Training in progress, epoch 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-3-1b-pt",
+  "base_model_name_or_path": "google/gemma-3-4b-pt",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -26,13 +26,17 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "down_proj",
-    "k_proj",
-    "v_proj",
     "q_proj",
+    "fc1",
+    "v_proj",
+    "fc2",
+    "out_proj",
+    "gate_proj",
+    "up_proj",
     "o_proj",
-    "up_proj"
+    "lm_head",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:611c48a50df54f8315c3664c2912979503464307bf9a73f0e229a4b24e74de7b
-size 1260191096
+oid sha256:7fbe8decdc983399bff0aca412b34486a267a27a7448f24913769e0f5e5642d2
+size 2839124552

runs/Apr06_21-57-42_188c1ef0fac5/events.out.tfevents.1743976677.188c1ef0fac5.1238.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21eeb2819da0465628fd1d5f226d86b5cc9be17920aee3a30c9a6ad58ddd0f0f
+size 4184

tokenizer_config.json

@@ -51325,7 +51325,7 @@
   },
   "boi_token": "<start_of_image>",
   "bos_token": "<bos>",
-  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
+  "chat_template": "",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
   "eos_token": "<eos>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65dd17741a84626ab54b5582f45a827b6237083e9f2ad0a142870f152dce6ecc
+oid sha256:7bb71ef10551c52434f375778e9e2b2f501d058a6fbb1a12884cca4412b944d0
 size 5624