Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bac167572e05d90a558ea20ee9417e0bb6bed3ec1de4b70b3ebf25712480a14
+oid sha256:a0fe840d266817847966b254df854a21bcece67809f0ee3f595b7c2324c2f968
 size 335604696

config.json

@@ -1,4 +1,5 @@
 {
+  "_attn_implementation_autoset": true,
   "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
@@ -7,6 +8,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": 128009,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -44,7 +46,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.43.1",
+  "transformers_version": "4.46.1",
   "use_cache": false,
   "vocab_size": 128256
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794c3cad57a18acf0daa552f636e6a4ddaf4fc5f3a2e8a670c30fbb17fefecd1
-size 6072
+oid sha256:8e459e905652d5f89a34dd2689762edbef44e03573d067fd9264703872f273ff
+size 6200