Training in progress, step 500

config.json

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

runs/Jan31_18-52-17_emotional-turmeric-vulture-6dd559ff59-xmlwz/events.out.tfevents.1738349540.emotional-turmeric-vulture-6dd559ff59-xmlwz.1804.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:616354d2f30268f4a510f7c412d4635f822ae503b2727d957a1b9ffe64c4de04
+size 5362

tokenizer_config.json

@@ -200,9 +200,13 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "max_length": 1024,
   "model_max_length": 131072,
   "pad_token": "<|im_end|>",
   "split_special_tokens": false,
+  "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29cefa34ca3eb5d008bd4aaec00fafe15c00ca3a3293283e0b19918f4baf48e5
+oid sha256:554b48581a3606f61a6268e301f4d5b44b79112ea1fa410ece57adfd27800272
 size 5368