End of training

README.md

@@ -66,7 +66,7 @@ lora_model_dir: null
 lora_r: 32
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 20
+max_steps: 50
 micro_batch_size: 1
 mlflow_experiment_name: /tmp/bd684c24fae39600_train_data.json
 model_type: AutoModelForCausalLM
@@ -103,7 +103,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [unsloth/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0922
+- Loss: 0.0745
 
 ## Model description
 
@@ -131,17 +131,16 @@ The following hyperparameters were used during training:
 - 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: 20
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.4698        | 0.0015 | 1    | 1.7292          |
-| 1.2989        | 0.0075 | 5    | 1.7222          |
-| 1.1088        | 0.0150 | 10   | 1.5535          |
-| 0.8043        | 0.0225 | 15   | 1.2118          |
-| 0.7881        | 0.0300 | 20   | 1.0922          |
+| 1.2364        | 0.0195 | 13   | 1.3321          |
+| 0.289         | 0.0390 | 26   | 0.3452          |
+| 0.0635        | 0.0584 | 39   | 0.0745          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "down_proj",
-    "o_proj",
-    "v_proj",
-    "q_proj",
     "up_proj",
-    "gate_proj"
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_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 sha256:68604427cd083b580fc3c5d4d8958b7a287c470ad87b2a1ac645c43cc13c6bf2
+oid sha256:d5f8ff9917efa786ab1cf4cf474ebfc8a53543c5bade01f9c1d46b811fee9554
 size 323103018

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19cbf4ecbfce042252e641022bd504ddfce76d4ae8beaef0e80bba513676731b
+oid sha256:78102a43db16e692d1ea6a566807b28ac716dcf4f4908683065afe8e41fc9a5f
 size 323014168

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2582b8260dcd9ba74e4729f3dca3eddc9202355c03409cb87a0c310e92a237dd
+oid sha256:004d3e011643fbfcbb780589c7d95d33b23c819b8403b6d5a07ab9641302271b
 size 6776