Training in progress, step 150, checkpoint

checkpoint-150/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613380280d3cd56dd958ffa13b63bc2bba19e9a4bbab89d8ace7f962baaf1865
+oid sha256:8deb0060d7358aeabd1230137b33365c199273f1adea1fb63f5896477c8c3c65
 size 165012392

checkpoint-150/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e41a29e47e1a17cd3a5a368ad2a24e159a4f38da0f71f5801290242d6ebd5521
+oid sha256:f6e5566d2fb0d78e03b6c33471dcf154fb8928ec5659362421bf60549d15e1f0
 size 84690389

checkpoint-150/trainer_state.json

@@ -11,115 +11,115 @@
   "log_history": [
     {
       "epoch": 0.022308979364194088,
-      "grad_norm": 4.757451057434082,
+      "grad_norm": 4.709710597991943,
       "learning_rate": 0.00019999446787180336,
-      "loss": 3.6770606994628907,
+      "loss": 3.676974868774414,
       "step": 10
     },
     {
       "epoch": 0.044617958728388175,
-      "grad_norm": 1.3747667074203491,
+      "grad_norm": 1.4567488431930542,
       "learning_rate": 0.00019989613595281384,
-      "loss": 1.009000873565674,
+      "loss": 0.9999975204467774,
       "step": 20
     },
     {
       "epoch": 0.06692693809258227,
-      "grad_norm": 1.0401424169540405,
+      "grad_norm": 1.1962672472000122,
       "learning_rate": 0.00019967500698688952,
-      "loss": 0.6844106197357178,
+      "loss": 0.6824670314788819,
       "step": 30
     },
     {
       "epoch": 0.08923591745677635,
-      "grad_norm": 0.8778170347213745,
+      "grad_norm": 0.8628137707710266,
       "learning_rate": 0.0001993313527961959,
-      "loss": 0.5973338603973388,
+      "loss": 0.5993218421936035,
       "step": 40
     },
     {
       "epoch": 0.11154489682097044,
-      "grad_norm": 1.0252398252487183,
+      "grad_norm": 1.0308934450149536,
       "learning_rate": 0.00019886559581668999,
-      "loss": 0.5388701915740967,
+      "loss": 0.542162561416626,
       "step": 50
     },
     {
       "epoch": 0.13385387618516453,
-      "grad_norm": 0.9101352095603943,
+      "grad_norm": 0.9261613488197327,
       "learning_rate": 0.00019827830857884173,
-      "loss": 0.44642319679260256,
+      "loss": 0.44734554290771483,
       "step": 60
     },
     {
       "epoch": 0.1561628555493586,
-      "grad_norm": 0.8221309185028076,
+      "grad_norm": 0.9318423867225647,
       "learning_rate": 0.00019757021300385286,
-      "loss": 0.4484751224517822,
+      "loss": 0.44412760734558104,
       "step": 70
     },
     {
       "epoch": 0.1784718349135527,
-      "grad_norm": 0.5932356119155884,
+      "grad_norm": 0.5784896612167358,
       "learning_rate": 0.00019674217951623707,
-      "loss": 0.40591115951538087,
+      "loss": 0.40378632545471194,
       "step": 80
     },
     {
       "epoch": 0.2007808142777468,
-      "grad_norm": 0.7747540473937988,
+      "grad_norm": 0.7836484909057617,
       "learning_rate": 0.00019579522597385315,
-      "loss": 0.38509316444396974,
+      "loss": 0.3856403350830078,
       "step": 90
     },
     {
       "epoch": 0.22308979364194087,
-      "grad_norm": 0.6519433259963989,
+      "grad_norm": 0.6503493189811707,
       "learning_rate": 0.00019473051641670606,
-      "loss": 0.38065552711486816,
+      "loss": 0.3800614356994629,
       "step": 100
     },
     {
       "epoch": 0.22308979364194087,
-      "eval_loss": 8.738031387329102,
-      "eval_runtime": 244.6378,
-      "eval_samples_per_second": 1.844,
-      "eval_steps_per_second": 1.844,
+      "eval_loss": 8.158984184265137,
+      "eval_runtime": 248.821,
+      "eval_samples_per_second": 1.813,
+      "eval_steps_per_second": 1.813,
       "step": 100
     },
     {
       "epoch": 0.24539877300613497,
-      "grad_norm": 0.5722377896308899,
+      "grad_norm": 0.582433819770813,
       "learning_rate": 0.00019354935963605393,
-      "loss": 0.3379225730895996,
+      "loss": 0.34090685844421387,
       "step": 110
     },
     {
       "epoch": 0.26770775237032907,
-      "grad_norm": 0.6395815014839172,
+      "grad_norm": 0.6219270825386047,
       "learning_rate": 0.00019225320756558023,
-      "loss": 0.3527653932571411,
+      "loss": 0.3560009956359863,
       "step": 120
     },
     {
       "epoch": 0.29001673173452314,
-      "grad_norm": 0.5309840440750122,
+      "grad_norm": 0.5081164836883545,
       "learning_rate": 0.0001908436534966081,
-      "loss": 0.32701103687286376,
+      "loss": 0.32209837436676025,
       "step": 130
     },
     {
       "epoch": 0.3123257110987172,
-      "grad_norm": 1.1165753602981567,
+      "grad_norm": 1.0672804117202759,
       "learning_rate": 0.00018932243011955154,
-      "loss": 0.42706594467163084,
+      "loss": 0.4280549049377441,
       "step": 140
     },
     {
       "epoch": 0.33463469046291133,
-      "grad_norm": 0.5633851885795593,
+      "grad_norm": 0.5716775059700012,
       "learning_rate": 0.00018769140739401062,
-      "loss": 0.2921785354614258,
+      "loss": 0.29103860855102537,
       "step": 150
     }
   ],