Training complete

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8061
-- Bleu: 63.7292
-- Gen Len: 26.9254
+- Loss: 7.2188
+- Bleu: 0.0
+- Gen Len: 3.2627
 
 ## Model description
 
@@ -49,15 +49,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 34   | 2.0386          | 64.2529 | 27.4478 |
-| No log        | 2.0   | 68   | 1.8061          | 63.7292 | 26.9254 |
+| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:----:|:-------:|
+| No log        | 1.0   | 217  | 10.6696         | 0.0  | 2.0184  |
+| No log        | 2.0   | 434  | 7.2188          | 0.0  | 3.2627  |
 
 
 ### Framework versions
 
-- Transformers 4.37.2
+- Transformers 4.38.1
 - Pytorch 2.1.0+cu121
-- Datasets 2.17.0
+- Datasets 2.17.1
 - Tokenizers 0.15.2

config.json

@@ -52,7 +52,7 @@
   "static_position_embeddings": false,
   "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.38.1",
   "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": "4.37.2"
+  "transformers_version": "4.38.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a4ebde0652a89ba32c9f5a36165eb884c9936801e870c6b4b3f23beb0411e4a
+oid sha256:1eccbc1c72529951ab58b55a61d009bb4063c53541ac4fe5cf4facb590220e5a
 size 2444578688

runs/Feb23_08-19-56_aae53cc3cbcd/events.out.tfevents.1708676452.aae53cc3cbcd.822.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97434d85f6f18bb29c0e6e0c43f3ac2d601c43c57014943c7aca3727a1027360
+size 6560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1f6b3aa0cedad723e3fd8cd76521a4dbb67312f1f60f80c18ca191f38bb9905
-size 4856
+oid sha256:2628d4c2d7c1351bc5586ceacea7c2fba4ed4c4613caee0b387aa9ee4777740e
+size 5048