End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4647
-- Accuracy: 0.8284
-- F1 Macro: 0.7893
+- Loss: 0.3923
+- Accuracy: 0.8414
+- F1 Macro: 0.8365
 
 ## Model description
 
@@ -55,18 +55,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
-| 0.9663        | 1.0   | 461  | 0.9493          | 0.6278   | 0.4609   |
-| 0.5136        | 2.0   | 922  | 0.5921          | 0.7721   | 0.6943   |
-| 0.4578        | 3.0   | 1383 | 0.5004          | 0.8128   | 0.7707   |
-| 0.4147        | 4.0   | 1844 | 0.4632          | 0.8313   | 0.7930   |
-| 0.4134        | 5.0   | 2305 | 0.4603          | 0.8302   | 0.7950   |
-| 0.3137        | 6.0   | 2766 | 0.4506          | 0.8334   | 0.8007   |
+| 1.8719        | 1.0   | 454  | 0.8635          | 0.6562   | 0.6261   |
+| 0.9455        | 2.0   | 908  | 0.4734          | 0.8168   | 0.8068   |
+| 0.7437        | 3.0   | 1362 | 0.4071          | 0.8366   | 0.8305   |
+| 0.7825        | 4.0   | 1816 | 0.3959          | 0.8433   | 0.8391   |
+| 0.6047        | 5.0   | 2270 | 0.3910          | 0.8400   | 0.8341   |
 
 
 ### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.46.3
+- PEFT 0.14.0
+- Transformers 4.47.1
 - Pytorch 2.5.1+cu121
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
   "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": 8,
+  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -24,9 +27,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "q_proj",
     "o_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2bcd6c60001dbc2237b3505e76e426e0c04ec24b290b237796366b11b88369f
-size 13705936
+oid sha256:c9570697e31ab5a34151d097d327027761065671d7f15bdf09ea2e268ce59e17
+size 13689552

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88edd027c86f02ac7eeed3312ae46b879bba5fa6513a61b33b80af8e429a3603
-size 5240
+oid sha256:228d077441d5e7cbe1b2437a6229a57c88d77117b635799e27470c0e6ef6e9e6
+size 5304