Training in progress, step 100

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa0ff820d4b65b49d4ca8d55e9fade3459eb6bf5e198f768b16c1ff13bcafb0
+oid sha256:5cb7fa9dabb96f956418850f137678ff8d7de17c593584b1b41919c117471848
 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_09-39-45_e701f26e2ec3/events.out.tfevents.1746524464.e701f26e2ec3.260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28ff3c8a9ab71b95df33d7b1106a39a9a50ec590a57ea9422590dabd834a637
+size 74860

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7ab7350fc5412773ab659f773fb8c1464cdb5acdc32de5453a0e234f2fd257
+oid sha256:81030ea02f8cefe2e869057e29502a73ebaae75ef17e6b84a48c6f71f944b1ff
 size 7160