Training in progress, step 4

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e2123ca9a2d36e169840e2c4c76ecb105c7c7ffde354068a168bc87169d3a8
-size 394944
+oid sha256:095367e7f18707114d84fd51db6a2a448cf18defc47c86ea0553733892d8afdb
+size 51880912

special_tokens_map.json

@@ -1,19 +1,23 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<|endoftext|>",
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf430678137c8491ca82fb7092ee49e44ad38857fffe1e4a4a5ed860139a5b8
-size 2113738
+oid sha256:df12c5d52a5b5c540dec10869c2efddc9740cd8dd9caac9654ab1443b78bf211
+size 2114211

tokenizer_config.json

@@ -200,13 +200,34 @@
       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "50277": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50278": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|im_end|>",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13733564e0c6eba50fa1c5c70f4bc5e48734bb30cc944a3c8a394f979935f714
+oid sha256:9c6bec8b7a17e796db55dcdc7d9a8448fa232fcb0350e17f923e5e808a381d95
 size 4856