llamantino7b_question_answering_finetuining

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [swap-uniba/LLaMAntino-2-7b-hf-ITA](https://huggingface.co/swap-uniba/LLaMAntino-2-7b-hf-ITA) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4122
+- Loss: 1.9046
 
 ## Model description
 
@@ -44,15 +44,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 3
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6512        | 1.0   | 90   | 1.4570          |
-| 1.1883        | 2.0   | 180  | 1.3863          |
-| 0.8381        | 3.0   | 270  | 1.4122          |
+| 1.6731        | 1.0   | 90   | 1.5039          |
+| 1.2298        | 2.0   | 180  | 1.4252          |
+| 0.8714        | 3.0   | 270  | 1.4593          |
+| 0.5776        | 4.0   | 360  | 1.4850          |
+| 0.3747        | 5.0   | 450  | 1.5199          |
+| 0.2584        | 6.0   | 540  | 1.6924          |
+| 0.1781        | 7.0   | 630  | 1.8130          |
+| 0.1373        | 8.0   | 720  | 1.6641          |
+| 0.0993        | 9.0   | 810  | 1.7835          |
+| 0.0728        | 10.0  | 900  | 1.9046          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:993954f9ce4becbddd037c39dc491eec4d1a6ee4902b806353dbb77551c460ca
+oid sha256:9c2bfc2a55106a9664ae2b78b967063ba76640ded7bd529fbf1d1cfc15941e73
 size 134235048

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79dcf18fbeb323b5d98ac12737e836d00054fe2efd3d36492ac88a8e9c0bef19
+oid sha256:fb77ff0653c5f5c2324aba636415478eb1b421b961ae164bd3772bdb21f0dc7c
 size 4411