End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.0415
+- Loss: 0.2677
 
 ## Model description
 
@@ -36,26 +36,25 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 2
-- eval_batch_size: 1
+- eval_batch_size: 2
 - seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 7.9301        | 0.51  | 20   | 5.5874          |
-| 4.5762        | 1.03  | 40   | 4.2359          |
-| 4.1575        | 1.54  | 60   | 4.1457          |
-| 3.9223        | 2.05  | 80   | 4.0708          |
-| 3.9971        | 2.56  | 100  | 4.0415          |
+| 1.4276        | 4.56  | 200  | 0.2848          |
+| 0.4608        | 9.12  | 400  | 0.2677          |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
+- Transformers 4.33.2
 - Pytorch 2.0.1+cu117
 - Datasets 2.14.5
 - Tokenizers 0.13.3

config.json

@@ -26,7 +26,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.33.2",
   "use_cache": false,
   "vocab_size": 36100
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.33.1"
+  "transformers_version": "4.33.2"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eca7b6d3dc820c7e1fc2562cf60966be6be93f46b8136dee51400f29dad7629
+oid sha256:f13cc5e4db4645218b26421d9bb742ba269f5b3f8ac08699e7bd1298c3d2f8ce
 size 3165332293

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b35b57f3df7b9418eb04f147f33facd7c4b930df5587c1192593ae4fb2000c
+oid sha256:385c3f03dadcb879cb805675034b7d981864d17b569a5b6843def24d9eeb6515
 size 4155