Training in progress, step 10000

adapter_config.json

@@ -14,11 +14,10 @@
   "loftq_config": {},
   "lora_alpha": 128,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
-    "lm_head",
     "embed_tokens"
   ],
   "peft_type": "LORA",
@@ -26,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "o_proj",
+    "gate_proj",
     "down_proj",
     "up_proj",
-    "gate_proj",
-    "v_proj",
-    "k_proj"
+    "k_proj",
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35cfbdf024ea39a1704bf3014fa872d815887c79b0420831544bfdba087db982
-size 3638754864
+oid sha256:d43f521b3fffd12a17469fad2b3680f8c0890df1eafffc5e3ba430e5f7c7fb6f
+size 2296249792

runs/May15_06-33-14_gio-MS-7C80/events.out.tfevents.1747277169.gio-MS-7C80.3672051.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24104ddcf298add2bf914199f54da928657dec0bf1123322e88c5239c5a4fdb
+size 43574

runs/May15_09-02-35_gio-MS-7C80/events.out.tfevents.1747286933.gio-MS-7C80.3701490.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e700eabcd408a7514e638d9adf2e8d4f9450e4cdd69c79f6aae14fbe6c301d1
+size 5686

runs/May15_09-33-50_gio-MS-7C80/events.out.tfevents.1747288160.gio-MS-7C80.3708886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:375a07a31d622d1ce237fbd1410073b3300d13f2408e665c7f888bfcc376d5b0
+size 280626

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ef5777ac4fde181fc3c90b2d372ea4ea7be94d37168e496d857d8424b03b37
+oid sha256:b57e73014f826f7a13c33ea519bbf50c98bd190a8a877abab0dd59967e568990
 size 5624