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/andreas-jansson-2010-own/huggingface/runs/nqccs8t9) 
+ 
 
 
 This model was trained with SFT.
@@ -37,9 +37,9 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.15.2
-- Transformers: 4.48.3
-- Pytorch: 2.5.1+cu124
-- Datasets: 3.3.2
+- Transformers: 4.47.0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.3.1
 - Tokenizers: 0.21.0
 
 ## Citations

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.47.0",
   "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": "4.48.3"
+  "transformers_version": "4.47.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674b0d96227cb1c87998eb87cdb4c5b6081b7ef362d641bc30ddd5fcbe781062
+oid sha256:71701e97ac79efa716c9fc2900f7d4c1edda37b3f7a07490707cb079b24bcfa6
 size 538090408

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6f8dd16993d32d7cf20691c3f0929e759f4c488077e8215a4bebab35e7c04e
+oid sha256:55c397bb101c0ae937b29dc16782dd8f1311ced711ee141c2bf93e4d12dfb1ed
 size 5560