Training in progress, step 125

config.json

@@ -22,5 +22,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.3",
   "use_cache": false,
-  "vocab_size": 1179
+  "vocab_size": 1180
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5619aa69a4aceae15e7644d3e20670d1fb58dcdff64baafa61da1d90059229d
-size 4118832
+oid sha256:66edfe649d2e8798398d4764fda0a250e67e1803c89d518a892bafe35d140ce6
+size 4119216

special_tokens_map.json

@@ -14,7 +14,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|pad|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

tokenizer_config.json

@@ -8,13 +8,21 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "1": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 72,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
   "tokenizer_class": "AISTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdba98e96cc9f40be41cef54566a38f527af4941194cf501d6e85a347c69ca4c
+oid sha256:18161469b1be421d788bde105ca0aa5a5595fe9d0179b70e8f5c579a9c26cba6
 size 4920

vocab_file.txt

@@ -1,4 +1,5 @@
 <|endoftext|>
+<|pad|>
 #
 (
 )