End of training

README.md

@@ -2,7 +2,7 @@
 tags:
 - generated_from_trainer
 datasets:
-- category_cleaning
+- Displate/category_cleaning
 model-index:
 - name: category_cleaning
   results: []
@@ -13,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # category_cleaning
 
-This model was trained from scratch on the category_cleaning dataset.
+This model was trained from scratch on the Displate/category_cleaning dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7922
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 20.0,
-    "eval_loss": 0.9225080609321594,
-    "eval_runtime": 0.6477,
-    "eval_samples_per_second": 115.8,
-    "eval_steps_per_second": 3.088,
+    "eval_loss": 2.79219126701355,
+    "eval_runtime": 0.1414,
+    "eval_samples_per_second": 84.885,
+    "eval_steps_per_second": 7.074,
     "train_loss": 0.8449213981628418,
-    "train_runtime": 25.8102,
-    "train_samples_per_second": 58.117,
-    "train_steps_per_second": 1.55
+    "train_runtime": 26.0499,
+    "train_samples_per_second": 57.582,
+    "train_steps_per_second": 1.536
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 20.0,
-    "eval_loss": 0.9225080609321594,
-    "eval_runtime": 0.6477,
-    "eval_samples_per_second": 115.8,
-    "eval_steps_per_second": 3.088
+    "eval_loss": 2.79219126701355,
+    "eval_runtime": 0.1414,
+    "eval_samples_per_second": 84.885,
+    "eval_steps_per_second": 7.074
 }

runs/Mar08_11-26-39_9da45c1bcf23/events.out.tfevents.1709897238.9da45c1bcf23.34342.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1afba1c140eae7e12145839f4af4bf0671aaf10419d9b8b45873e7a76c9c9893
+size 354

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 20.0,
     "train_loss": 0.8449213981628418,
-    "train_runtime": 25.8102,
-    "train_samples_per_second": 58.117,
-    "train_steps_per_second": 1.55
+    "train_runtime": 26.0499,
+    "train_samples_per_second": 57.582,
+    "train_steps_per_second": 1.536
 }

trainer_state.json

@@ -13,9 +13,9 @@
       "step": 40,
       "total_flos": 87250496949000.0,
       "train_loss": 0.8449213981628418,
-      "train_runtime": 25.8102,
-      "train_samples_per_second": 58.117,
-      "train_steps_per_second": 1.55
+      "train_runtime": 26.0499,
+      "train_samples_per_second": 57.582,
+      "train_steps_per_second": 1.536
     }
   ],
   "logging_steps": 500,