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: 1.1395
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
-    "eval_loss": 4.553551197052002,
-    "eval_runtime": 33.1837,
-    "eval_samples_per_second": 125.965,
-    "eval_steps_per_second": 1.989,
-    "train_loss": 2.0936863049357926,
-    "train_runtime": 1350.8765,
-    "train_samples_per_second": 55.695,
-    "train_steps_per_second": 0.871
+    "eval_loss": 1.139454960823059,
+    "eval_runtime": 0.728,
+    "eval_samples_per_second": 103.017,
+    "eval_steps_per_second": 2.747,
+    "train_loss": 1.8652879397074382,
+    "train_runtime": 4.8374,
+    "train_samples_per_second": 46.512,
+    "train_steps_per_second": 1.24
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "eval_loss": 4.553551197052002,
-    "eval_runtime": 33.1837,
-    "eval_samples_per_second": 125.965,
-    "eval_steps_per_second": 1.989
+    "eval_loss": 1.139454960823059,
+    "eval_runtime": 0.728,
+    "eval_samples_per_second": 103.017,
+    "eval_steps_per_second": 2.747
 }

runs/Mar08_11-05-33_9da45c1bcf23/events.out.tfevents.1709896014.9da45c1bcf23.28844.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8308bb08391c400da5bddd743d5443eb3cbe7d026b928dac8392e38ad1a9c5ca
+size 354

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 2.0936863049357926,
-    "train_runtime": 1350.8765,
-    "train_samples_per_second": 55.695,
-    "train_steps_per_second": 0.871
+    "train_loss": 1.8652879397074382,
+    "train_runtime": 4.8374,
+    "train_samples_per_second": 46.512,
+    "train_steps_per_second": 1.24
 }

trainer_state.json

@@ -3,41 +3,27 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1176,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 1.28,
-      "grad_norm": 25.054931640625,
-      "learning_rate": 2.8741496598639456e-05,
-      "loss": 2.6571,
-      "step": 500
-    },
-    {
-      "epoch": 2.55,
-      "grad_norm": 19.457901000976562,
-      "learning_rate": 7.482993197278912e-06,
-      "loss": 1.7886,
-      "step": 1000
-    },
     {
       "epoch": 3.0,
-      "step": 1176,
-      "total_flos": 4376310425967942.0,
-      "train_loss": 2.0936863049357926,
-      "train_runtime": 1350.8765,
-      "train_samples_per_second": 55.695,
-      "train_steps_per_second": 0.871
+      "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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1176,
+  "max_steps": 6,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 4376310425967942.0,
+  "total_flos": 13087574542350.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null