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: 1.4078
-- F1: 63.5837
-- Gen Len: 2.0704
+- Loss: 1.2829
+- F1: 65.7304
+- Gen Len: 2.0755
 
 ## 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: 15
+- num_epochs: 10
 
 ### Training results
 

logs/events.out.tfevents.1739737168.8e3f8e6aefc8.31.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7634cd15d06f29740f34b3d54314e33af48d48ee0987de6e57c9de49b10651c0
-size 6646
+oid sha256:174fa967b0976a37669888bf52a03ca2c55f9aa60efeed0c568c8b01be22e1ad
+size 7000

logs/events.out.tfevents.1739737999.8e3f8e6aefc8.31.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb02061784a3c502dfaa311013cc2f682fb9ecac3a0ec2ba1b01b6b8308b5af4
+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,