End of training

README.md

@@ -66,7 +66,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 1
+max_steps: 50
 micro_batch_size: 8
 mlflow_experiment_name: /tmp/e51bf03bb498f9d1_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 321707c0-4ea8-4130-bb14-e36f4b768cbb
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 321707c0-4ea8-4130-bb14-e36f4b768cbb
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 

adapter_config.json

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

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16f8a699f3774c4472e55225eb6b4fda0c7749229838b150cac6064aacb76c9
+oid sha256:9839088483684ae0eebfe5ada4f234c82e5a455c14badf86c307fd5218373c75
 size 84047370

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c819fc31fa9b21de4af61a0ebddfe4ef4763622f7727e156c17414cb9ad8e91
+oid sha256:e30ad3a932f4f7315c4414f25b60020ad5dcde2f3ac00dc06e981ee2931e153d
 size 83945296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2747b3250531dc8232743af8505dc9acdbf1aee199e7d5a116f6466686da79
+oid sha256:12826a485a919a9a47b038227148c97de1c80a85426d6e19c25ee546c6305dff
 size 6776