End of training

README.md

@@ -27,17 +27,18 @@ print(output["generated_text"])
 
 ## Training procedure
 
+ 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.2
-- Transformers: 4.46.3
+- TRL: 0.13.0
+- Transformers: 4.47.1
 - Pytorch: 2.5.1+cu121
 - Datasets: 3.2.0
-- Tokenizers: 0.20.3
+- Tokenizers: 0.21.0
 
 ## Citations
 

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "meta-llama/Llama-3.2-3B",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 64,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "q_proj",
     "o_proj",
     "v_proj",
-    "q_proj"
+    "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 sha256:0f347f3db07578c68c18a72614ac3bae1c3b66754bbb6388673bd7a8c3170a72
+oid sha256:b02e62f6165d9ab598f6f361e9bbf455cc83738d2c8b2a82c2106b80b8f86fac
 size 36730224

runs/Dec25_20-37-10_192eac3a7992/events.out.tfevents.1735159270.192eac3a7992.568.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267805afeccad04f34d63f2dc4ff2829b4b4706e56c1b5320458e63e6c8f794d
+size 16653

runs/Dec25_21-00-46_192eac3a7992/events.out.tfevents.1735160681.192eac3a7992.568.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c764d1e71ddc587aab0180644395672dda5043c9cf532649b9ef625b82de7e
+size 111442

tokenizer_config.json

@@ -2052,6 +2052,7 @@
   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ec612874ca34750e3a27345a41d46becd0fec48ec1a83f24676ca11f056672
-size 5560
+oid sha256:ef0b4fbb33c70ac0ad87f565705ca01f2c24ba341dc3fc349e50d17cd404b7d4
+size 5624