updated weights

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4576e678e5ba090b8e55536601ba56fbdf3b23deb3ab6d16529ec6ca6eb7e4
+size 875988101

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18170c2bfbd6cad02a29ccbbad9efe9f35306b0b5f1ede04ee39659b9ffacc8
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8ed8f13396c7484ac7ba6e23de0e54f73f6ab5e3b73cf96616da00285bc1a5
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b822a091b5ac94987a820182ddf83180bf6e008c2110389c49928cc36fba8c
+size 627

trainer_state.json

@@ -29,9 +29,9 @@
       "eval_f1_macro": 0.8164747268943042,
       "eval_f1_weighted": 0.8671586721613128,
       "eval_loss": 0.3063889145851135,
-      "eval_runtime": 9.6219,
-      "eval_samples_per_second": 415.716,
-      "eval_steps_per_second": 25.982,
+      "eval_runtime": 9.6345,
+      "eval_samples_per_second": 415.174,
+      "eval_steps_per_second": 25.948,
       "step": 1000
     },
     {
@@ -56,9 +56,9 @@
       "eval_f1_macro": 0.8238171249071711,
       "eval_f1_weighted": 0.8707720634053486,
       "eval_loss": 0.3905148506164551,
-      "eval_runtime": 9.6114,
-      "eval_samples_per_second": 416.171,
-      "eval_steps_per_second": 26.011,
+      "eval_runtime": 9.6074,
+      "eval_samples_per_second": 416.348,
+      "eval_steps_per_second": 26.022,
       "step": 2000
     },
     {
@@ -83,19 +83,10 @@
       "eval_f1_macro": 0.8301269502098749,
       "eval_f1_weighted": 0.8771718049600645,
       "eval_loss": 0.4823172092437744,
-      "eval_runtime": 9.6152,
-      "eval_samples_per_second": 416.008,
-      "eval_steps_per_second": 26.001,
+      "eval_runtime": 9.6225,
+      "eval_samples_per_second": 415.692,
+      "eval_steps_per_second": 25.981,
       "step": 3000
-    },
-    {
-      "epoch": 3.0,
-      "step": 3000,
-      "total_flos": 1.262933065728e+16,
-      "train_loss": 0.2520793151855469,
-      "train_runtime": 436.5353,
-      "train_samples_per_second": 109.957,
-      "train_steps_per_second": 6.872
     }
   ],
   "max_steps": 3000,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f690688caffb0146c3fa68d936f62ed393c2384ca461e7f940fd8e53c0aff02
-size 3643
+oid sha256:3339ea6cd4c40a8cccf32dfd823bcd135cf0d42f2a8369a143f9bc5aab5ebb78
+size 3579