End of training

README.md

@@ -29,7 +29,7 @@ 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/manuel2788-student/huggingface/runs/vw9xw443) 
 
 
 This model was trained with SFT.
@@ -37,8 +37,8 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.13.0
-- Transformers: 4.48.0
-- Pytorch: 2.5.1
+- Transformers: 4.47.1
+- Pytorch: 2.5.1+cu121
 - Datasets: 3.2.0
 - Tokenizers: 0.21.0
 

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.0",
+  "transformers_version": "4.47.1",
   "use_cache": true,
   "vocab_size": 49152
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.48.0"
+  "transformers_version": "4.47.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5869564fc98e8c817bb3259acee67d509c4161b594a2b57c61ca83f7aab07109
+oid sha256:57fa1e8f0723858dc466ac1f84366e3c3698c70849a5f63ec91d64cc0f0ca0ac
 size 538090408

runs/Jan13_20-04-11_26f63dd49317/events.out.tfevents.1736798661.26f63dd49317.1427.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1d9072bdda0c3c47dda8916d119d386735f9b901ceb3202aa0fa25639db1ea
+size 9667

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:210c7ede970dcf902a0bd65ba35e79047a790bff78b36a9b3be02b3d40bf78af
+oid sha256:28232b5014551e40539306ed57a4d9f1ff156ba0168c3a499c5a0d834f289792
 size 5624