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: 0.9814
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 1.2932854890823364,
-    "eval_runtime": 0.156,
-    "eval_samples_per_second": 76.917,
-    "eval_steps_per_second": 6.41,
-    "train_loss": 1.8652879397074382,
-    "train_runtime": 4.7964,
-    "train_samples_per_second": 46.91,
-    "train_steps_per_second": 1.251
+    "epoch": 10.0,
+    "eval_loss": 0.9814479351043701,
+    "eval_runtime": 0.6923,
+    "eval_samples_per_second": 108.332,
+    "eval_steps_per_second": 2.889,
+    "train_loss": 1.109443473815918,
+    "train_runtime": 13.1048,
+    "train_samples_per_second": 57.231,
+    "train_steps_per_second": 1.526
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 1.2932854890823364,
-    "eval_runtime": 0.156,
-    "eval_samples_per_second": 76.917,
-    "eval_steps_per_second": 6.41
+    "epoch": 10.0,
+    "eval_loss": 0.9814479351043701,
+    "eval_runtime": 0.6923,
+    "eval_samples_per_second": 108.332,
+    "eval_steps_per_second": 2.889
 }

runs/Mar08_11-22-59_9da45c1bcf23/events.out.tfevents.1709897050.9da45c1bcf23.33316.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc42e6e85a120ac60b7214845f008d35fc5cdc7379e7fb7190ac06bdbced4de
+size 354

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 77,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 77
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 49407,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 49406,

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.8652879397074382,
-    "train_runtime": 4.7964,
-    "train_samples_per_second": 46.91,
-    "train_steps_per_second": 1.251
+    "epoch": 10.0,
+    "train_loss": 1.109443473815918,
+    "train_runtime": 13.1048,
+    "train_samples_per_second": 57.231,
+    "train_steps_per_second": 1.526
 }

trainer_state.json

@@ -1,29 +1,29 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 6,
+  "global_step": 20,
   "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": 4.7964,
-      "train_samples_per_second": 46.91,
-      "train_steps_per_second": 1.251
+      "epoch": 10.0,
+      "step": 20,
+      "total_flos": 43625248474500.0,
+      "train_loss": 1.109443473815918,
+      "train_runtime": 13.1048,
+      "train_samples_per_second": 57.231,
+      "train_steps_per_second": 1.526
     }
   ],
   "logging_steps": 500,
-  "max_steps": 6,
+  "max_steps": 20,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 13087574542350.0,
+  "total_flos": 43625248474500.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null