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": 33.5078,
-    "eval_samples_per_second": 124.747,
-    "eval_steps_per_second": 1.97,
+    "eval_runtime": 33.4667,
+    "eval_samples_per_second": 124.9,
+    "eval_steps_per_second": 1.972,
     "train_loss": 2.093686363324016,
-    "train_runtime": 1348.3251,
-    "train_samples_per_second": 55.8,
-    "train_steps_per_second": 0.872
+    "train_runtime": 1371.5717,
+    "train_samples_per_second": 54.855,
+    "train_steps_per_second": 0.857
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
     "eval_loss": 4.553551197052002,
-    "eval_runtime": 33.5078,
-    "eval_samples_per_second": 124.747,
-    "eval_steps_per_second": 1.97
+    "eval_runtime": 33.4667,
+    "eval_samples_per_second": 124.9,
+    "eval_steps_per_second": 1.972
 }

runs/Mar08_14-42-38_9da45c1bcf23/events.out.tfevents.1709910378.9da45c1bcf23.83071.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1168c5f9dbc30410187ffc6f7f3ee2aa4d4338e45a564d7776a07de540b0bc3e
+size 359

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
     "train_loss": 2.093686363324016,
-    "train_runtime": 1348.3251,
-    "train_samples_per_second": 55.8,
-    "train_steps_per_second": 0.872
+    "train_runtime": 1371.5717,
+    "train_samples_per_second": 54.855,
+    "train_steps_per_second": 0.857
 }

trainer_state.json

@@ -2,7 +2,7 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 3.0,
-  "eval_steps": 500,
+  "eval_steps": 200.0,
   "global_step": 1176,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -90,9 +90,9 @@
       "step": 1176,
       "total_flos": 4376310425967942.0,
       "train_loss": 2.093686363324016,
-      "train_runtime": 1348.3251,
-      "train_samples_per_second": 55.8,
-      "train_steps_per_second": 0.872
+      "train_runtime": 1371.5717,
+      "train_samples_per_second": 54.855,
+      "train_steps_per_second": 0.857
     }
   ],
   "logging_steps": 100,