End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: Helsinki-NLP/opus-mt-en-ro
+base_model: Helsinki-NLP/opus-mt-en-vi
 tags:
 - generated_from_trainer
 metrics:
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Final-DeepLearning
 
-This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ro](https://huggingface.co/Helsinki-NLP/opus-mt-en-ro) on an unknown dataset.
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-vi](https://huggingface.co/Helsinki-NLP/opus-mt-en-vi) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5198
-- Bleu: 10.7188
-- Gen Len: 16.769
+- Loss: 1.6884
+- Bleu: 26.3182
+- Gen Len: 11.991
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| 2.4733        | 1.0   | 6250 | 2.5198          | 10.7188 | 16.769  |
+| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
+| 1.697         | 1.0   | 31250 | 1.6884          | 26.3182 | 11.991  |
 
 
 ### Framework versions

config.json

@@ -1,6 +1,5 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-en-ro",
-  "_num_labels": 3,
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-vi",
   "activation_dropout": 0.0,
   "activation_function": "swish",
   "add_bias_logits": false,
@@ -11,7 +10,7 @@
   "attention_dropout": 0.0,
   "bad_words_ids": [
     [
-      59542
+      53684
     ]
   ],
   "bos_token_id": 0,
@@ -22,14 +21,15 @@
   "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
-  "decoder_start_token_id": 59542,
-  "decoder_vocab_size": 59543,
+  "decoder_start_token_id": 53684,
+  "decoder_vocab_size": 53685,
   "dropout": 0.1,
   "encoder_attention_heads": 8,
   "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 0,
+  "extra_pos_embeddings": 53685,
   "forced_eos_token_id": 0,
   "id2label": {
     "0": "LABEL_0",
@@ -50,12 +50,12 @@
   "normalize_embedding": false,
   "num_beams": 4,
   "num_hidden_layers": 6,
-  "pad_token_id": 59542,
+  "pad_token_id": 53684,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
   "use_cache": true,
-  "vocab_size": 59543
+  "vocab_size": 53685
 }

generation_config.json

@@ -1,16 +1,16 @@
 {
   "bad_words_ids": [
     [
-      59542
+      53684
     ]
   ],
   "bos_token_id": 0,
-  "decoder_start_token_id": 59542,
+  "decoder_start_token_id": 53684,
   "eos_token_id": 0,
   "forced_eos_token_id": 0,
   "max_length": 512,
   "num_beams": 4,
-  "pad_token_id": 59542,
+  "pad_token_id": 53684,
   "renormalize_logits": true,
   "transformers_version": "4.40.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26681cee87d8e76586a85b2feb6ad62fafc7aae952dd6feae303ef83bf2e7f42
-size 298765276
+oid sha256:d4ee024a57cfa5771019d1d3b732dc1364269496744972103d3df06e8f943c22
+size 286744660

runs/May13_15-28-00_00387894e89d/events.out.tfevents.1715614091.00387894e89d.4653.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d3d154fcf346807107e8e701ebab42324a87a724cd3b6f47a9ac7aaac2b29df
+size 19509

runs/May13_15-28-00_00387894e89d/events.out.tfevents.1715617920.00387894e89d.4653.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6951e6fd2b3011fc53c93ea2786d039500a210ef488cc5847194ea7aed2fc1ce
+size 465

tokenizer_config.json

@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "59542": {
+    "53684": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,
@@ -30,9 +30,9 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "separate_vocabs": false,
-  "source_lang": "en",
+  "source_lang": "eng",
   "sp_model_kwargs": {},
-  "target_lang": "ro",
+  "target_lang": "vie",
   "tokenizer_class": "MarianTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5e0389f98bdbd5feac5e597d19503565c9c23acc9d9f64fa2f8ba1ca1c2dee
+oid sha256:4d349494ae8156305e09efcc20439fc982f8dcb380124342c5e9a68d7c3a07af
 size 5112