Training in progress, step 100

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "o_proj",
-    "v_proj",
-    "up_proj",
     "q_proj",
+    "v_proj",
+    "k_proj",
     "gate_proj",
-    "down_proj"
+    "down_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3a4601f703670ee1acd1b0d08276f848416fc63b285f41d80ffd36fc3c6f84
+oid sha256:7bc1e32c4358f85d93cc9d65c14620e6375ef0a7ee908500819cc976d4ae5ade
 size 161533192

tokenizer_config.json

@@ -207,10 +207,14 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "max_length": 1024,
   "model_max_length": 32768,
   "pad_token": "<|PAD_TOKEN|>",
   "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:c5f2cb6d0d6ecb7e0f8c69776de80850c3e58041f3136ce0c1c77865397b2c2f
-size 6801
+oid sha256:3048e96d2d47abd6a65b4c99e7ff2739d57dcfd25844d2ad989dfdb2bdd86f9f
+size 6865