Training in progress, epoch 3

added_tokens.json

@@ -1,24 +1,3 @@
 {
-  "</tool_call>": 151658,
-  "<tool_call>": 151657,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
+  "<image_soft_token>": 262144
 }

chat_template.jinja

@@ -1,54 +1,47 @@
-{%- if tools %}
-    {{- '<|im_start|>system\n' }}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- messages[0]['content'] }}
-    {%- else %}
-        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
-    {%- endif %}
-    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
-{%- else %}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
-    {%- else %}
-        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
-    {%- endif %}
-{%- endif %}
-{%- for message in messages %}
-    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
-    {%- elif message.role == "assistant" %}
-        {{- '<|im_start|>' + message.role }}
-        {%- if message.content %}
-            {{- '\n' + message.content }}
-        {%- endif %}
-        {%- for tool_call in message.tool_calls %}
-            {%- if tool_call.function is defined %}
-                {%- set tool_call = tool_call.function %}
-            {%- endif %}
-            {{- '\n<tool_call>\n{"name": "' }}
-            {{- tool_call.name }}
-            {{- '", "arguments": ' }}
-            {{- tool_call.arguments | tojson }}
-            {{- '}\n</tool_call>' }}
-        {%- endfor %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- message.content }}
-        {{- '\n</tool_response>' }}
-        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-{%- endif %}
+{{ 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 -%}

config.json

@@ -1,54 +1,62 @@
 {
+  "_sliding_window_pattern": 6,
   "architectures": [
-    "Qwen2ForCausalLM"
+    "Gemma3ForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
   "dtype": "bfloat16",
-  "eos_token_id": 151645,
-  "hidden_act": "silu",
-  "hidden_size": 896,
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
   "initializer_range": 0.02,
-  "intermediate_size": 4864,
+  "intermediate_size": 6912,
   "layer_types": [
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention"
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
   ],
   "max_position_embeddings": 32768,
-  "max_window_layers": 21,
-  "model_type": "qwen2",
-  "num_attention_heads": 14,
-  "num_hidden_layers": 24,
-  "num_key_value_heads": 2,
-  "pad_token_id": 151643,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": true,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
   "transformers_version": "4.56.1",
   "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 262144
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02f9a191acd1532573bcde6021a1175614346a971b2bcbc7f66fbed367c7ed3
-size 988097824
+oid sha256:83d87826640be103acf5b3d31f2879ca3c170b68f1e2198b4aebb736f6853e18
+size 1999811208

special_tokens_map.json

@@ -1,28 +1,30 @@
 {
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<eos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "image_token": "<image_soft_token>",
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02bb4b3cd253faf0bafe1b8f17c85e126b7fd2f5ca926e75a97e9dfb1791f063
+oid sha256:9c4627e47ce9f1e800b6b5bd02eb2ea4b6f5f5405fabe78284a903201f46155f
 size 6289