Training in progress, step 108

README.md

@@ -28,7 +28,7 @@ More information needed
 
 ## Training and evaluation data
 
-Trained on the 0.4% of successful pass@100 traces (https://huggingface.co/datasets/3N3G/qwen3-4b-instruct-qwen3-instruct-hard-problems-guided-rft) generated by qwen3-4b-instruct from https://huggingface.co/datasets/d1shs0ap/qwen3-instruct-hard-problems-guided
+More information needed
 
 ## Training procedure
 

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b2a238ce8ff81c7e44636e1c0e073f188ca88da5bdbb8646d3b44f0c4659235
+oid sha256:e93e354d9bfc3f33ffe75d00a52d3a25b8d70d33576bc4306ca9e8aef0dac63e
 size 4990095032

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:411a065e94f0b73457df5dacf339efc77f4f9faaa632a11612f8a85d704a5b65
+oid sha256:311ded241c99714639975e8b392060eedce8443d9ae70b217f823b60832dc365
 size 4944309096

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b001d04573fa303c7114053eabb415c7fdab64746ec39260aeac24b70947987
+oid sha256:4cb66bdf8d414d021d725fd0ae94b6ef8388e83d8f638dcebf31d43d0a52d3c3
 size 4996758848

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d384e87bbe697fcb8e3e8bfd32234880739ae6dc813dfb98754b39746ed7cc9
+oid sha256:52079ad60c1653bbb4563ab6dca41d41a42023767bd70b0d2194ca05c6c823b2
 size 1158754848

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8da7f055f72a8c41e1d87a4a7864843bb00ea5cb4873b037bd9b1a09f4176684
-size 5816
+oid sha256:3da58462a98ec5866a89a78d1f378581bf52c74fc0efd23601fcf4f17df3afcb
+size 5880