Training in progress, step 500

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "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",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023cf2c1625cfe96616269c682463a8a62c8e0d5c9fb6c137768e9e9d7f224eb
+size 159967880

args.txt

@@ -0,0 +1,14 @@
+base_model_name: lmsys/vicuna-7b-v1.5
+batch_size: 4
+cot: true
+dataset_name: BENBENBENb/CommonsenseQA1000COT
+epochs: 20
+eval_strategy: epoch
+evaluation: false
+learning_rate: 0.0001
+logging_steps: 1
+output_dir: brettbbb/cs_cot_128
+seed: 42
+skip_example: true
+train_size: 128
+warmup_steps: 5

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929d5bac71fe87c6214b8e53fa652e17d951507a4893de2c394a86a2d2a30cb4
+size 4600