Training in progress, step 100

adapter_config.json

@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0.0,
   "megatron_config": null,
@@ -25,14 +25,14 @@
   "peft_type": "LORA",
   "peft_version": "0.18.0",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_fc",
-    "q_attn",
+    "c_attn",
     "c_proj",
-    "c_attn"
+    "q_attn",
+    "c_fc"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ea9792bf0055794aebd3e95deff4de692c5b43571001ed40ed3c86a566d0e5
-size 22241240
+oid sha256:ee65b5b0d453a506fe15a3ec1e693f6a9ad6eade99e8b70cecf6796b34eb5c7c
+size 88891680

runs/Jan08_14-00-28_711d505acec9/events.out.tfevents.1767880844.711d505acec9.442.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a14c5f159eb6b31049e847aaacc5a3a2922b9d64f047cdf791cf66adeb30640
+size 6303

runs/Jan08_14-03-57_711d505acec9/events.out.tfevents.1767881046.711d505acec9.442.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa729dd5e5db4910166ad2db3ed55cc68f4cf27b96bcd71723140c38606b922b
+size 6717

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e0a07be0ce96bf38456d5c22c1de59962605d222e5cd25220162e154e82a0c
+oid sha256:5c68ef8801f53820ebf78b70cc447ec2c95a378723f970172da704e9c916e42d
 size 5841