Training in progress, epoch 0

adapter_config.json

@@ -10,24 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 256,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "up_proj",
-    "v_proj",
-    "gate_proj",
+    "q_proj",
     "o_proj",
-    "down_proj",
-    "lm_head",
-    "q_proj"
+    "k_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:310be69f0778ee7cdbaf6b2f4a9e5f08c3ab5f7a2d3d2b9a715494f24da7c7b5
-size 1204678496
+oid sha256:a27d7d6f916900d48c938e5253962e7c64c2822c9d5c18189c6aea85b1b9475b
+size 872450448

tokenizer_config.json

@@ -33,7 +33,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 1024,
+  "model_max_length": 512,
   "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e880aa3f573c21aaa0672948ee96d83a70be8888fde0b2d6f363a089f376be8e
+oid sha256:cbcb14553c1077bce53b3739e98bc72a2b84f7ca2e8f1bb2766ec818865ea1da
 size 4984