End of training

README.md

@@ -1,6 +1,7 @@
 ---
+library_name: transformers
 license: mit
-base_model: VietAI/ViT5-base
+base_model: VietAI/vit5-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ViNormT5
 
-This model is a fine-tuned version of [VietAI/ViT5-base](https://huggingface.co/VietAI/ViT5-base) on the None dataset.
+This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2171
-- Bleu Score: 75.3569
-- Gen Len: 13.1514
+- Loss: 0.2302
+- Bleu Score: 73.8994
+- Gen Len: 13.2
 
 ## Model description
 
@@ -36,26 +37,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.0001
+- 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: 3
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu Score | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:----------:|:-------:|
-| 0.4669        | 1.0   | 524  | 0.2426          | 73.5538    | 13.1838 |
-| 0.1732        | 2.0   | 1048 | 0.2127          | 74.877     | 13.1457 |
-| 0.0691        | 3.0   | 1572 | 0.2171          | 75.3569    | 13.1514 |
+| 0.4035        | 1.0   | 1047 | 0.2302          | 73.8994    | 13.2    |
 
 
 ### Framework versions
 
-- Transformers 4.40.2
-- Pytorch 2.2.1+cu121
-- Datasets 2.19.1
-- Tokenizers 0.19.1
+- Transformers 4.45.0
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.0
+- Tokenizers 0.20.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "VietAI/ViT5-base",
+  "_name_or_path": "VietAI/vit5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -26,7 +26,7 @@
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.45.0",
   "use_cache": true,
   "vocab_size": 36096
 }

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.45.0"
 }

logs/events.out.tfevents.1727288158.bff8058f5765.284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947add78459fdf826552471b94f2b1687194d9927f0c7d5b3b808e9368231902
+size 5153

logs/events.out.tfevents.1727288768.bff8058f5765.3515.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5939e56cbcd5bac74a79517a12dd39fb3e2b829fcd757139e0f4291a2db0bd34
+size 6123

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adeac3b72c78d65a8171a50fe063e8265ce8575e0b093d748a63e7d4434fe889
+oid sha256:3fa29406cb614bdcaf184a87b9f0826ee865ebe4698c08c4b4082053421024d0
 size 903834408

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0cff575a8dc157cad6c4435900365becfb72edbe5ec52f386fdcb61e3b99ad
-size 5112
+oid sha256:93949cfb1f986ac46e7b4900541787ed01503c07e3cac43ae122984910898794
+size 5304