norm": 1.1926625967025757,
       "learning_rate": 0.00019944775053558678,
-      "loss": 2.133456802368164,
+      "loss": 2.1333871841430665,
       "step": 70
     },
     {
       "epoch": 0.011420821585352797,
-      "grad_norm": 0.9966805577278137,
+      "grad_norm": 0.9967195391654968,
       "learning_rate": 0.00019935253511068794,
-      "loss": 2.2791345596313475,
+      "loss": 2.279196929931641,
       "step": 80
     },
     {
       "epoch": 0.012848424283521896,
-      "grad_norm": 1.1346687078475952,
+      "grad_norm": 1.1345535516738892,
       "learning_rate": 0.00019925731968578912,
-      "loss": 2.181142044067383,
+      "loss": 2.181261444091797,
       "step": 90
     },
     {
       "epoch": 0.014276026981690995,
-      "grad_norm": 1.228360652923584,
+      "grad_norm": 1.2285407781600952,
       "learning_rate": 0.00019916210426089027,
-      "loss": 2.2281381607055666,
+      "loss": 2.2282310485839845,
       "step": 100
     },
     {
       "epoch": 0.015703629679860096,
-      "grad_norm": 2.206587314605713,
+      "grad_norm": 2.191948890686035,
       "learning_rate": 0.00019906688883599146,
-      "loss": 2.2829971313476562,
+      "loss": 2.2829305648803713,
       "step": 110
     },
     {
       "epoch": 0.017131232378029194,
-      "grad_norm": 1.18593168258667,
+      "grad_norm": 1.1868839263916016,
       "learning_rate": 0.00019897167341109258,
-      "loss": 2.1636577606201173,
+      "loss": 2.1634748458862303,
       "step": 120
     },
     {
       "epoch": 0.018558835076198293,
-      "grad_norm": 1.3732795715332031,
+      "grad_norm": 1.3730543851852417,
       "learning_rate": 0.00019887645798619377,
-      "loss": 2.235016441345215,
+      "loss": 2.235073471069336,
       "step": 130
     },
     {
       "epoch": 0.019986437774367392,
-      "grad_norm": 1.3090860843658447,
+      "grad_norm": 1.3060146570205688,
       "learning_rate": 0.00019878124256129492,
-      "loss": 2.2546611785888673,
+      "loss": 2.254693031311035,
       "step": 140
     },
     {
       "epoch": 0.021414040472536495,
-      "grad_norm": 1.1369000673294067,
+      "grad_norm": 1.13761305809021,
       "learning_rate": 0.0001986860271363961,
-      "loss": 2.2553131103515627,
+      "loss": 2.255308723449707,
       "step": 150
     },
     {
       "epoch": 0.022841643170705594,
-      "grad_norm": 1.2429536581039429,
+      "grad_norm": 1.2420964241027832,
       "learning_rate": 0.00019859081171149726,
-      "loss": 2.1992692947387695,
+      "loss": 2.199342155456543,
       "step": 160
     },
     {
       "epoch": 0.024269245868874693,
-      "grad_norm": 1.2623324394226074,
+      "grad_norm": 1.2628268003463745,
       "learning_rate": 0.00019849559628659844,
-      "loss": 2.25687198638916,
+      "loss": 2.2568809509277346,
       "step": 170
     },
     {
       "epoch": 0.02569684856704379,
-      "grad_norm": 1.0435346364974976,
+      "grad_norm": 1.0423402786254883,
       "learning_rate": 0.0001984003808616996,
-      "loss": 2.2015625,
+      "loss": 2.201403045654297,
       "step": 180
     },
     {
       "epoch": 0.02712445126521289,
-      "grad_norm": 1.3203520774841309,
+      "grad_norm": 1.3187193870544434,
       "learning_rate": 0.00019830516543680078,
-      "loss": 2.310222625732422,
+      "loss": 2.31024055480957,
       "step": 190
     },
     {
       "epoch": 0.02855205396338199,
-      "grad_norm": 1.2872213125228882,
+      "grad_norm": 1.287013292312622,
       "learning_rate": 0.00019820995001190194,
-      "loss": 2.2774518966674804,
+      "loss": 2.2775556564331056,
       "step": 200
     },
     {
       "epoch": 0.029979656661551092,
-      "grad_norm": 1.4448614120483398,
+      "grad_norm": 1.445034384727478,
       "learning_rate": 0.00019811473458700312,
-      "loss": 2.2141748428344727,
+      "loss": 2.214271354675293,
       "step": 210
     },
     {
       "epoch": 0.03140725935972019,
-      "grad_norm": 1.4330700635910034,
+      "grad_norm": 1.4336904287338257,
       "learning_rate": 0.00019801951916210427,
-      "loss": 2.121222496032715,
+      "loss": 2.1211181640625,
       "step": 220
     },
     {
       "epoch": 0.03283486205788929,
-      "grad_norm": 1.3029669523239136,
+      "grad_norm": 1.303303837776184,
       "learning_rate": 0.00019792430373720543,
-      "loss": 2.1038030624389648,
+      "loss": 2.1037008285522463,
       "step": 230
     },
     {
       "epoch": 0.03426246475605839,
