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": 1.2932854890823364,
-    "eval_runtime": 0.1299,
-    "eval_samples_per_second": 92.356,
-    "eval_steps_per_second": 7.696,
+    "eval_runtime": 0.1643,
+    "eval_samples_per_second": 73.032,
+    "eval_steps_per_second": 6.086,
     "train_loss": 1.8652879397074382,
-    "train_runtime": 4.8165,
-    "train_samples_per_second": 46.715,
-    "train_steps_per_second": 1.246
+    "train_runtime": 4.9548,
+    "train_samples_per_second": 45.411,
+    "train_steps_per_second": 1.211
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
     "eval_loss": 1.2932854890823364,
-    "eval_runtime": 0.1299,
-    "eval_samples_per_second": 92.356,
-    "eval_steps_per_second": 7.696
+    "eval_runtime": 0.1643,
+    "eval_samples_per_second": 73.032,
+    "eval_steps_per_second": 6.086
 }

runs/Mar08_15-13-25_9da45c1bcf23/events.out.tfevents.1709910826.9da45c1bcf23.90928.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf5992cc498f1fcae557be2789f4b8356af421b58529150e51b82b6d4f851db
+size 354

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
     "train_loss": 1.8652879397074382,
-    "train_runtime": 4.8165,
-    "train_samples_per_second": 46.715,
-    "train_steps_per_second": 1.246
+    "train_runtime": 4.9548,
+    "train_samples_per_second": 45.411,
+    "train_steps_per_second": 1.211
 }

trainer_state.json

@@ -2,7 +2,7 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 3.0,
-  "eval_steps": 100,
+  "eval_steps": 10,
   "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -13,12 +13,12 @@
       "step": 6,
       "total_flos": 13087574542350.0,
       "train_loss": 1.8652879397074382,
-      "train_runtime": 4.8165,
-      "train_samples_per_second": 46.715,
-      "train_steps_per_second": 1.246
+      "train_runtime": 4.9548,
+      "train_samples_per_second": 45.411,
+      "train_steps_per_second": 1.211
     }
   ],
-  "logging_steps": 100,
+  "logging_steps": 10,
   "max_steps": 6,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,