Training in progress, step 500

adapter_config.json

@@ -15,21 +15,21 @@
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
-    "embed_tokens",
-    "lm_head"
+    "lm_head",
+    "embed_tokens"
   ],
   "peft_type": "LORA",
   "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "k_proj",
+    "gate_proj",
     "down_proj",
     "up_proj",
+    "q_proj",
     "o_proj",
-    "v_proj",
-    "gate_proj",
-    "k_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:d267d8b8ee6daf38a788777a73177794a0273a04b3043b9fb7d63a0c7e073821
+oid sha256:243f605abbe07d81a8dabe176fbca804ac114ee24f3a33e0d3a9d8b7c6592348
 size 928031856

runs/Sep24_01-51-05_sammie/events.out.tfevents.1727164395.sammie.364485.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e768288b2e11234fe4e022bd6c35087befcdbad1c201846b35220eee27f5593c
+size 16240

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c750b60303af2a2b5c01d7de4b0117c092f04379827ff62731f3912f38b2b0d7
+oid sha256:c6129c47eb3d79d123e565041755fd270ca35bbb347ebac7e635faa2854c724d
 size 5496