Training in progress, step 100

adapter_config.json

@@ -11,12 +11,12 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.0,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c9a6d8fa5455e4494fe0a7fcd7f6f838e493c850c69c7bb4e92c6d1eb5586c
-size 27280152
+oid sha256:b18a61db6b81db86528addefe547fbe982f3c42a65de033374c4c23b5e738e07
+size 13648432

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -51,7 +51,6 @@
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
-  "padding": true,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8da70643df584803d10bb95f072a1368de84aa3c23b5bf5fda0a6ef509562aef
+oid sha256:2edb5c7129b0c2529b582c65732664143a7a4d9790847436905330e5f3cc5865
 size 5432