Add checkpoint-200

checkpoints/checkpoint-200/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d1cc562ee0218efe873e0cce1029f1dad1bfd42d969ed1c40ff8eb64a46915
+oid sha256:7a1335028d7b7b1091d4451bd772131e3e89d977e7d29cbf8bec79237743568b
 size 4724960

checkpoints/checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d58c5b3b3668d03de85ead03f9527ad42a691311d8c0f3956123a58e1efa6ebf
+oid sha256:59e92889ba3415d06c03b9c4874147e6bb948a81edb01e39daecf54e9e81f9b9
 size 2455755

checkpoints/checkpoint-200/trainer_state.json

@@ -11,142 +11,142 @@
   "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
     }
   ],