Training in progress, step 500

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315b5a3874915037a354c8e6f40cb6dbde2c5b520b4295964823a0613b4eb2ad
+size 159967880

args.txt

@@ -0,0 +1,11 @@
+base_model_name: meta-llama/Llama-2-7b-hf
+batch_size: 4
+cot: true
+dataset_name: BENBENBENb/CommonsenseQA1000COT
+epochs: 20
+eval_strategy: epoch
+learning_rate: 0.0001
+logging_steps: 1
+output_dir: brettbbb/llama_finetune_cs_20_cot
+seed: 42
+warmup_steps: 5

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9db2812b5f6e244e891ed567be963b07f5b4cadd17ec8a267af0dca9aa5d28a
+size 4664