Upload folder using huggingface_hub

checkpoint-600/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:349414166cba298420b7d258a8646e5a2739f6f68b6de484bf0ee534f9ab641e
+oid sha256:9072726981ec7e8bf7d7756cc5487ad55281d66945a89c30b6a780ee878272ba
 size 501759848

checkpoint-600/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6f2bf80d3aad8ca62b05862952bf4bdd06c94c4aec076c56ebef337e100749
+oid sha256:e0e65d287cc1248788f59572bcae4537952068dbb45d16433f12032db06b0122
 size 254410983

checkpoint-600/trainer_state.json

@@ -361,72 +361,72 @@
     },
     {
       "epoch": 0.3138340833044883,
-      "grad_norm": 63.695133209228516,
+      "grad_norm": 63.603389739990234,
       "learning_rate": 5.0199999999999994e-05,
       "loss": 6.0088,
       "step": 510
     },
     {
       "epoch": 0.3199876927810469,
-      "grad_norm": 50.28738784790039,
+      "grad_norm": 50.28224563598633,
       "learning_rate": 5.119999999999999e-05,
       "loss": 5.9469,
       "step": 520
     },
     {
       "epoch": 0.32614130225760546,
-      "grad_norm": 43.3399543762207,
+      "grad_norm": 43.31625747680664,
       "learning_rate": 5.2199999999999995e-05,
       "loss": 5.9464,
       "step": 530
     },
     {
       "epoch": 0.3322949117341641,
-      "grad_norm": 48.50353240966797,
+      "grad_norm": 56.94966506958008,
       "learning_rate": 5.32e-05,
-      "loss": 5.9137,
+      "loss": 5.9139,
       "step": 540
     },
     {
       "epoch": 0.33844852121072266,
-      "grad_norm": 97.7204360961914,
+      "grad_norm": 97.49286651611328,
       "learning_rate": 5.4199999999999996e-05,
-      "loss": 5.9181,
+      "loss": 5.9177,
       "step": 550
     },
     {
       "epoch": 0.34460213068728124,
-      "grad_norm": 43.342079162597656,
+      "grad_norm": 57.25851058959961,
       "learning_rate": 5.519999999999999e-05,
-      "loss": 5.8822,
+      "loss": 5.8818,
       "step": 560
     },
     {
       "epoch": 0.35075574016383987,
-      "grad_norm": 51.02119827270508,
+      "grad_norm": 40.23714065551758,
       "learning_rate": 5.619999999999999e-05,
-      "loss": 5.8766,
+      "loss": 5.8755,
       "step": 570
     },
     {
       "epoch": 0.35690934964039844,
-      "grad_norm": 54.75588607788086,
+      "grad_norm": 39.241878509521484,
       "learning_rate": 5.72e-05,
-      "loss": 5.842,
+      "loss": 5.8417,
       "step": 580
     },
     {
       "epoch": 0.363062959116957,
-      "grad_norm": 49.630027770996094,
+      "grad_norm": 46.391117095947266,
       "learning_rate": 5.82e-05,
-      "loss": 5.8319,
+      "loss": 5.8327,
       "step": 590
     },
     {
       "epoch": 0.36921656859351565,
-      "grad_norm": 50.86918258666992,
+      "grad_norm": 51.62196350097656,
       "learning_rate": 5.9199999999999996e-05,
-      "loss": 5.7875,
+      "loss": 5.7876,
       "step": 600
     }
   ],