correct weights

README.md

@@ -5,14 +5,14 @@ metrics:
 - f1
 - accuracy
 model-index:
-- name: final-lr2e-5-bs16
+- name: final-lr2e-5-bs16-fp16-2
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# final-lr2e-5-bs16
+# final-lr2e-5-bs16-fp16-2
 
 This model is a fine-tuned version of [clincolnoz/MoreSexistBERT](https://huggingface.co/clincolnoz/MoreSexistBERT) on an unknown dataset.
 It achieves the following results on the evaluation set:

all_results.json

@@ -8,13 +8,13 @@
     "eval_f1_macro": 0.8461404562716657,
     "eval_f1_weighted": 0.886848806675738,
     "eval_loss": 0.33370330929756165,
-    "eval_runtime": 9.6197,
+    "eval_runtime": 9.6296,
     "eval_samples": 4000,
-    "eval_samples_per_second": 415.813,
-    "eval_steps_per_second": 25.988,
+    "eval_samples_per_second": 415.386,
+    "eval_steps_per_second": 25.962,
     "train_loss": 0.276834108988444,
-    "train_runtime": 437.8665,
+    "train_runtime": 431.6054,
     "train_samples": 16000,
-    "train_samples_per_second": 109.622,
-    "train_steps_per_second": 6.851
+    "train_samples_per_second": 111.213,
+    "train_steps_per_second": 6.951
 }

eval_results.json

@@ -8,8 +8,8 @@
     "eval_f1_macro": 0.8461404562716657,
     "eval_f1_weighted": 0.886848806675738,
     "eval_loss": 0.33370330929756165,
-    "eval_runtime": 9.6197,
+    "eval_runtime": 9.6296,
     "eval_samples": 4000,
-    "eval_samples_per_second": 415.813,
-    "eval_steps_per_second": 25.988
+    "eval_samples_per_second": 415.386,
+    "eval_steps_per_second": 25.962
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 0.276834108988444,
-    "train_runtime": 437.8665,
+    "train_runtime": 431.6054,
     "train_samples": 16000,
-    "train_samples_per_second": 109.622,
-    "train_steps_per_second": 6.851
+    "train_samples_per_second": 111.213,
+    "train_steps_per_second": 6.951
 }

trainer_state.json

@@ -29,9 +29,9 @@
       "eval_f1_macro": 0.8423411796129907,
       "eval_f1_weighted": 0.8870995333532351,
       "eval_loss": 0.2972576320171356,
-      "eval_runtime": 9.6794,
-      "eval_samples_per_second": 413.25,
-      "eval_steps_per_second": 25.828,
+      "eval_runtime": 9.6365,
+      "eval_samples_per_second": 415.089,
+      "eval_steps_per_second": 25.943,
       "step": 1000
     },
     {
@@ -56,9 +56,9 @@
       "eval_f1_macro": 0.8447159555400194,
       "eval_f1_weighted": 0.887180706758268,
       "eval_loss": 0.3277442157268524,
-      "eval_runtime": 9.6941,
-      "eval_samples_per_second": 412.622,
-      "eval_steps_per_second": 25.789,
+      "eval_runtime": 9.6604,
+      "eval_samples_per_second": 414.059,
+      "eval_steps_per_second": 25.879,
       "step": 2000
     },
     {
@@ -83,9 +83,9 @@
       "eval_f1_macro": 0.8461404562716657,
       "eval_f1_weighted": 0.886848806675738,
       "eval_loss": 0.33370330929756165,
-      "eval_runtime": 9.687,
-      "eval_samples_per_second": 412.925,
-      "eval_steps_per_second": 25.808,
+      "eval_runtime": 9.6495,
+      "eval_samples_per_second": 414.529,
+      "eval_steps_per_second": 25.908,
       "step": 3000
     },
     {
@@ -93,9 +93,9 @@
       "step": 3000,
       "total_flos": 1.262933065728e+16,
       "train_loss": 0.276834108988444,
-      "train_runtime": 437.8665,
-      "train_samples_per_second": 109.622,
-      "train_steps_per_second": 6.851
+      "train_runtime": 431.6054,
+      "train_samples_per_second": 111.213,
+      "train_steps_per_second": 6.951
     }
   ],
   "max_steps": 3000,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb122df23b2c784764604dd87da5c1c43d19519d4ac27e0d283af256f439e775
+oid sha256:a9ada95d1d7426f3a12392ac5aedd1f2ab1372620de8007e576b8a24b5d5cc21
 size 3643