Training in progress, step 12

FP16/adapter_config.json

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

FP16/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea26d34eb6a39fc0ca2845178e9d7017b00bf7454f61c2dea10e963c5b7a3dc7
+oid sha256:d693e4b77d740670ba4486fba597e12e170bee8cd18c5d7f0b63d653a0b38a38
 size 167832240

FP16/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 128256
+}

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
     "o_proj",
     "up_proj",
-    "k_proj",
     "down_proj",
-    "gate_proj"
+    "k_proj",
+    "q_proj",
+    "gate_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:d693e4b77d740670ba4486fba597e12e170bee8cd18c5d7f0b63d653a0b38a38
+oid sha256:e294bc7627a33d7909569424d0998e203d85f12a8dadb02254323e63ef93f2fc
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e274b58872ba681f17322367b0459525f40013832ee223a66e9b461693060d
+oid sha256:e4e9dee0397176cfee5a536de2a454ab26081d329cbae3f71150fb94d4f2aa8f
 size 5496