Training in progress, epoch 1

README.md

@@ -28,17 +28,17 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/dpo_smiplification/runs/ztfwit0b) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/dpo_smiplification/runs/tyu12m4x) 
 
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 
 ### Framework versions
 
-- TRL: 0.23.0
-- Transformers: 4.56.2
-- Pytorch: 2.8.0
-- Datasets: 3.6.0
+- TRL: 0.24.0
+- Transformers: 4.57.3
+- Pytorch: 2.9.0
+- Datasets: 4.3.0
 - Tokenizers: 0.22.1
 
 ## Citations

adapter_config.json

@@ -1,9 +1,16 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral",
+    "unsloth_fixed": true
+  },
   "base_model_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
   "bias": "none",
   "corda_config": null,
+  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -20,18 +27,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.0",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "up_proj",
-    "k_proj",
     "gate_proj",
+    "q_proj",
     "down_proj",
-    "o_proj"
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c260b48c0a7d488b06d4d0666290048d457d733f659055895a3863763bfae3e
+oid sha256:74065212c9d3bf7b824618e60b16b77e0656ae9a78d5f13554bd30f5edc9d200
 size 167832240

tokenizer.json

@@ -6964,6 +6964,12 @@
           "id": "A",
           "type_id": 0
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
       }
     ],
     "pair": [
@@ -6979,6 +6985,12 @@
           "type_id": 0
         }
       },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -6990,9 +7002,24 @@
           "id": "B",
           "type_id": 1
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 1
+        }
       }
     ],
     "special_tokens": {
+      "</s>": {
+        "id": "</s>",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "</s>"
+        ]
+      },
       "<s>": {
         "id": "<s>",
         "ids": [

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
+  "add_eos_token": true,
   "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d11c0521246a68bdb6a8335ed968d814e898bd344f90101460a310eed56b3895
-size 6865
+oid sha256:a3431d0c4d717553177a1a69fd77ec6e3d1ece5bbb135a5a8575cb75f7b6cda3
+size 6929