-      "grad_norm": 1.236972451210022,
+      "grad_norm": 1.2367061376571655,
       "learning_rate": 0.0001978290883123066,
-      "loss": 2.128954315185547,
+      "loss": 2.1291038513183596,
       "step": 240
     },
     {
       "epoch": 0.03569006745422749,
-      "grad_norm": 1.3134138584136963,
+      "grad_norm": 1.314647912979126,
       "learning_rate": 0.00019773387288740777,
-      "loss": 2.135414886474609,
+      "loss": 2.1351301193237306,
       "step": 250
     },
     {
       "epoch": 0.03711767015239659,
-      "grad_norm": 1.3093985319137573,
+      "grad_norm": 1.3084362745285034,
       "learning_rate": 0.00019763865746250895,
-      "loss": 2.098076057434082,
+      "loss": 2.0980342864990233,
       "step": 260
     },
     {
       "epoch": 0.038545272850565686,
-      "grad_norm": 1.7127153873443604,
+      "grad_norm": 1.712534785270691,
       "learning_rate": 0.0001975434420376101,
-      "loss": 2.255548095703125,
+      "loss": 2.25567569732666,
       "step": 270
     },
     {
       "epoch": 0.039972875548734785,
-      "grad_norm": 1.5121700763702393,
+      "grad_norm": 1.5107096433639526,
       "learning_rate": 0.0001974482266127113,
-      "loss": 2.1986673355102537,
+      "loss": 2.198653793334961,
       "step": 280
     },
     {
       "epoch": 0.041400478246903884,
-      "grad_norm": 1.1628669500350952,
+      "grad_norm": 1.1626437902450562,
       "learning_rate": 0.00019735301118781244,
-      "loss": 2.1367721557617188,
+      "loss": 2.136816215515137,
       "step": 290
     },
     {
       "epoch": 0.04282808094507299,
-      "grad_norm": 1.5496574640274048,
+      "grad_norm": 1.551853060722351,
       "learning_rate": 0.00019725779576291362,
-      "loss": 2.2107372283935547,
+      "loss": 2.2106935501098635,
       "step": 300
     },
     {
       "epoch": 0.04425568364324209,
-      "grad_norm": 1.5125689506530762,
+      "grad_norm": 1.5131734609603882,
       "learning_rate": 0.00019716258033801475,
-      "loss": 2.096792221069336,
+      "loss": 2.0967830657958983,
       "step": 310
     },
     {
       "epoch": 0.04568328634141119,
-      "grad_norm": 1.3094804286956787,
+      "grad_norm": 1.310641884803772,
       "learning_rate": 0.00019706736491311593,
-      "loss": 2.2105518341064454,
+      "loss": 2.2105255126953125,
       "step": 320
     },
     {
       "epoch": 0.047110889039580287,
-      "grad_norm": 1.362282633781433,
+      "grad_norm": 1.3621881008148193,
       "learning_rate": 0.0001969721494882171,
-      "loss": 2.177376937866211,
+      "loss": 2.1775463104248045,
       "step": 330
     },
     {
       "epoch": 0.048538491737749385,
-      "grad_norm": 1.4631069898605347,
+      "grad_norm": 1.4618415832519531,
       "learning_rate": 0.00019687693406331827,
-      "loss": 2.1494699478149415,
+      "loss": 2.148931694030762,
       "step": 340
     },
     {
       "epoch": 0.049966094435918484,
-      "grad_norm": 1.320152997970581,
+      "grad_norm": 1.3173977136611938,
       "learning_rate": 0.00019678171863841943,
-      "loss": 2.1968358993530273,
+      "loss": 2.1974794387817385,
       "step": 350
     },
     {
       "epoch": 0.05139369713408758,
-      "grad_norm": 1.183519959449768,
+      "grad_norm": 1.1830055713653564,
       "learning_rate": 0.0001966865032135206,
-      "loss": 2.17010383605957,
+      "loss": 2.1695978164672853,
       "step": 360
     },
     {
       "epoch": 0.05282129983225668,
-      "grad_norm": 1.1852158308029175,
+      "grad_norm": 1.1831724643707275,
       "learning_rate": 0.00019659128778862177,
-      "loss": 2.0825677871704102,
+      "loss": 2.0823343276977537,
       "step": 370
     },
     {
       "epoch": 0.05424890253042578,
-      "grad_norm": 1.171343445777893,
+      "grad_norm": 1.1693743467330933,
       "learning_rate": 0.00019649607236372295,
-      "loss": 2.1860904693603516,
+      "loss": 2.1867488861083983,
       "step": 380
     },
     {
       "epoch": 0.05567650522859488,
-      "grad_norm": 1.2613917589187622,
+      "grad_norm": 1.25830078125,
       "learning_rate": 0.0001964008569388241,
-      "loss": 2.213835334777832,
+      "loss": 2.2133615493774412,
       "step": 390
     },
     {
       "epoch": 0.05710410792676398,
-      "grad_norm": 1.3591234683990479,
+      "grad_norm": 1.3678141832351685,
       "learning_rate": 0.00019630564151392529,
-      "loss": 2.3102283477783203,
+      "loss": 2.308313751220703,
       "step": 400
     }
   ],