Training in progress, step 500

adapter_config.json

@@ -24,12 +24,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "o_proj",
     "v_proj",
     "down_proj",
-    "gate_proj",
     "up_proj",
-    "q_proj"
+    "o_proj",
+    "q_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb8e8cdf3a574fc79eccdcf9bdd5ad7b7c4d83d62d42405897795b10eacd931
+oid sha256:9a537fe1a52eb564b11fba0e32e85d33c5133c6befd0be278ca674802458b534
 size 405935888

chat_template.json

@@ -1,3 +1,3 @@
 {
-  "chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}"
+  "chat_template": "{% if 'role' in messages[0] %}{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% if messages[1]['role'] == 'user' %}{{ '[INST] ' + messages[0]['content'] + ' ' + messages[1]['content'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ '[INST] ' + messages[0]['content'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% else %}{{ bos_token }}{% if messages[0]['from'] == 'system' %}{% if messages[1]['from'] == 'human' %}{{ '[INST] ' + messages[0]['value'] + ' ' + messages[1]['value'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ '[INST] ' + messages[0]['value'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['from'] == 'human' %}{{ '[INST] ' + message['value'] + ' [/INST]' }}{% elif message['from'] == 'gpt' %}{{ message['value'] + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% endif %}"
 }

runs/Apr22_12-47-14_0bfa65aa8dea/events.out.tfevents.1745326050.0bfa65aa8dea.78321.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbed341ee4376720f8bcccb9bee943417c3fce76328d965927fb98206355cf5
+size 6454

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10dc96dad88872133320143b67a615d9e04b3c545ac0993d87e98071aca259e3
+oid sha256:b6d33790491945f9d46bb12d014b7654ac2a72958a42cde551577e858b50a57b
 size 5560