Training in progress, step 20

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5902
+- Loss: 0.5699
 
 ## Model description
 
@@ -39,21 +39,22 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- training_steps: 80
+- training_steps: 100
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.1581        | 0.02  | 20   | 1.9857          |
-| 1.1128        | 0.04  | 40   | 0.8156          |
-| 0.8092        | 0.05  | 60   | 0.6632          |
-| 0.5965        | 0.07  | 80   | 0.5902          |
+| 2.1594        | 0.04  | 20   | 1.9765          |
+| 1.1079        | 0.07  | 40   | 0.8140          |
+| 0.8124        | 0.11  | 60   | 0.6610          |
+| 0.5827        | 0.14  | 80   | 0.5901          |
+| 0.4148        | 0.18  | 100  | 0.5699          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "o_proj",
     "q_proj",
     "v_proj",
-    "o_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd19ae0476802f82752fb3a6199d13bde26c836b1a2e5342892688f59aba329
+oid sha256:e2f6526d19004c7e9832ef5eeb254e3d39aa3d639e20d8c32b9dcf3542f65826
 size 67143296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d2bc654f8aa85fed95b942ed73d1b0c8b49a104a6c1523d3bca806caa40068
+oid sha256:bec8f9f245df0ded77c6cf1d11f8f56d034ba2c408a5f3f292f80fa38360aba6
 size 4283