Training in progress, step 400, checkpoint

last-checkpoint/adapter_config.json

@@ -10,20 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "lora_dropout": 0.3,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "dense_4h_to_h",
+    "query_key_value",
     "dense_h_to_4h",
-    "query_key_value"
+    "dense",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6122248efad15f08bb35ef89dbfb4db02d69860b1a9b820e62900a2fb0d6353
-size 1579384
+oid sha256:2e6374bc3566853a4db892ea7b0fd3e6d67f067050d548def61a7bc8ea045488
+size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ba50451f2f4098994e44c0276099046264f1481fc025e6ae04dd5638e8e654
-size 857338
+oid sha256:96e456810618b2bc95941220c7dbb08646e4b9612a4ae69f86e58166b45e52cc
+size 531194

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c52f76d1e84367eddd916a38c99e13d998a1aef7da30e4dfa7343385bc109fbf
+oid sha256:2329ea8a8fa88344048f0a1cbddfdf8f3d626222182a1cf6cf50c74bc80030fe
 size 1064

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c25f947011cdcfeb2e2cd6b6797fb101f0c43353904140320fa5ceb0b490467
+oid sha256:f9577e2af7afb07c1d7a1aeeecfd7678c692b1dad8317f69302400bc7232785f
 size 6712