Training in progress, step 200

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
     "Wqkv",
+    "out_proj",
     "layer"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f30275384600729bcfd077d0123f3112d35ed4e0f19f813113cac6af12f8e6
+oid sha256:9dfe620a946a47a20cc42084532c7a69b0602b1b2444bba9dd4f267ea9b9ff21
 size 18064

config.json

@@ -27,21 +27,6 @@
   "n_layers": 2,
   "num_key_value_heads": 2,
   "output_router_logits": false,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_storage": "bfloat16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "resid_pdrop": 0.0,
   "router_aux_loss_coef": 0.05,
   "tie_word_embeddings": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d39dd8e26d1ac93b0c23933cdca1cb83315b06d440ce30d09da1f97075ba9b
+oid sha256:b905233ac8be15849b764d721be5139b034d739112027fbed233ecf14c7edc07
 size 6776