Training in progress, step 500

config.json

@@ -9,6 +9,11 @@
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      58088
+    ]
+  ],
   "bos_token_id": 0,
   "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
@@ -38,19 +43,19 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_length": null,
+  "max_length": 512,
   "max_position_embeddings": 512,
   "model_type": "marian",
   "normalize_before": false,
   "normalize_embedding": false,
-  "num_beams": null,
+  "num_beams": 4,
   "num_hidden_layers": 6,
   "pad_token_id": 58088,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.0",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 58089
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e8e51667035251ede3b7b0ac74818b5f6c8c3aafae146c0cce98b360cb03621
+oid sha256:ead9888d0328e45b8c58cd18b4a04a0325bc0804bcb73f820b3d8ecbf35a1cd9
 size 295781668

runs/Feb16_11-02-46_3e27c6f5ab54/events.out.tfevents.1739703768.3e27c6f5ab54.21.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d8f604e40ca35d990831bb920e72a2268faf4fac40648fb494fb82d337f4a8
+size 5900

tokenizer_config.json

@@ -27,7 +27,6 @@
   },
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
-  "extra_special_tokens": {},
   "model_max_length": 512,
   "pad_token": "<pad>",
   "separate_vocabs": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a50905dfe1370df7558e0c8ce666a5d383769af9bc2f91eef85a25c1ffe9e4e
-size 5496
+oid sha256:ebf03bcf5899a76b90d1f47f604925cdc9e9cfc1ad0906f7eee9a66197d1d6aa
+size 5368