Training in progress, step 247

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -10,18 +10,26 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
     "v_proj",
-    "q_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6bc2846705e1524a64304248e1a2d51bee7d7184b6d58831a5362b2f31ac0b
-size 54543184
+oid sha256:825c292c6d213f5c75e707029db388057a53934e04d753330f5c5cb76e18f7e9
+size 4370526560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3de621dbb3c70defc65ba9ac75f5e40b197fb3cd820a764cd4c742930a2e7197
-size 5624
+oid sha256:8c2f486133559a991f1cc7c338acdd178096f650911238ddf7915e3c9ce24127
+size 5688