Training in progress, step 1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "gate_proj",
     "down_proj",
+    "up_proj",
     "v_proj",
-    "o_proj",
     "q_proj",
     "k_proj",
-    "gate_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb7fa9dabb96f956418850f137678ff8d7de17c593584b1b41919c117471848
+oid sha256:e7918ce948202b67b7334bd1fc85b2954de91d072dd090a582cce989b70ca9c6
 size 671149168

config.json

@@ -1,4 +1,5 @@
 {
+  "_attn_implementation_autoset": true,
   "_name_or_path": "Intel/neural-chat-7b-v3-3",
   "architectures": [
     "MistralForCausalLM"
@@ -20,7 +21,7 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.46.0",
   "use_cache": false,
   "vocab_size": 32000

runs/May06_11-05-30_3f5d108b94d2/events.out.tfevents.1746529597.3f5d108b94d2.260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f102ec8c0e2f9d6b455f0d32ccf665a054fa32c7ad8d73f1e2d47f43fce6ac94
+size 7934

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81030ea02f8cefe2e869057e29502a73ebaae75ef17e6b84a48c6f71f944b1ff
+oid sha256:7836735b7779707169c01c179c78d625c812c7c52eb26bf707dd85a41bd5fc54
 size 7160