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: 1.2933
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
-    "eval_loss": 1.139454960823059,
-    "eval_runtime": 0.728,
-    "eval_samples_per_second": 103.017,
-    "eval_steps_per_second": 2.747,
+    "eval_loss": 1.2932854890823364,
+    "eval_runtime": 0.156,
+    "eval_samples_per_second": 76.917,
+    "eval_steps_per_second": 6.41,
     "train_loss": 1.8652879397074382,
-    "train_runtime": 4.8374,
-    "train_samples_per_second": 46.512,
-    "train_steps_per_second": 1.24
+    "train_runtime": 4.7964,
+    "train_samples_per_second": 46.91,
+    "train_steps_per_second": 1.251
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "eval_loss": 1.139454960823059,
-    "eval_runtime": 0.728,
-    "eval_samples_per_second": 103.017,
-    "eval_steps_per_second": 2.747
+    "eval_loss": 1.2932854890823364,
+    "eval_runtime": 0.156,
+    "eval_samples_per_second": 76.917,
+    "eval_steps_per_second": 6.41
 }

runs/Mar08_11-07-54_9da45c1bcf23/events.out.tfevents.1709896093.9da45c1bcf23.29499.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6730a3ad673d18680aa7afd58b6577692eb014a867df4c8f80d5a249bbfd283
+size 354

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
     "train_loss": 1.8652879397074382,
-    "train_runtime": 4.8374,
-    "train_samples_per_second": 46.512,
-    "train_steps_per_second": 1.24
+    "train_runtime": 4.7964,
+    "train_samples_per_second": 46.91,
+    "train_steps_per_second": 1.251
 }

trainer_state.json

@@ -13,9 +13,9 @@
       "step": 6,
       "total_flos": 13087574542350.0,
       "train_loss": 1.8652879397074382,
-      "train_runtime": 4.8374,
-      "train_samples_per_second": 46.512,
-      "train_steps_per_second": 1.24
+      "train_runtime": 4.7964,
+      "train_samples_per_second": 46.91,
+      "train_steps_per_second": 1.251
     }
   ],
   "logging_steps": 500,