Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "reaperdoesntknow/DeepReasoning_1R",
+  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

runs/Jan31_22-01-08_hefty-gardenia-butterfly-744db6889-4bk7w/events.out.tfevents.1738360871.hefty-gardenia-butterfly-744db6889-4bk7w.833.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df20ff239645f4f86ae85d7231022b6f0993d5456c3c597a6d3764f7f010ef4
+size 5146

runs/Jan31_22-02-39_hefty-gardenia-butterfly-744db6889-4bk7w/events.out.tfevents.1738360962.hefty-gardenia-butterfly-744db6889-4bk7w.1122.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141d638b1ab75b63a1e032be8103d2209fe2f023fb911de6b1961b78bfb72b26
+size 5354

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145191e3b102f64e84dab1926006ee71528c1ea536df048ef9ff6c48d01f95de
-size 11421995
+oid sha256:3bdce21acd901eb87a17e1302d0e9a90b137688f30877bd043b336ec7ed8348c
+size 11421996

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d61389722e4935879835c0a85e1e3220f536af80506f51b0756e623495ca5f2
+oid sha256:f815caf89ddf2e693deeb3b3fdb1e8bfd7408d2439a3fee0ae1987318cdb41d4
 size 5368