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": 3.0,
-    "eval_loss": 1.2932854890823364,
-    "eval_runtime": 0.1308,
-    "eval_samples_per_second": 91.776,
-    "eval_steps_per_second": 7.648,
-    "train_loss": 1.8652879397074382,
-    "train_runtime": 4.8651,
-    "train_samples_per_second": 46.248,
-    "train_steps_per_second": 1.233
+    "epoch": 20.0,
+    "eval_loss": 2.79219126701355,
+    "eval_runtime": 0.1303,
+    "eval_samples_per_second": 92.084,
+    "eval_steps_per_second": 7.674,
+    "train_loss": 0.8449213981628418,
+    "train_runtime": 26.4579,
+    "train_samples_per_second": 56.694,
+    "train_steps_per_second": 1.512
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 1.2932854890823364,
-    "eval_runtime": 0.1308,
-    "eval_samples_per_second": 91.776,
-    "eval_steps_per_second": 7.648
+    "epoch": 20.0,
+    "eval_loss": 2.79219126701355,
+    "eval_runtime": 0.1303,
+    "eval_samples_per_second": 92.084,
+    "eval_steps_per_second": 7.674
 }

runs/Mar08_11-28-40_9da45c1bcf23/events.out.tfevents.1709897361.9da45c1bcf23.34946.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959ca3a9247108d159bf5240e58492fbe80b868dd4553844b0f5b5c4bf5d7d86
+size 354

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.8652879397074382,
-    "train_runtime": 4.8651,
-    "train_samples_per_second": 46.248,
-    "train_steps_per_second": 1.233
+    "epoch": 20.0,
+    "train_loss": 0.8449213981628418,
+    "train_runtime": 26.4579,
+    "train_samples_per_second": 56.694,
+    "train_steps_per_second": 1.512
 }

trainer_state.json

@@ -1,29 +1,29 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 6,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 6,
-      "total_flos": 13087574542350.0,
-      "train_loss": 1.8652879397074382,
-      "train_runtime": 4.8651,
-      "train_samples_per_second": 46.248,
-      "train_steps_per_second": 1.233
+      "epoch": 20.0,
+      "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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 6,
+  "max_steps": 40,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 13087574542350.0,
+  "total_flos": 87250496949000.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null