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: 1.2829
-- F1: 65.7304
-- Gen Len: 2.0755
+- Loss: 1.4133
+- F1: 64.2468
+- Gen Len: 2.0708
 
 ## Model description
 
@@ -38,8 +38,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

logs/events.out.tfevents.1739850696.ee6f4c9d7b3c.31.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27456448adca0c628444e4d8628dd3804559a8a49290e541ed8f8d57b349fc18
-size 6649
+oid sha256:81b049992d46d2e6a19d29124f2f4b8b3c05040bf2668330e0910f2419fded1c
+size 7003

logs/events.out.tfevents.1739851685.ee6f4c9d7b3c.31.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4150255c9a9cf601220e31f3a1a9eaa19169b9bafb495a823429e4f6670ebe6d
+size 456

tokenizer.json

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