End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: google-bert/bert-base-multilingual-cased
+license: other
+base_model: tiiuae/Falcon3-1B-Instruct
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-finetuned
 
-This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
+This model is a fine-tuned version of [tiiuae/Falcon3-1B-Instruct](https://huggingface.co/tiiuae/Falcon3-1B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.5548
+- Loss: 5.6657
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 396  | 5.1889          |
-| 3.4178        | 2.0   | 792  | 5.3704          |
-| 2.5552        | 3.0   | 1188 | 5.5548          |
+| No log        | 1.0   | 396  | 5.8367          |
+| 3.2426        | 2.0   | 792  | 5.2895          |
+| 1.9326        | 3.0   | 1188 | 5.6657          |
 
 
 ### Framework versions

generation_config.json

@@ -1,5 +1,6 @@
 {
   "_from_model_config": true,
-  "pad_token_id": 0,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
   "transformers_version": "4.47.1"
 }