Training in progress, epoch 0

added_tokens.json

@@ -1,8 +1,7 @@
 {
   "<|begin_of_c-sharp_code|>": 50267,
-  "<|begin_of_java_code|>": 50265,
-  "<|begin_of_sentence|>": 50270,
-  "<|end_of_c-sharp_code|>": 50268,
-  "<|end_of_java_code|>": 50266,
-  "<|translate|>": 50269
+  "<|begin_of_java_code|>": 50269,
+  "<|end_of_c-sharp_code|>": 50265,
+  "<|end_of_java_code|>": 50268,
+  "<|translate|>": 50266
 }

config.json

@@ -21,8 +21,8 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.35.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50271
+  "vocab_size": 50270
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b072600d7884df844c93069f29be1a6a4bb4f3014ce56a0a32c4f7502dd215e
+size 498829328

special_tokens_map.json

@@ -1,15 +1,62 @@
 {
   "additional_special_tokens": [
-    "<|begin_of_java_code|>",
-    "<|end_of_java_code|>",
-    "<|begin_of_c-sharp_code|>",
-    "<|end_of_c-sharp_code|>",
-    "<|translate|>",
-    "<|begin_of_sentence|>"
+    {
+      "content": "<|end_of_c-sharp_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|translate|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|begin_of_c-sharp_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_of_java_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|begin_of_java_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -18,6 +65,18 @@
     "single_word": false
   },
   "pad_token": "</s>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -9,7 +9,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -18,7 +18,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -27,7 +27,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -36,7 +36,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -50,7 +50,7 @@
     },
     {
       "id": 50265,
-      "content": "<|begin_of_java_code|>",
+      "content": "<|end_of_c-sharp_code|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -59,7 +59,7 @@
     },
     {
       "id": 50266,
-      "content": "<|end_of_java_code|>",
+      "content": "<|translate|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -77,7 +77,7 @@
     },
     {
       "id": 50268,
-      "content": "<|end_of_c-sharp_code|>",
+      "content": "<|end_of_java_code|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -86,16 +86,7 @@
     },
     {
       "id": 50269,
-      "content": "<|translate|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 50270,
-      "content": "<|begin_of_sentence|>",
+      "content": "<|begin_of_java_code|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -1,64 +1,104 @@
 {
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "<|end_of_c-sharp_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50266": {
+      "content": "<|translate|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50267": {
+      "content": "<|begin_of_c-sharp_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50268": {
+      "content": "<|end_of_java_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50269": {
+      "content": "<|begin_of_java_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "additional_special_tokens": [
+    "<|end_of_c-sharp_code|>",
+    "<|translate|>",
+    "<|begin_of_c-sharp_code|>",
+    "<|end_of_java_code|>",
+    "<|begin_of_java_code|>"
+  ],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "errors": "replace",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": {
-    "__type": "AddedToken",
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "</s>",
+  "sep_token": "</s>",
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff6ead4ed5eed7f06edef81f4d02a85417b09e428063c25561ee6d306ce7a18
-size 4027
+oid sha256:5a73e50d9c89167324ae7b38a9b9bcd977eaf008680ca69c1a5dbe36bd21a67b
+size 4600