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": 0.1313,
-    "eval_samples_per_second": 91.37,
-    "eval_steps_per_second": 7.614,
-    "train_loss": 0.8449213981628418,
-    "train_runtime": 65.3395,
-    "train_samples_per_second": 22.957,
-    "train_steps_per_second": 0.612
+    "eval_runtime": 0.1465,
+    "eval_samples_per_second": 81.924,
+    "eval_steps_per_second": 6.827,
+    "train_loss": 0.8449213564395904,
+    "train_runtime": 26.3276,
+    "train_samples_per_second": 56.974,
+    "train_steps_per_second": 1.519
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 20.0,
     "eval_loss": 2.79219126701355,
-    "eval_runtime": 0.1313,
-    "eval_samples_per_second": 91.37,
-    "eval_steps_per_second": 7.614
+    "eval_runtime": 0.1465,
+    "eval_samples_per_second": 81.924,
+    "eval_steps_per_second": 6.827
 }

runs/Mar08_11-40-06_9da45c1bcf23/events.out.tfevents.1709898047.9da45c1bcf23.38033.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2fae667595bc5705f02cc47bad7d9389d521280265f964bd9a11585b201837
+size 354

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 20.0,
-    "train_loss": 0.8449213981628418,
-    "train_runtime": 65.3395,
-    "train_samples_per_second": 22.957,
-    "train_steps_per_second": 0.612
+    "train_loss": 0.8449213564395904,
+    "train_runtime": 26.3276,
+    "train_samples_per_second": 56.974,
+    "train_steps_per_second": 1.519
 }

trainer_state.json

@@ -8,21 +8,77 @@
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 2.5,
+      "grad_norm": 37.25093460083008,
+      "learning_rate": 4.375e-05,
+      "loss": 2.2626,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 49.72227096557617,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.8291,
+      "step": 10
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 16.81373405456543,
+      "learning_rate": 3.125e-05,
+      "loss": 0.8602,
+      "step": 15
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 7.272302627563477,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5567,
+      "step": 20
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 9.128313064575195,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.7576,
+      "step": 25
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 14.296534538269043,
+      "learning_rate": 1.25e-05,
+      "loss": 0.4636,
+      "step": 30
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 5.532127380371094,
+      "learning_rate": 6.25e-06,
+      "loss": 0.6616,
+      "step": 35
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.8484093546867371,
+      "learning_rate": 0.0,
+      "loss": 0.3679,
+      "step": 40
+    },
     {
       "epoch": 20.0,
       "step": 40,
       "total_flos": 87250496949000.0,
-      "train_loss": 0.8449213981628418,
-      "train_runtime": 65.3395,
-      "train_samples_per_second": 22.957,
-      "train_steps_per_second": 0.612
+      "train_loss": 0.8449213564395904,
+      "train_runtime": 26.3276,
+      "train_samples_per_second": 56.974,
+      "train_steps_per_second": 1.519
     }
   ],
-  "logging_steps": 500,
+  "logging_steps": 5,
   "max_steps": 40,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
-  "save_steps": 5,
+  "save_steps": 500,
   "total_flos": 87250496949000.0,
   "train_batch_size": 64,
   "trial_name": null,