Training in progress, step 30

adapter_config.json

@@ -7,11 +7,11 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 2048,
+  "lora_alpha": 1024,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 1024,
+  "r": 512,
   "revision": null,
   "target_modules": [
     "gate_proj",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7e5f822abe45c0cf7b00dfd5cd2f549fc65dde6e4de98a622173642b7c5b2f
-size 5905624816
+oid sha256:b08e255c82179377befa54b3d195e3b4ab980d6d5f498e17282ed5cb29199494
+size 2952834352

runs/Aug19_13-37-37_chimera13/events.out.tfevents.1724089059.chimera13.237850.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcab64573b17b0739e395ac709259b50522f31c7fa5965e8eb86b84c2dfd6e03
+size 20187

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
@@ -2353,6 +2348,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbbe28adb26d00331d91c8e9bc766cd0699493135652b048bc2b0b4642161b6e
-size 4920
+oid sha256:84cd8e86bcb1e7a6e7ac358918abae6042e2acd0f5bc5480aada1c52b10f2322
+size 5624