End of training

README.md

@@ -47,7 +47,7 @@ hub_model_id: nblinh/64c30a82-f90b-4b9f-a1a7-e574d63cd349
 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
@@ -59,7 +59,7 @@ 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/ab6a4989cba219b1_train_data.json
 model_type: AutoModelForCausalLM
@@ -115,20 +115,20 @@ 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           | 0.0109 | 100  | nan             |
+| 0.0           | 0.0054 | 50   | nan             |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "up_proj",
-    "k_proj",
-    "o_proj",
     "v_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
     "gate_proj",
-    "q_proj"
+    "o_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:e8d1813d936a3779118e88f791cfa0eb02454a704a672a14e2c410d648eeefec
+oid sha256:346b1e886a671bb9d59642bc7f7551ae110289c164c52ffce625561cdf9f7d88
 size 34895178

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c187c8e9a3d3952404f3115250d09fb77d4a77e9bca5476420db0c2549e160
+oid sha256:1ec38deb34bb935cc9e157433f37c453f4688a0fe65ead7042ec4a47939383fe
 size 34793120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0bba07a9510369a18b2943c8a30565d555c7d097b82138e44b6750ba586823b
+oid sha256:adf3252c605e6f09ea1cb43fc1079555f814bf7bdee71d0f8ce2be040a251c78
 size 6776