End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0217
-- F1: 93.8974
-- Gen Len: 7.5422
+- Loss: 0.0711
+- F1: 93.9739
+- Gen Len: 2.5591
 
 ## Model description
 
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1      | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| 0.0466        | 1.0   | 1466 | 0.0234          | 92.7414 | 7.5399  |
-| 0.0231        | 2.0   | 2932 | 0.0217          | 93.8974 | 7.5422  |
+| 0.1323        | 1.0   | 1466 | 0.0928          | 90.9839 | 2.6044  |
+| 0.0707        | 2.0   | 2932 | 0.0711          | 93.9739 | 2.5591  |
 
 
 ### Framework versions

logs/events.out.tfevents.1734379163.411a85c0634c.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30253d5a7c9fb2536e609701934a741302e6ac1137c5ca9a92e84d4d5c7dee0d
+size 456

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 8,
+    "max_length": 3,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 8
+      "Fixed": 3
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -927,7 +927,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 512,