Training in progress, step 200

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: nmt_21
 tags:
 - generated_from_trainer
-- trl
 - grpo
+- trl
 licence: license
 ---
 
@@ -27,7 +27,7 @@ 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/oleg-dats/nmt/runs/4dem28qn) 
+[<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/oleg-dats/nmt/runs/u8jyz3l9) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7686115b201e4f415409e5c01a68b58390e9f631ba4d1b33236cbca0e853d78e
+oid sha256:ad79f5a559141bbd0b1cd3d9b3f4e512bfbf33060521d64143ab5617be85a930
 size 1999811208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0129085a3334f196038e56c59c31749d00da1d7005996f5269e39777e9d9f6
-size 6904
+oid sha256:76fe024da92bce1c7bf8cff9ee12ca373a3a8667017dab3d942229b1baad9d63
+size 6776