Training in progress, epoch 1

README.md

@@ -1,16 +1,17 @@
 ---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-14B-S
 tags:
 - generated_from_trainer
-- trl
 - grpo
+- trl
 licence: license
 ---
 
 # Model Card for DeepSeek-R1-Distill-Qwen-14B-S
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -26,18 +27,18 @@ 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/leonwenderoth-tu-darmstadt/huggingface/runs/6a386o6n) 
+[<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/leonwenderoth-tu-darmstadt/huggingface/runs/iu6e5zo1) 
 
 
 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).
 
 ### Framework versions
 
-- TRL: 0.23.0
-- Transformers: 4.56.1
+- TRL: 0.23.1
+- Transformers: 4.57.0
 - Pytorch: 2.7.1
-- Datasets: 4.1.0
-- Tokenizers: 0.22.0
+- Datasets: 4.1.1
+- Tokenizers: 0.22.1
 
 ## Citations
 

config.json

@@ -72,7 +72,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.56.1",
+  "transformers_version": "4.57.0",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064

generation_config.json

@@ -2,9 +2,11 @@
   "_from_model_config": true,
   "bos_token_id": 151646,
   "do_sample": true,
-  "eos_token_id": 151643,
+  "eos_token_id": [
+    151643
+  ],
   "pad_token_id": 151643,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.56.1"
+  "transformers_version": "4.57.0"
 }

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76a14ed54417be239f27ae59777ae7eebd875f750335f2fa47e677351557665
+oid sha256:4a28ed54e22d1618184d024bbc615ce235dc2f619f2bcc00752cf2de8cf38671
 size 4986211280

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e70a36d0608d44151409b6f25c45549a0623b37d3516a02d3c8dd33c8e891c7
+oid sha256:49aaf3ca229073a79400b90f6f281145c765b5fb75bef79acdbfcb02b8c92db4
 size 4954847344

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d48a71e319ad69a142680ee76a11e5e7a43f727f109ba63697e40f28547eb05
+oid sha256:1534325c790b6626a9001027609b400d0c93c70c57266277bc83bf090ae252d1
 size 4954847392

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84bdc0df9ca25d511c5e674897da06ff95534c72818f1ae3dc8d9b6c8ed2a1bb
+oid sha256:63dd4e92e1598cc694a91cc5a63d49ec247022d1f4279dc9a8a712ddd747232d
 size 4954847392

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89b3dd9932916841f82346a061eb10a1eedaa983bc71ae905b7ab16779fbb08d
+oid sha256:44fbdff5473f1003f51bede61ee47a581c324932965b1953c580d76a22def7cd
 size 4954847392

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789e3540d3ee9e48735631e0033a68bf200e1784d4450e97267aba93e9a49c11
+oid sha256:28281519df0036b34b38bd0cc1f41e5c7a4d0627df22a7956b6dd24fca00dd9f
 size 4734533160

tokenizer_config.json

@@ -185,12 +185,8 @@
   "eos_token": "<｜end▁of▁sentence｜>",
   "extra_special_tokens": {},
   "legacy": true,
-  "max_length": null,
   "model_max_length": 16384,
-  "pad_to_multiple_of": null,
   "pad_token": "<｜end▁of▁sentence｜>",
-  "pad_token_type_id": 0,
-  "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizerFast",
   "unk_token": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d80aafc48380c25f7aee75112f98f473c886053a645dba01c313d2bd0f1f7af3
-size 11665
+oid sha256:8d2f7cc3fdd41307ad68275dea955ad58f734e9b3a6c9f65bb8ec2cb84479e42
+size 11729