Training in progress, step 2

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0e923de915afa71992e0252268590f35050c95cc8e8656dfb8b763d4ffadf1
+oid sha256:524eb78f81bdfbf84c8981961e852f0bfb05dc358e18e720bdc27e20ab00c546
 size 100966336

config.json

@@ -19,12 +19,27 @@
   "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",
-  "transformers_version": "4.45.0",
+  "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 sha256:6dc9a1db3c88547e6538ace2414899776f04cd977fd4f6151cd412468efb0186
+oid sha256:0ccaea925f3b138b8e0b110e67d330fc8173aa9cf5a7cec55c1926d7601989ee
 size 6200