Training in progress, step 10

adapter_config.json

@@ -3,6 +3,7 @@
   "auto_mapping": null,
   "base_model_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
   "bias": "none",
+  "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -12,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
+  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -21,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
     "dense",
     "dense_h_to_4h",
-    "query_key_value"
+    "query_key_value",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af93310b50cfc41d5abc25ca8b4e6d34c3cbcb7fc5814a8dd83c0b3d5dca9769
+oid sha256:e2f3449228776f84f4a79a30ddfdab7df154a8b797d111c75d1bdb9a3878dc8b
 size 261131840

runs/Dec12_10-57-19_493b1151e23a/events.out.tfevents.1734001040.493b1151e23a.470.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ac6a2795b530e2e01eede304175fa8a0aa17ac82e6eb846fd1b24e921bc8a4
+size 6856

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1116ef3fe976cb5662d5a4d2533136ba6484cae4e85e529ec6d771a571d60c9b
+oid sha256:864bd1a9240960deed89becb4ec6c983c98bc54d148a373a1c666db47a5040ec
 size 5560