End of training

README.md

@@ -54,7 +54,7 @@ hub_model_id: nblinh/f3d74a4d-432f-45ee-b179-fc56d24fe2e9
 hub_repo: null
 hub_strategy: end
 hub_token: null
-learning_rate: 0.0003
+learning_rate: 0.0002
 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: 100
+max_steps: 50
 micro_batch_size: 1
 mlflow_experiment_name: /tmp/4657317b69958f28_train_data.json
 model_type: AutoModelForCausalLM
@@ -122,20 +122,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0002
 - 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: 100
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0           | 0.0005 | 100  | nan             |
+| 0.0           | 0.0003 | 50   | nan             |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "q_proj",
     "v_proj",
+    "gate_proj",
     "up_proj",
-    "q_proj",
+    "k_proj",
     "o_proj",
-    "down_proj",
-    "k_proj"
+    "down_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:fd0998943300cd7a14af7ddb8b58fb90f1f5337366a6e6b5fbc0ada0ba755aec
+oid sha256:cbcf8b569ce6c26c168272e768657a612f0aae7e5592a6443e8fec6f72b932d6
 size 251901130

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b24f5ab65d37c819542dfca4fe090fe5346d9b7b6b70610ffa48b69640ef9044
+oid sha256:8721cec5d030fe8be4ef1e4a17eb7d93752b518f306d38b9db3c9c8cd3c1bd88
 size 251748704

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf02d8c14dd5502fc6066c9ddef6181760830d98e42bc966a148ce68613177e5
+oid sha256:3f0bd37f5827450f237f36b84faf36aeb6877809d296399b946a2df359888368
 size 6776