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: 4.5536
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
     "eval_loss": 4.553551197052002,
-    "eval_runtime": 31.4178,
-    "eval_samples_per_second": 133.046,
-    "eval_steps_per_second": 2.101,
+    "eval_runtime": 33.1837,
+    "eval_samples_per_second": 125.965,
+    "eval_steps_per_second": 1.989,
     "train_loss": 2.0936863049357926,
-    "train_runtime": 1316.5495,
-    "train_samples_per_second": 57.147,
-    "train_steps_per_second": 0.893
+    "train_runtime": 1350.8765,
+    "train_samples_per_second": 55.695,
+    "train_steps_per_second": 0.871
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
     "eval_loss": 4.553551197052002,
-    "eval_runtime": 31.4178,
-    "eval_samples_per_second": 133.046,
-    "eval_steps_per_second": 2.101
+    "eval_runtime": 33.1837,
+    "eval_samples_per_second": 125.965,
+    "eval_steps_per_second": 1.989
 }

runs/Mar08_10-34-19_9da45c1bcf23/events.out.tfevents.1709895456.9da45c1bcf23.20857.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b435b8473de09b5b55dd2ba5b03360cdd2aa8a3a5e79a31c19d8cf6a267b8a05
+size 359

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
     "train_loss": 2.0936863049357926,
-    "train_runtime": 1316.5495,
-    "train_samples_per_second": 57.147,
-    "train_steps_per_second": 0.893
+    "train_runtime": 1350.8765,
+    "train_samples_per_second": 55.695,
+    "train_steps_per_second": 0.871
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "step": 1176,
       "total_flos": 4376310425967942.0,
       "train_loss": 2.0936863049357926,
-      "train_runtime": 1316.5495,
-      "train_samples_per_second": 57.147,
-      "train_steps_per_second": 0.893
+      "train_runtime": 1350.8765,
+      "train_samples_per_second": 55.695,
+      "train_steps_per_second": 0.871
     }
   ],
   "logging_steps": 500,