End of training

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: Mistral_7B-DPO
 tags:
 - generated_from_trainer
+- unsloth
 - trl
 - dpo
-- unsloth
 licence: license
 ---
 
@@ -35,11 +35,11 @@ This model was trained with DPO, a method introduced in [Direct Preference Optim
 
 ### Framework versions
 
-- TRL: 0.13.0
-- Transformers: 4.49.0.dev0
-- Pytorch: 2.1.0+cu118
-- Datasets: 3.2.0
-- Tokenizers: 0.21.0
+- TRL: 0.15.2
+- Transformers: 4.50.0
+- Pytorch: 2.6.0
+- Datasets: 3.4.1
+- Tokenizers: 0.21.1
 
 ## Citations
 

adapter_config.json

@@ -3,6 +3,7 @@
   "auto_mapping": null,
   "base_model_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
   "bias": "none",
+  "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -23,15 +24,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "v_proj",
     "q_proj",
-    "k_proj",
-    "gate_proj",
-    "o_proj",
     "up_proj",
-    "down_proj"
+    "down_proj",
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3216c79cc3f3dcb792e9483861df1582229f938e12a6c3057a49f7a377e49037
+oid sha256:1ccb9d1fedd46f63f17f184aec0d805358f5aea908520004997fc0497934028d
 size 167832240

tokenizer_config.json

@@ -6173,7 +6173,6 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "alpaca",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0700e29a23833f5033edc6cd73e17db0f62f06c4f2f3fa08d131bde0b889b66
-size 6200
+oid sha256:2382abf2eb9bf526959044d2e4372aeff604be2da83dd452144fd02d5ad02af3
+size 6264