Training in progress, step 250

adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "v_proj",
-    "q_proj"
+    "o_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b098f5be97368564400daa33e61e01649d6898d5f945ead65c7699fe89f22c2
+oid sha256:94598c2ddb228fb1d2135fdc101c0644ee5193e51cf3fc49b155e994beca8e53
 size 59021064

runs/Jan29_14-46-45_a4b9db7fb077/events.out.tfevents.1738162009.a4b9db7fb077.17.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22c0f14e3a95fd69b66a93327f0382e24a378aa5543beca62bc399b6e0cb289
+size 16603

tokenizer_config.json

@@ -207,10 +207,16 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "max_length": 4096,
   "model_max_length": 32768,
+  "pad_to_multiple_of": null,
   "pad_token": "<|PAD_TOKEN|>",
+  "pad_token_type_id": 0,
   "padding_side": "right",
   "split_special_tokens": false,
+  "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d943a4e54196cfafe2ccbd67fea9be9b81170f52fff3eddc00ac7d1672f3b07b
-size 5560
+oid sha256:add45799a67f153bafa276db61374a176531e06e777cc6ded0d3da54dc515062
+size 5688