Upload folder using huggingface_hub

checkpoint-800/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b924d546b2d6e9f0c3e794b5d6af38a078d3488f324c6d95b1f62fdcf5c49ec5
+oid sha256:14acfe5d0a60ad01859235191f46b05c380259a3ae31692d5b97fb19370f7ab9
 size 501759848

checkpoint-800/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4017f7937b70cba45805cc7651f9675c2d03e2353f9b33d79f0fd87a4e9459db
+oid sha256:6f820a60232165ebc3b04cc7f3ff1672d7999e5857c1c9ce371d4dbb4d1b81e4
 size 254410983

checkpoint-800/trainer_state.json

@@ -501,72 +501,72 @@
     },
     {
       "epoch": 0.4369062728356602,
-      "grad_norm": 41.11359786987305,
+      "grad_norm": 41.100425720214844,
       "learning_rate": 7.02e-05,
       "loss": 5.6157,
       "step": 710
     },
     {
       "epoch": 0.44305988231221877,
-      "grad_norm": 46.67518997192383,
+      "grad_norm": 46.8226432800293,
       "learning_rate": 7.12e-05,
       "loss": 5.5794,
       "step": 720
     },
     {
       "epoch": 0.44921349178877734,
-      "grad_norm": 33.07991409301758,
+      "grad_norm": 33.2792854309082,
       "learning_rate": 7.219999999999999e-05,
-      "loss": 5.573,
+      "loss": 5.5731,
       "step": 730
     },
     {
       "epoch": 0.45536710126533597,
-      "grad_norm": 42.006980895996094,
+      "grad_norm": 44.90331268310547,
       "learning_rate": 7.319999999999999e-05,
       "loss": 5.5528,
       "step": 740
     },
     {
       "epoch": 0.46152071074189455,
-      "grad_norm": 48.60676956176758,
+      "grad_norm": 48.1407356262207,
       "learning_rate": 7.419999999999999e-05,
-      "loss": 5.539,
+      "loss": 5.5387,
       "step": 750
     },
     {
       "epoch": 0.4676743202184531,
-      "grad_norm": 37.12602996826172,
+      "grad_norm": 37.969139099121094,
       "learning_rate": 7.519999999999998e-05,
       "loss": 5.5043,
       "step": 760
     },
     {
       "epoch": 0.47382792969501175,
-      "grad_norm": 34.83266830444336,
+      "grad_norm": 35.248779296875,
       "learning_rate": 7.62e-05,
-      "loss": 5.4856,
+      "loss": 5.4854,
       "step": 770
     },
     {
       "epoch": 0.4799815391715703,
-      "grad_norm": 33.03480911254883,
+      "grad_norm": 32.92762756347656,
       "learning_rate": 7.72e-05,
       "loss": 5.4737,
       "step": 780
     },
     {
       "epoch": 0.4861351486481289,
-      "grad_norm": 36.85569381713867,
+      "grad_norm": 44.820735931396484,
       "learning_rate": 7.819999999999999e-05,
-      "loss": 5.469,
+      "loss": 5.4688,
       "step": 790
     },
     {
       "epoch": 0.49228875812468753,
-      "grad_norm": 40.46368408203125,
+      "grad_norm": 46.39222717285156,
       "learning_rate": 7.92e-05,
-      "loss": 5.4437,
+      "loss": 5.4436,
       "step": 800
     }
   ],