Add checkpoint-200

checkpoints/checkpoint-200/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737d599e8299e3e2a0d0d022af2549a1d3255a98df469166c547a14064c5283e
+oid sha256:0d60c174b986e136c187dc651be078ab10be81e1d394e2181a2c66a2d5f1d07f
 size 4724960

checkpoints/checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a9437cdfbf7d2ba3f5a5ac39a35ec7f5950dabb40d5f79ed5f32eb6d434dc6
+oid sha256:8ab08a6da78da54be3a086d10247f100b7a781d7c0e85137e9e1eb43ce779cca
 size 2455755

checkpoints/checkpoint-200/trainer_state.json

@@ -11,142 +11,142 @@
   "log_history": [
     {
       "epoch": 0.0054010261949770455,
-      "grad_norm": 1.428126573562622,
+      "grad_norm": 1.4275089502334595,
       "learning_rate": 0.00016,
-      "loss": 3.4878021240234376,
+      "loss": 3.4877567291259766,
       "step": 10
     },
     {
       "epoch": 0.010802052389954091,
-      "grad_norm": 1.4069736003875732,
+      "grad_norm": 1.4062877893447876,
       "learning_rate": 0.00019971150378651282,
-      "loss": 3.1774940490722656,
+      "loss": 3.177476501464844,
       "step": 20
     },
     {
       "epoch": 0.016203078584931137,
-      "grad_norm": 1.4898899793624878,
+      "grad_norm": 1.4894630908966064,
       "learning_rate": 0.0001993508835196538,
-      "loss": 2.949423408508301,
+      "loss": 2.949508857727051,
       "step": 30
     },
     {
       "epoch": 0.021604104779908182,
-      "grad_norm": 1.1627568006515503,
+      "grad_norm": 1.1637152433395386,
       "learning_rate": 0.00019899026325279482,
-      "loss": 3.2568889617919923,
+      "loss": 3.2568588256835938,
       "step": 40
     },
     {
       "epoch": 0.027005130974885227,
-      "grad_norm": 1.071158528327942,
+      "grad_norm": 1.0710796117782593,
       "learning_rate": 0.00019862964298593581,
-      "loss": 3.033279609680176,
+      "loss": 3.033162307739258,
       "step": 50
     },
     {
       "epoch": 0.032406157169862275,
-      "grad_norm": 1.03691565990448,
+      "grad_norm": 1.036720633506775,
       "learning_rate": 0.0001982690227190768,
-      "loss": 2.9209321975708007,
+      "loss": 2.9209388732910155,
       "step": 60
     },
     {
       "epoch": 0.03780718336483932,
-      "grad_norm": 1.5099613666534424,
+      "grad_norm": 1.5094584226608276,
       "learning_rate": 0.00019790840245221782,
-      "loss": 3.1997047424316407,
+      "loss": 3.199975776672363,
       "step": 70
     },
     {
       "epoch": 0.043208209559816364,
-      "grad_norm": 1.2505701780319214,
+      "grad_norm": 1.25065016746521,
       "learning_rate": 0.00019754778218535884,
-      "loss": 3.158730316162109,
+      "loss": 3.1586023330688477,
       "step": 80
     },
     {
       "epoch": 0.04860923575479341,
-      "grad_norm": 1.0929311513900757,
+      "grad_norm": 1.093263864517212,
       "learning_rate": 0.00019718716191849983,
-      "loss": 3.16729679107666,
+      "loss": 3.1673559188842773,
       "step": 90
     },
     {
       "epoch": 0.054010261949770454,
-      "grad_norm": 1.7020047903060913,
+      "grad_norm": 1.7025214433670044,
       "learning_rate": 0.00019682654165164082,
-      "loss": 3.009043502807617,
+      "loss": 3.0090349197387694,
       "step": 100
     },
     {
       "epoch": 0.059411288144747505,
-      "grad_norm": 1.0370606184005737,
+      "grad_norm": 1.0379327535629272,
       "learning_rate": 0.00019646592138478184,
-      "loss": 3.086234283447266,
+      "loss": 3.0862411499023437,
       "step": 110
     },
     {
       "epoch": 0.06481231433972455,
-      "grad_norm": 1.0744086503982544,
+      "grad_norm": 1.0767595767974854,
       "learning_rate": 0.00019610530111792285,
-      "loss": 2.934561538696289,
+      "loss": 2.9345855712890625,
       "step": 120
     },
     {
       "epoch": 0.07021334053470159,
-      "grad_norm": 1.2475906610488892,
+      "grad_norm": 1.2473753690719604,
       "learning_rate": 0.00019574468085106384,
-      "loss": 3.168362617492676,
+      "loss": 3.168864440917969,
       "step": 130
     },
     {
       "epoch": 0.07561436672967864,
-      "grad_norm": 1.154983639717102,
+      "grad_norm": 1.1580232381820679,
       "learning_rate": 0.00019538406058420483,
-      "loss": 3.0430318832397463,
+      "loss": 3.0444286346435545,
       "step": 140
     },
     {
       "epoch": 0.08101539292465569,
-      "grad_norm": 1.1540956497192383,
+      "grad_norm": 1.1562517881393433,
       "learning_rate": 0.00019502344031734585,
-      "loss": 3.067497444152832,
+      "loss": 3.0681676864624023,
       "step": 150
     },
     {
       "epoch": 0.08641641911963273,
-      "grad_norm": 1.2023861408233643,
+      "grad_norm": 1.2069370746612549,
       "learning_rate": 0.00019466282005048684,
-      "loss": 3.147787857055664,
+      "loss": 3.147779846191406,
       "step": 160
     },
     {
       "epoch": 0.09181744531460978,
-      "grad_norm": 1.1540592908859253,
+      "grad_norm": 1.1520271301269531,
       "learning_rate": 0.00019430219978362786,
-      "loss": 3.2142364501953127,
+      "loss": 3.2159664154052736,
       "step": 170
     },
     {
       "epoch": 0.09721847150958682,
-      "grad_norm": 1.3427095413208008,
+      "grad_norm": 1.3290963172912598,
       "learning_rate": 0.00019394157951676885,
-      "loss": 3.1775146484375,
+      "loss": 3.17901668548584,
       "step": 180
     },
     {
       "epoch": 0.10261949770456387,
-      "grad_norm": 1.453772783279419,
+      "grad_norm": 1.4537458419799805,
       "learning_rate": 0.00019358095924990984,
-      "loss": 3.076451301574707,
+      "loss": 3.076709747314453,
       "step": 190
     },
     {
       "epoch": 0.10802052389954091,
-      "grad_norm": 1.6937741041183472,
+      "grad_norm": 1.6899892091751099,
       "learning_rate": 0.00019322033898305085,
-      "loss": 2.9374858856201174,
+      "loss": 2.9362957000732424,
       "step": 200
     }
   ],