End of training

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4301
+- Loss: 0.4247
 
 ## Model description
 
@@ -55,22 +55,22 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8205        | 0.3   | 25   | 0.5577          |
-| 0.5013        | 0.59  | 50   | 0.4856          |
-| 0.4588        | 0.89  | 75   | 0.4663          |
-| 0.4503        | 1.18  | 100  | 0.4556          |
-| 0.4319        | 1.48  | 125  | 0.4482          |
-| 0.4293        | 1.77  | 150  | 0.4429          |
-| 0.4272        | 2.07  | 175  | 0.4387          |
-| 0.4153        | 2.37  | 200  | 0.4365          |
-| 0.4111        | 2.66  | 225  | 0.4343          |
-| 0.4031        | 2.96  | 250  | 0.4322          |
-| 0.406         | 3.25  | 275  | 0.4317          |
-| 0.3996        | 3.55  | 300  | 0.4309          |
-| 0.3959        | 3.84  | 325  | 0.4303          |
-| 0.3989        | 4.14  | 350  | 0.4302          |
-| 0.4035        | 4.43  | 375  | 0.4303          |
-| 0.3929        | 4.73  | 400  | 0.4301          |
+| 0.7919        | 0.3   | 25   | 0.5285          |
+| 0.4811        | 0.59  | 50   | 0.4738          |
+| 0.4512        | 0.89  | 75   | 0.4567          |
+| 0.4367        | 1.18  | 100  | 0.4465          |
+| 0.4162        | 1.48  | 125  | 0.4399          |
+| 0.4188        | 1.77  | 150  | 0.4352          |
+| 0.4127        | 2.07  | 175  | 0.4318          |
+| 0.3981        | 2.37  | 200  | 0.4296          |
+| 0.3887        | 2.66  | 225  | 0.4281          |
+| 0.3943        | 2.96  | 250  | 0.4258          |
+| 0.3808        | 3.25  | 275  | 0.4263          |
+| 0.3836        | 3.55  | 300  | 0.4251          |
+| 0.3824        | 3.84  | 325  | 0.4247          |
+| 0.3782        | 4.14  | 350  | 0.4246          |
+| 0.377         | 4.43  | 375  | 0.4247          |
+| 0.3725        | 4.73  | 400  | 0.4247          |
 
 
 ### Framework versions

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a723e022024cdfece83514750f0c6efcf4dc33aefc626f199a1553a4a60f8d
-size 25191728
+oid sha256:3f6e54b85b5e1c319ff06364aeaea95c8377744edc2f8c79bacf1b9407e39b8c
+size 50357632

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b08e1878e76116da9d989483eca71f784ccf29c23ca5c4fb9e809222fcba214
+oid sha256:a2247bb79d70a2c0061f08825809540083701a72d23993237e18e744b81f6631
 size 4920