trained on new dataset for 2 epochs

README.md

@@ -1,9 +1,12 @@
 ---
 library_name: transformers
-license: mit
-base_model: facebook/mbart-large-50
+base_model: facebook/mbart-large-50-many-to-many-mmt
 tags:
 - generated_from_trainer
+metrics:
+- sacrebleu
+- bleu
+- rouge
 model-index:
 - name: results
   results: []
@@ -14,21 +17,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
+This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2581
-- eval_sacrebleu: 32.6503
-- eval_bleu: 0.3265
-- eval_rouge1: 0.6372
-- eval_rouge2: 0.4402
-- eval_rougeL: 0.5635
-- eval_rougeLsum: 0.5632
-- eval_ter: 60.4240
-- eval_runtime: 826.7326
-- eval_samples_per_second: 1.512
-- eval_steps_per_second: 0.379
-- epoch: 2.0
-- step: 2969
+- Loss: 0.1030
+- Sacrebleu: 36.1071
+- Bleu: 0.3611
+- Rouge1: 0.6827
+- Rouge2: 0.4557
+- Rougel: 0.6584
+- Rougelsum: 0.6574
+- Ter: 44.4372
 
 ## Model description
 
@@ -55,13 +53,28 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 700
-- num_epochs: 5
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 6
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Sacrebleu | Bleu   | Rouge1 | Rouge2 | Rougel | Rougelsum | Ter     |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:------:|:------:|:---------:|:-------:|
+| 9.9972        | 0.3534 | 50   | 9.4988          | 19.6720   | 0.1967 | 0.5861 | 0.3417 | 0.5513 | 0.5522    | 58.0351 |
+| 7.8177        | 0.7067 | 100  | 6.7801          | 26.8668   | 0.2687 | 0.6116 | 0.3719 | 0.5788 | 0.5795    | 53.6109 |
+| 4.1506        | 1.0565 | 150  | 3.1994          | 28.3941   | 0.2839 | 0.6266 | 0.3892 | 0.5946 | 0.5955    | 52.1145 |
+| 1.2625        | 1.4099 | 200  | 0.7019          | 32.1449   | 0.3214 | 0.6506 | 0.4209 | 0.6206 | 0.6210    | 49.5771 |
+| 0.1995        | 1.7633 | 250  | 0.1521          | 32.0543   | 0.3205 | 0.6496 | 0.4085 | 0.6208 | 0.6198    | 48.5361 |
+| 0.0878        | 2.1131 | 300  | 0.1119          | 32.5852   | 0.3259 | 0.6653 | 0.4304 | 0.6378 | 0.6376    | 48.2759 |
+| 0.0726        | 2.4664 | 350  | 0.1039          | 35.1243   | 0.3512 | 0.6755 | 0.4455 | 0.6478 | 0.6474    | 45.2180 |
+| 0.0672        | 2.8198 | 400  | 0.1007          | 36.5523   | 0.3655 | 0.6749 | 0.4555 | 0.6538 | 0.6541    | 44.6975 |
+| 0.0475        | 3.1696 | 450  | 0.1030          | 36.1071   | 0.3611 | 0.6827 | 0.4557 | 0.6584 | 0.6574    | 44.4372 |
+
+
 ### Framework versions
 
-- Transformers 4.46.3
+- Transformers 4.47.0
 - Pytorch 2.1.2
 - Datasets 3.1.0
-- Tokenizers 0.20.3
+- Tokenizers 0.21.0

config.json

@@ -1,8 +1,8 @@
 {
-  "_name_or_path": "facebook/mbart-large-50",
+  "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
   "_num_labels": 3,
   "activation_dropout": 0.0,
-  "activation_function": "gelu",
+  "activation_function": "relu",
   "add_bias_logits": false,
   "add_final_layer_norm": true,
   "architectures": [
@@ -52,7 +52,7 @@
   "static_position_embeddings": false,
   "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 250054
 }

generation_config.json

@@ -7,5 +7,5 @@
   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.47.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95ab08cebabd0e7ed31f9eb7fbfd791e229df4e8a32de44e1f4764825147139f
+oid sha256:709f2f2f2a8d5af222cdad46304c72819f4d688fc334a488d92579673506873f
 size 2444578688

tokenizer_config.json

@@ -515,8 +515,10 @@
   "clean_up_tokenization_spaces": false,
   "cls_token": "<s>",
   "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "language_codes": "ML50",
   "mask_token": "<mask>",
-  "model_max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa7a50051e6f6db3fa6a91c95035ec9ada3e5ad7cbe89fd2b3495d6de9e3e6a
-size 5432
+oid sha256:22fce6c916e8f5ef9c359b6ea4312054269397fd7309989df7da52c7ee9e1cd2
+size 5496