End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7752
+- Loss: 1.8785
 
 ## Model description
 
@@ -36,26 +36,26 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 4856
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.995) and epsilon=1e-08
 - lr_scheduler_type: reduce_lr_on_plateau
 - num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch  | Step  | Validation Loss |
-|:-------------:|:------:|:-----:|:---------------:|
-| 1.8951        | 1.0000 | 7824  | 1.8894          |
-| 1.7225        | 1.9999 | 15648 | 1.7752          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.0279        | 0.9999 | 3912 | 1.9928          |
+| 1.8365        | 1.9999 | 7824 | 1.8785          |
 
 
 ### Framework versions
 
-- PEFT 0.13.2
+- PEFT 0.14.0
 - Transformers 4.45.1
 - Pytorch 2.4.0
 - Datasets 3.0.1

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "google/gemma-2-2b-it",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "k_proj",
+    "up_proj",
     "q_proj",
-    "gate_proj",
     "v_proj",
-    "k_proj",
     "down_proj",
-    "o_proj",
-    "up_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a370041cafe67597a41400a259b78c0ab58862ba4bac2dbe32295fcfcff0d2e
+oid sha256:81074065d77991800b5b0a08d6783de402a32d8780a3a451ade3cd8d6f55402b
 size 41581360

runs/Dec08_07-56-39_3c46bd1dcd85/events.out.tfevents.1733644600.3c46bd1dcd85.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e393b7dbaec7aa7222e0f166debfd7601b49eb6a6bbbc5c60ee036c27f0e89
+size 9734

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3937b0bacb52dab66fdae21c3d354cb35fd3bf0b9bdaf7f337581ea386e2c697
+oid sha256:405eba1f683dc1d69866e1c523b97c83fcbd8e4c693884b09e9278a7b5dcb6b5
 size 5240