End of training

README.md

@@ -29,16 +29,16 @@ 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/rchai/huggingface/runs/0smlqe8x) 
+[<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/rchai/huggingface/runs/5huic83c) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.15.1
-- Transformers: 4.48.3
-- Pytorch: 2.5.1+cu124
+- TRL: 0.15.2
+- Transformers: 4.49.0
+- Pytorch: 2.1.1+cu121
 - Datasets: 3.3.2
 - Tokenizers: 0.21.0
 

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.49.0",
   "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": "4.49.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58031ed46d247ecb2944573e104145ff0fb5ec0967469067a1a94bf650b293f9
+oid sha256:3412f19b0961890f4618a7e6f14ae70a782a359943d863a5248c8c39febd1896
 size 538090408

runs/Feb26_15-33-01_nuaeuxv1k8/events.out.tfevents.1740583995.nuaeuxv1k8.410.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf34e2a8ac531d93064945ef1cf61756e4e24c59bfe0654de2f1ea0fa54e38b
+size 39997

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f7a37d4215cebf3fc5b9c1220d52b058b13d47279d829f9dff18345b9cb3de1
+oid sha256:29ff49ac90b9ee103849fa8952756a0e17f4c11fd88035246d23306ea8ecccf0
 size 5560