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-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0231
-- F1: 97.6467
-- Gen Len: 7.5860
+- Loss: 0.0539
+- F1: 97.4262
+- Gen Len: 2.6128
 
 ## Model description
 
@@ -39,20 +39,24 @@ 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
-- num_epochs: 10
+- num_epochs: 2
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | F1      | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| 0.0857        | 1.0   | 1385 | 0.0637          | 95.5888 | 2.5885  |
+| 0.0255        | 2.0   | 2770 | 0.0539          | 97.4262 | 2.6128  |
 
 
 ### Framework versions
 
 - Transformers 4.44.0
 - Pytorch 2.4.0
-- Datasets 3.0.1
+- Datasets 3.1.0
 - Tokenizers 0.19.1

logs/events.out.tfevents.1734433923.d9a1597ffdf1.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114231716e5a279e3dd0d32201286ce44067fb3347bc44045ed34766a21efa45
+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,