Training in progress, step 10

README.md

@@ -1,18 +1,18 @@
 ---
-base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
+base_model: unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
 library_name: transformers
 model_name: test2
 tags:
 - generated_from_trainer
+- unsloth
 - trl
 - sft
-- unsloth
 licence: license
 ---
 
 # Model Card for test2
 
-This model is a fine-tuned version of [unsloth/qwen3-0.6b-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen3-0.6b-unsloth-bnb-4bit).
+This model is a fine-tuned version of [unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -3,11 +3,11 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": {
-    "base_model_class": "Qwen3ForCausalLM",
-    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
+  "base_model_name_or_path": "unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -29,17 +29,17 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
-    "q_proj",
     "up_proj",
+    "q_proj",
+    "o_proj",
     "down_proj",
-    "k_proj",
-    "o_proj"
+    "v_proj",
+    "gate_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:fb6062623c401be6884015d9d22ab9ece656c01498887dc7f6631c1f91a9680f
-size 10143496
+oid sha256:a616e38fa8e78d658c3597cb8b80666469400ae0af05db84f75fda5e1b965d18
+size 17640136

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
-size 11423114
+oid sha256:6b4360dd6a184650ffc48056c2569bc603f896c5adfe94b10f1c79f809638aa5
+size 11422166

tokenizer_config.json

@@ -4,7 +4,7 @@
   "bos_token": null,
   "eos_token": "<|im_end|>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|PAD_TOKEN|>",
+  "pad_token": "<|vision_pad|>",
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null,
   "added_tokens_decoder": {
@@ -183,46 +183,6 @@
       "rstrip": false,
       "normalized": false,
       "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
-    },
-    "151669": {
-      "content": "<|PAD_TOKEN|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72acde95f427f5c0caceca3d439bf221e41298f573bef3ae7440a8d707625ea4
+oid sha256:62ef5223b9379a2e2e03f9ae8eb4a1125fbf4b72c2cc943819d449b0935619a3
 size 5777