Training in progress, step 14

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8617bd02544f5556e023e601031e99dff1e9c35a6f0d5a4a2ec1724b506e9c80
+oid sha256:705b0541b4947617523f30cc2b2deccae98f8e6cdd127eff975977bb55d7925c
 size 100966336

config.json

@@ -19,11 +19,26 @@
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
   "pretraining_tp": 1,
+  "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"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.45.2",
   "use_cache": false,
   "vocab_size": 32000

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f867b091d49282071cb97c113cd07cda3dfcf15b6a62effa2f404a3c116cb5
+oid sha256:e9cd48b99e5ae6d8e0a64e11e64924029040c2336b7d4abe6c41abeb2dace80e
 size 6520