Training in progress, step 20

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-bnb-4bit",
+  "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "v_proj",
-    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
     "q_proj",
     "up_proj",
-    "down_proj",
-    "k_proj"
+    "o_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:a166dbb8982791dbed5b7ac7703a38c48901d8a909d9abcba5576c0913006292
+oid sha256:092fc9c4c943535e67d41cb9e32e90f024f7df45786597221e9efef1bf211b56
 size 73911112

added_tokens.json

@@ -1,7 +1,6 @@
 {
   "</tool_call>": 151658,
   "<tool_call>": 151657,
-  "<|PAD_TOKEN|>": 151665,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

special_tokens_map.json

@@ -22,7 +22,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|PAD_TOKEN|>",
+    "content": "<|vision_pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:228f830c422e3cba9a535edebc7526e9cb362ed4e4b2458587d2d3eece80fc66
-size 11422254
+oid sha256:02e2c18eaf9a0b64d16f11f381664b17389bd92bcf13130ba6f754c95b078300
+size 11422065

tokenizer_config.json

@@ -177,14 +177,6 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "151665": {
-      "content": "<|PAD_TOKEN|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
@@ -209,7 +201,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 32768,
-  "pad_token": "<|PAD_TOKEN|>",
+  "pad_token": "<|vision_pad|>",
   "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcbc18ede3cb4c5985230811e40b55e3332c728769b417f5300b6670e1f4db28
+oid sha256:5093f3b3229f2ae3e7d4ab2df778af84e808428a469324cb401cf2238849448f
 size 5624