Training in progress, step 5

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "o_proj",
     "v_proj",
-    "q_proj",
     "k_proj",
-    "up_proj",
-    "o_proj",
     "gate_proj",
-    "down_proj"
+    "up_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71c2d294e85b0ae32deab70c3aa5243cb11c08e1d82d08535ae2e035f16391e0
-size 335604696
+oid sha256:fce98b9412e33c04da0c3da1e7ed55419c145aeee95b7dc557ebf1a07ca0cc4e
+size 167832240

config.json

@@ -1,4 +1,5 @@
 {
+  "_attn_implementation_autoset": true,
   "_name_or_path": "unsloth/Meta-Llama-3.1-8B",
   "architectures": [
     "LlamaForCausalLM"
@@ -20,6 +21,21 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "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": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,
@@ -31,7 +47,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.46.0",
   "unsloth_version": "2024.9",
   "use_cache": false,
   "vocab_size": 128256

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48ef0b89091cfb6f98b41134b810e90dcf70e831ed96352258e0467245f82b8
-size 6776
+oid sha256:a7393946c6a0ae6950912f3007a72a846e21fa9dc9f191af94803afe85a7e356
+size 6712