Training in progress, step 20

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
     "dense_4h_to_h",
     "dense",
-    "query_key_value"
+    "query_key_value",
+    "dense_h_to_4h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84dda87555a088f827be18a88a5696a83bec67d75a881038a2c7f8515a7f649
+oid sha256:e0bb6fe2934d7c30ac803eaa551dab8a1f56b32c7cd6eff82ae11bf60a9721d4
 size 261131840

runs/Apr20_18-59-45_19a45bfdbd4f/events.out.tfevents.1713639620.19a45bfdbd4f.285.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59ee7f54a9b16a0bbcb339cb1c0ce2bc58e52e86c157e639f993717d7e5533f
+size 6038

tokenizer.json

@@ -160,6 +160,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       ">>TITLE<<": 0,
       ">>ABSTRACT<<": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67444c5987fde2816e82f5c69976556ee49ad2ce9ea48426c3ebf53aa9ed0dfc
-size 5048
+oid sha256:6c58c7317538783fcce134559a05499f19ac24e39355ed4d0aea6f64698ab9b7
+size 5112