Training in progress, step 10

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-3-4b-it",
+  "base_model_name_or_path": "meta-llama/Llama-3.2-11B-Vision-Instruct",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -15,19 +15,17 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
-    "o_proj",
-    "k_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8694e65007155d6230d44caf4735ea0be09aef0da7fa83fc71dced57664879ab
-size 47662456
+oid sha256:3e7b5f404744f278be8b38fe98a3990474a2a7a8e960f4f7966e637ffeed1f15
+size 23642216

chat_template.jinja

@@ -0,0 +1,119 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+    {%- set user_supplied_system_message = true %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set user_supplied_system_message = false %}
+{%- endif %}
+
+{#- Find out if there are any images #}
+{% set image_ns = namespace(has_images=false) %}      
+{%- for message in messages %}
+    {%- for content in message['content'] %}
+        {%- if content['type'] == 'image' %}
+            {%- set image_ns.has_images = true %}
+        {%- endif %}
+    {%- endfor %}
+{%- endfor %}
+
+{#- System message if there are no images, or if the user supplied one #}
+{%- if user_supplied_system_message or not image_ns.has_images %}
+    {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+    {%- if tools is not none %}
+        {{- "Environment: ipython\n" }}
+    {%- endif %}
+    {{- "Cutting Knowledge Date: December 2023\n" }}
+    {{- "Today Date: " + date_string + "\n\n" }}
+    {%- if tools is not none and not tools_in_user_message %}
+        {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+        {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+        {{- "Do not use variables.\n\n" }}
+        {%- for t in tools %}
+            {{- t | tojson(indent=4) }}
+            {{- "\n\n" }}
+        {%- endfor %}
+    {%- endif %}
+    {{- system_message }}
+    {{- "<|eot_id|>" }}
+{%- endif %}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'image' %}
+                    {{- '<|image|>' }}
+                {%- elif content['type'] == 'text' %}
+                    {{- content['text'] }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

special_tokens_map.json

@@ -1,30 +1,20 @@
 {
-  "boi_token": "<start_of_image>",
   "bos_token": {
-    "content": "<bos>",
+    "content": "<|begin_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "eoi_token": "<end_of_image>",
   "eos_token": {
-    "content": "<eos>",
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "image_token": "<image_soft_token>",
   "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<|finetune_right_pad_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
-size 33384568
+oid sha256:9816d43bd5347d64bccc66b7710947fb18e9818cc660215b1462061d4a44e449
+size 17210088

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab654c430c73f81b26976ec8809e76c64a8602714d5b1dd08a09ee6626a411b
+oid sha256:a27eb875fcfdbb8472a300831a8ee02163eeaaa7780bcc07cb63b7d61d6bbe8d
 size 5624