Training in progress, step 100

adapter_config.json

@@ -20,12 +20,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "gate_proj",
+    "up_proj",
     "down_proj",
-    "v_proj",
     "q_proj",
     "k_proj",
-    "gate_proj",
-    "up_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5595d5709e08dfe18a5e6f2986317e21a3e06942bd5a4d3e5c0bbc18374bcd7e
+oid sha256:eef327aafea92767d08f5bd905260852573c3a62e6208a0f3bc2ebd03310ebe4
 size 83945744

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

runs/Jan23_20-43-15_dpo-tests-2-85c5c9854f-p9wdp/events.out.tfevents.1706043566.dpo-tests-2-85c5c9854f-p9wdp.12217.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca46ea80d725a007fbba48eb2ec76fddc8c829abd0554254b5185c254dd9d9a8
+size 12276

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -29,6 +29,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32000,
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32001,
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -25,13 +25,29 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
   "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": 2048,
   "pad_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8610158fb4e92ecf681be13fb2555f0196d3eeb00790c30c3133d72d90c9ab6d
+oid sha256:76f1f69c96e944323d9d0f9898ff0fb78a56c61efac08f912a2dcd3b42dfcd54
 size 4539