Training in progress, step 25

adapter_config.json

@@ -18,8 +18,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
     "up_proj",
+    "gate_proj",
+    "o_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a27886c0f7303783f3839d529b8c52466fb87acf68a9d1fe9ff96bff644ef538
-size 637592768
+oid sha256:e1e4faaaf1521ae3385817b6025147785b31bd432d919e7b5d5e9d1d9bce160a
+size 692219248

added_tokens.json

@@ -1,4 +1,8 @@
 {
+  "<|end|>": 32005,
+  "<|function_call|>": 32003,
   "<|im_end|>": 32000,
-  "<|im_start|>": 32001
+  "<|im_start|>": 32001,
+  "<|response|>": 32004,
+  "<|thoughts|>": 32002
 }

special_tokens_map.json

@@ -1,6 +1,18 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -41,13 +41,45 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32002": {
+      "content": "<|thoughts|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "<|function_call|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "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": false,
-  "eos_token": "</s>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b239c79424204a0c8ffc8edf94952bccae3e9a354372d5dc4f94a81aad08e77e
+oid sha256:0b0b916294bb1f5fed78f3d6296a880199d679bd0d0ab34bb146601e758b1936
 size 4664