End of training

README.md

@@ -54,7 +54,7 @@ hub_model_id: nblinh/9d94bc60-34ce-43f9-8b83-e855fe65505c
 hub_repo: null
 hub_strategy: end
 hub_token: null
-learning_rate: 0.0002
+learning_rate: 0.0003
 load_in_4bit: true
 load_in_8bit: true
 local_rank: null
@@ -66,7 +66,7 @@ lora_model_dir: null
 lora_r: 16
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 50
+max_steps: 100
 micro_batch_size: 1
 mlflow_experiment_name: /tmp/4ee3c1dbc52892e5_train_data.json
 model_type: AutoModelForCausalLM
@@ -122,20 +122,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 0.0003
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- training_steps: 50
+- training_steps: 100
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0           | 0.0078 | 50   | nan             |
+| 0.0           | 0.0156 | 100  | nan             |
 
 
 ### Framework versions

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "up_proj",
     "k_proj",
-    "q_proj",
     "o_proj",
     "v_proj",
+    "q_proj",
+    "gate_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34d07ccac93c5da56c8d31a145c7d38507b437ab4d9f828e004200e8b9287215
+oid sha256:c16477246674515acbf92a6e3658c6bf9f352e0f97e9fc94bf0ab99df74cd0db
 size 167934026

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c87f1d05b24f649243977bb3aebad69cd1fb8ab5a6aa841967f894c22d79d6e
+oid sha256:ef800e06ac4fc0a5fc48f5a1bb57cda565ee2cbd55b9fde6085c34573c21ed54
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99733778774707ffec22f7833c44abf823626b7a04f8f7d580ff8bd975e19d1f
+oid sha256:45538e3a232857059f47d606a5020956b7ee2cbd38c96bb4c9f729f7b0bef812
 size 6776