Training in progress, epoch 1

adapter_config.json

@@ -26,12 +26,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "up_proj",
-    "v_proj",
     "o_proj",
     "k_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ec8c7bbb508677748ca96edb3319e6e632f5a1d972fa8e2742e44ff4e53f65
-size 1260191096
+oid sha256:d15d17f99ffb450e17a100019c0def2db2b8c72f3f932d6ffc2488890a5ed886
+size 2468152240

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

runs/Feb24_15-30-38_high-memory-gpu-nv100-processor/events.out.tfevents.1771947038.high-memory-gpu-nv100-processor

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c99eb7a0aa80a49be728fd8207605fbaf8b14a1b142897870813e8accee4f1a
+size 35299

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
-size 33384568
+oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
+size 33384443

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93801ab444ad453485480a6d4bb0bb4abb23f59f19fc8f2ad28dd5e5f53b8c92
-size 6033
+oid sha256:d057eaae7a60331af90a483c6c84ed7a90e68d21d1e6d4644544269fc19abcb5
+size 5521