End of training

README.md

@@ -27,17 +27,18 @@ print(output["generated_text"])
 
 ## Training procedure
 
+ 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.1
-- Transformers: 4.46.2
-- Pytorch: 2.6.0+cu124
-- Datasets: 3.1.0
-- Tokenizers: 0.20.3
+- TRL: 0.15.2
+- Transformers: 4.49.0
+- Pytorch: 2.6.0+cu126
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
 
 ## Citations
 

adapter_config.json

@@ -1,8 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "base_model_name_or_path": null,
   "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": 16,
+  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -21,9 +24,9 @@
   "revision": null,
   "target_modules": [
     "gate_up_proj",
-    "qkv_proj",
+    "down_proj",
     "o_proj",
-    "down_proj"
+    "qkv_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d85af1485960ccbfd33f601afab4e7bc3d631d4e8a9c7801f1e7c877c886e3
-size 50365768
+oid sha256:c58704bade2987592dbd46e375d7be5143c747ad1828bc0f1f4cdfcb144a6245
+size 50370120

tokenizer_config.json

@@ -120,6 +120,7 @@
   "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 4096,
   "pad_token": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e7d4488442b69bb9ecbf5b60693a5eaa3f62a1c3ce7e0081e81469a0d0973a
-size 5496
+oid sha256:3381c747af9f2b3b8c2826668b1c54b2f5eaafb3207ce43b4e64a0864ef865da
+size 5560