End of training

README.md

@@ -35,11 +35,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.19.0
-- Transformers: 4.53.1
+- TRL: 0.21.0
+- Transformers: 4.55.0
 - Pytorch: 2.7.0
 - Datasets: 3.6.0
-- Tokenizers: 0.21.2
+- Tokenizers: 0.21.4
 
 ## Citations
 

adapter_config.json

@@ -25,14 +25,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "up_proj",
+    "down_proj",
     "v_proj",
     "o_proj",
-    "gate_proj",
-    "up_proj",
-    "q_proj",
     "k_proj",
-    "down_proj"
+    "gate_proj"
   ],
+  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a11d3506a380458920173d68b9b973bf21f86a820d736abd04bd863bdf40a10a
+oid sha256:b1a78aa4966aed68a01b6e118d9be6af2e46e7b09fbc0f01a3464a62537ba645
 size 194563400

chat_template.jinja

@@ -1,6 +1,11 @@
 {{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ '<|start_header_id|>system<|end_header_id|>
+
 ' + messages[0]['content'] + '<|eot_id|>' }}{% set loop_messages = messages[1:] %}{% else %}{{ '<|start_header_id|>system<|end_header_id|>
+
 Below are some instructions that describe some tasks. Write responses that appropriately complete each request.<|eot_id|>' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
+
 ' + message['content'] + '<|eot_id|>' }}{% elif message['role'] == 'assistant' %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
 ' + message['content'] + '<|eot_id|>' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
 ' }}{% endif %}

runs/Aug08_09-43-50_54b39aeabec8/events.out.tfevents.1754646239.54b39aeabec8.16942.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce26b7ec4004278672b72d77464263fa6799ca43e2655de3ae4483e4196af86
+size 27196

tokenizer_config.json

@@ -2060,7 +2060,7 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "left",
+  "padding_side": "right",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025c20e3c7b650b9739649b78a34345aca2bbfdce30de7a9880a9f89036e55fa
-size 6289
+oid sha256:b7b5ac3eb18e7aa01f0b881a93e3aea65416ae2b625af2c90964540ec6af9c6e
+size 6225