End of training

README.md

@@ -1,17 +1,19 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+datasets: knoveleng/open-rs
 library_name: transformers
 model_name: MMR-Sigmoid-DAPO-7B
 tags:
 - generated_from_trainer
-- trl
+- open-r1
 - dapo
+- trl
 licence: license
 ---
 
 # Model Card for MMR-Sigmoid-DAPO-7B
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) on the [knoveleng/open-rs](https://huggingface.co/datasets/knoveleng/open-rs) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73ce5bb2236b4cdce3e19a4b94c89f63a08ff478d69f9c59c55273bb37335ba
-size 323014560
+oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
+size 40

config.json

@@ -3,7 +3,7 @@
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
+  "bos_token_id": 151646,
   "dtype": "bfloat16",
   "eos_token_id": 151643,
   "hidden_act": "silu",
@@ -46,6 +46,7 @@
   "num_attention_heads": 28,
   "num_hidden_layers": 28,
   "num_key_value_heads": 4,
+  "pad_token_id": 151643,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000,

generation_config.json

@@ -2,7 +2,10 @@
   "_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": "4.57.1"

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb5dbf948772449c6d7308911db9995e65427350d89c564eb62d309161f6724
+oid sha256:9142bf7a9d8f65d00b8c23a51d0c3aa94fee7236d399f19edcd0b0f5ffbd3194
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89bcf86a06534b25c0267c30660f5990afd20d5759c346bdff9301b9ef7f7c93
+oid sha256:28f25564a2353df691bf70435186f1470af42384e753840a1c7dc3be9e4970b5
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a270e9eb2a3777089e8dde6727e8d7e7f1adfb8809c44a4f01326e33e9479e
+oid sha256:0bb46f5dc66b5f9fc8ad7c1ead1771218ca8ba5e52901927da1a8a66e05022e5
 size 4330865200