Training in progress, epoch 1

adapter_config.json

@@ -18,6 +18,7 @@
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
+    "Linear(in_features=1152, out_features=262144, bias=False)",
     "embed_tokens"
   ],
   "peft_type": "LORA",
@@ -25,9 +26,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "gate_proj",
-    "up_proj",
-    "down_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:bd4e714c34edc55f8637b26ca48421f9d53825a683a283f4619193ea4fd42faf
+oid sha256:aa5e9df79e032169a89d9876cd7de4b626ac6e2f7be08ac28718baa783462a03
 size 1248236248

runs/Mar22_17-40-49_HAL/events.out.tfevents.1742683257.HAL.15975.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df0af90a85f4db71f846f07794b937c22cfda9381ffe1124c7506ea081d1272
-size 6412
+oid sha256:5953ac3c6ae19c7df2352790c7a17427e09e06a59b302952327a068d8a18dedb
+size 7093

runs/Mar22_17-46-50_HAL/events.out.tfevents.1742683620.HAL.16353.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b1d0845604006a123db4181c0e8859dcd7033278300a909c563ca7e6f562be
+size 6412

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00630686d04903543d71f5785d379e194009fce1c8be394f0a5e1339c69ad2b3
+oid sha256:4e2c230221420843591186280209b0c149306f4087c98a6d6978aea92a25118d
 size 5624