Training in progress, epoch 1

README.md

@@ -28,7 +28,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
- 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/sft_best_simplification/runs/z8ase0iv) 
 
 
 This model was trained with SFT.
@@ -36,7 +36,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.24.0
-- Transformers: 4.57.2
+- Transformers: 4.57.3
 - Pytorch: 2.9.0
 - Datasets: 4.3.0
 - Tokenizers: 0.22.1

adapter_config.json

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "q_proj",
-    "gate_proj",
     "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
     "v_proj",
-    "k_proj"
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72eb424fcda49e1c6989872f6e1285cabdc01a8b195a05e340a9c235ec65bdf9
+oid sha256:64640b8ce0516430b391518ed24399ca4e51eb983c5960760dffc52efcbb2849
 size 167832240

tokenizer_config.json

@@ -6179,7 +6179,7 @@
   "legacy": false,
   "model_max_length": 32768,
   "pad_token": "[control_768]",
-  "padding_side": "left",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bd370958f23b8bcdae63fbf60cf67ea84485eb6f42a2ac31c8d63a9d834dac5
+oid sha256:728720adce4a059df15b2523efec96366c54f9461193f2cca2b1c04ee6c7c384
 size 6353