Training in progress, epoch 1

adapter_config.json

@@ -14,25 +14,17 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "lm_head",
-    "embed_tokens"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_proj",
-    "q_proj",
     "v_proj",
-    "down_proj",
-    "up_proj",
-    "k_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c7aa6805a20957ebec1a52bc24543392d8141dd70480a2387939eac0fcd5e94
-size 2468152240
+oid sha256:06562ceb5a9d97f0ebbf2d49a44645ec057282f23bee2e11575e5c752c22157e
+size 2995512

runs/Jun05_08-19-14_a1ca53c52470/events.out.tfevents.1749111773.a1ca53c52470.267.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7748b9beb16d190efd788bd5584066fe3a894ea8884b30c0814150f0f6f3f6e
+size 12698

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": "{% for message in messages %}{% if message['role'] == 'system' %}<start_of_turn>system\n{{ message['content'] }}<end_of_turn>\n{% elif message['role'] == 'user' %}<start_of_turn>user\n{{ message['content'] }}<end_of_turn>\n{% elif message['role'] == 'assistant' %}<start_of_turn>model\n{{ message['content'] }}<end_of_turn>\n{% endif %}{% endfor %}",
   "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 sha256:565bc04f7c093d29b82670fe6b634f2ccfffc247f4cddd5129dc04c9a9bc745d
+oid sha256:2d8dc3a2faa9bddaddb97efdc13c0d54db0a2d5bc563c12a321be9b147ba07fd
 size 5688