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": 2.79219126701355,
-    "eval_runtime": 0.1303,
-    "eval_samples_per_second": 92.084,
-    "eval_steps_per_second": 7.674,
+    "eval_runtime": 0.1313,
+    "eval_samples_per_second": 91.37,
+    "eval_steps_per_second": 7.614,
     "train_loss": 0.8449213981628418,
-    "train_runtime": 26.4579,
-    "train_samples_per_second": 56.694,
-    "train_steps_per_second": 1.512
+    "train_runtime": 65.3395,
+    "train_samples_per_second": 22.957,
+    "train_steps_per_second": 0.612
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 20.0,
     "eval_loss": 2.79219126701355,
-    "eval_runtime": 0.1303,
-    "eval_samples_per_second": 92.084,
-    "eval_steps_per_second": 7.674
+    "eval_runtime": 0.1313,
+    "eval_samples_per_second": 91.37,
+    "eval_steps_per_second": 7.614
 }

runs/Mar08_11-34-04_9da45c1bcf23/events.out.tfevents.1709897742.9da45c1bcf23.36373.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca6421f105ad4d68582a9c1d73ef2f1d6b69b32127529b28885a375e27f81f6
+size 354

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 20.0,
     "train_loss": 0.8449213981628418,
-    "train_runtime": 26.4579,
-    "train_samples_per_second": 56.694,
-    "train_steps_per_second": 1.512
+    "train_runtime": 65.3395,
+    "train_samples_per_second": 22.957,
+    "train_steps_per_second": 0.612
 }

trainer_state.json

@@ -13,16 +13,16 @@
       "step": 40,
       "total_flos": 87250496949000.0,
       "train_loss": 0.8449213981628418,
-      "train_runtime": 26.4579,
-      "train_samples_per_second": 56.694,
-      "train_steps_per_second": 1.512
+      "train_runtime": 65.3395,
+      "train_samples_per_second": 22.957,
+      "train_steps_per_second": 0.612
     }
   ],
   "logging_steps": 500,
   "max_steps": 40,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
-  "save_steps": 500,
+  "save_steps": 5,
   "total_flos": 87250496949000.0,
   "train_batch_size": 64,
   "trial_name": null,