Upload folder using huggingface_hub

checkpoint-2000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee717646ebb7d7bbc57bd5d823706955c90030c54b3c0b5ce6ba595079d4bae6
+oid sha256:15b8ad3702109a72e8f6aa1ec348f7abbc04f5efcbd76aebf21ef94ae101f52f
 size 501759848

checkpoint-2000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02639cf6f9bdb3a74b728b46f769b37cd8477cb8fd0bc433c1fd1ba7942a73ff
+oid sha256:4fd248cda17a410a248833d09823a46eab75e1a3832548d6d1743c0eefff1255
 size 254410983

checkpoint-2000/trainer_state.json

@@ -1341,72 +1341,72 @@
     },
     {
       "epoch": 1.174762509134264,
-      "grad_norm": 18.336278915405273,
+      "grad_norm": 18.34984016418457,
       "learning_rate": 0.0001902,
       "loss": 2.9567,
       "step": 1910
     },
     {
       "epoch": 1.1809161186108226,
-      "grad_norm": 17.372344970703125,
+      "grad_norm": 17.388120651245117,
       "learning_rate": 0.00019119999999999999,
       "loss": 2.9164,
       "step": 1920
     },
     {
       "epoch": 1.1870697280873812,
-      "grad_norm": 18.396799087524414,
+      "grad_norm": 18.276813507080078,
       "learning_rate": 0.0001922,
       "loss": 2.8638,
       "step": 1930
     },
     {
       "epoch": 1.1932233375639398,
-      "grad_norm": 17.33060646057129,
+      "grad_norm": 17.28123664855957,
       "learning_rate": 0.00019319999999999998,
-      "loss": 2.901,
+      "loss": 2.9009,
       "step": 1940
     },
     {
       "epoch": 1.1993769470404985,
-      "grad_norm": 17.035425186157227,
+      "grad_norm": 16.94942855834961,
       "learning_rate": 0.00019419999999999998,
-      "loss": 2.9129,
+      "loss": 2.9128,
       "step": 1950
     },
     {
       "epoch": 1.205530556517057,
-      "grad_norm": 18.460824966430664,
+      "grad_norm": 18.007675170898438,
       "learning_rate": 0.00019519999999999997,
       "loss": 2.8609,
       "step": 1960
     },
     {
       "epoch": 1.2116841659936157,
-      "grad_norm": 18.200681686401367,
+      "grad_norm": 18.41819953918457,
       "learning_rate": 0.0001962,
-      "loss": 2.8671,
+      "loss": 2.8666,
       "step": 1970
     },
     {
       "epoch": 1.2178377754701741,
-      "grad_norm": 17.20355224609375,
+      "grad_norm": 17.115619659423828,
       "learning_rate": 0.00019719999999999997,
-      "loss": 2.8814,
+      "loss": 2.8805,
       "step": 1980
     },
     {
       "epoch": 1.2239913849467328,
-      "grad_norm": 18.240800857543945,
+      "grad_norm": 17.493419647216797,
       "learning_rate": 0.00019819999999999997,
-      "loss": 2.8566,
+      "loss": 2.8557,
       "step": 1990
     },
     {
       "epoch": 1.2301449944232914,
-      "grad_norm": 18.11919403076172,
+      "grad_norm": 18.269655227661133,
       "learning_rate": 0.0001992,
-      "loss": 2.8356,
+      "loss": 2.8357,
       "step": 2000
     }
   ],