Training in progress, step 100

adapter_config.json

@@ -6,7 +6,7 @@
   "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
-  "fan_in_fan_out": true,
+  "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
@@ -20,19 +20,16 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "c_proj",
-    "c_attn",
-    "c_fc"
+    "c_fc",
+    "c_attn"
   ],
-  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
-  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007e3ba26fe5065f5f079ecc30a3cab7cdbfa9bc7960bb2fb3302d48242f35de
+oid sha256:73d0e3dcc26ea5d10e748c585994a65fd9ae36785b5a9c83be66897e5ae89f30
 size 4724672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e05a3fae2892d9e26057737536509c0ad9cf2dfed4b386d54ae81f8c02e8ec
-size 5713
+oid sha256:6ca173a0f2278ad3b985fe0a9bf7368117ea2ca7d476951572cee3952cb995ed
+size 5240