End of training

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2759
-- F1: 51.5181
-- Gen Len: 2.1307
+- Loss: 1.7845
+- F1: 54.9677
+- Gen Len: 2.3746
 
 ## Model description
 
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 10
 
 ### Training results
 

logs/events.out.tfevents.1714508539.0ce1cdb67813.20904.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75e09164bc1bcd6f3b80efbde6e62a38077b0e743d84108f1ef39dac03523c61
-size 6644
+oid sha256:d951aefcc217bb9bb162df117278725c1b5495de2c648e099261ad1c343e074d
+size 6998

logs/events.out.tfevents.1714512482.0ce1cdb67813.20904.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c797ca68ea8a8a6d5afeb3383ea91a133bcc0a2874e2068c81e33f4cb479216
+size 456

tokenizer.json

@@ -1,14 +1,9 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 3,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": {
     "strategy": {
-      "Fixed": 3
+      "Fixed": 512
     },
     "direction": "Right",
     "pad_to_multiple_of": null,