Training complete

README.md

@@ -5,7 +5,7 @@ tags:
 - text2text-generation
 - generated_from_trainer
 metrics:
-- rouge
+- sacrebleu
 model-index:
 - name: ViT5_Vietnamese_Correction
   results: []
@@ -18,12 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0456
-- Rouge1: 75.1415
-- Rouge2: 72.5591
-- Rougel: 74.7125
-- Rougelsum: 74.7157
-- Gen Len: 18.5922
+- Loss: 0.0413
+- Sacrebleu: 34.6205
 
 ## Model description
 
@@ -43,8 +39,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 5
+- eval_batch_size: 5
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -52,14 +48,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| 0.101         | 1.0   | 7500 | 0.0456          | 75.1415 | 72.5591 | 74.7125 | 74.7157   | 18.5922 |
+| Training Loss | Epoch | Step  | Validation Loss | Sacrebleu |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|
+| 0.0503        | 1.0   | 10000 | 0.0413          | 34.6205   |
 
 
 ### Framework versions
 
-- Transformers 4.41.0
+- Transformers 4.41.2
 - Pytorch 2.3.0+cu121
-- Datasets 2.19.1
+- Datasets 2.19.2
 - Tokenizers 0.19.1

config.json

@@ -26,7 +26,7 @@
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.0",
+  "transformers_version": "4.41.2",
   "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": "4.41.0"
+  "transformers_version": "4.41.2"
 }

logs/events.out.tfevents.1717609476.c2cc565344d6.878.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67fc5f60b58ce65125e159c9d99034f1b94d028f95983fc03e844a20af124357
+size 4184

logs/events.out.tfevents.1717609620.c2cc565344d6.2864.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13fa5fea938e95f0a3c7f7a1a79ea8770ba629650362b8512f8a97b929797eeb
+size 4184

logs/events.out.tfevents.1717609730.c2cc565344d6.3737.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dabe1c5da2ae85a8926a2699e11614b2b3a45afe48dd504722053fc125bbc4cc
+size 4184

logs/events.out.tfevents.1717609850.c2cc565344d6.4205.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e660ceddf1609e3dd903905b0b65cd2230f786c791aa41da92911d1556e8e6
+size 6214

logs/events.out.tfevents.1717618806.c2cc565344d6.4205.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62aeab96799d872de638316a3c2b9c897194b6b7a3038be295b1c165f4197ba1
+size 412

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f4d56848f5824b7010cb1dbd04817e725732cc8b306752cc10b3007577824c
+oid sha256:d8d24a754cce5ff931c597b2546f2fb51df1395c3e2e9eba52022c3ce06b94d7
 size 903834408

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c78cc6a5b964608fc9d307afafc229d4fbd5d6e9593fe50aab754a568d71ecf
-size 5240
+oid sha256:573c95f33fce6ac0ce2cb3cb8f9d13586b5cc23847c2633d584942bdafe4f396
+size 5304