Training in progress, step 10

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: Qwen2-0.5B-GRPO-test
 tags:
 - generated_from_trainer
-- trl
 - grpo
+- trl
 licence: license
 ---
 

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
-  "use_dora": false,
+  "use_dora": true,
   "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6bbba0c705140707c13178359306416fcc7d84540caee6847e0940b327a042
-size 2175168
+oid sha256:80be6d0c29e5c5010ab88df042f9d95ba3230bd62a6ba1070b573ee71f49bcd2
+size 2279984

special_tokens_map.json

@@ -10,11 +10,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|im_end|>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9899192fdb18f1dea0b6b1af923711bd8307b0d7bea52fb0c86edf1271ab472f
-size 11418531
+oid sha256:09ae1170fe6d155dd07f6038b04c251d1ebdab1b020382645cdaba1c25ed63eb
+size 11418528

tokenizer_config.json

@@ -36,9 +36,8 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 32768,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|im_end|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
-  "truncation_side": "left",
   "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e11bb2e71c80f7a10946104a8ef3957e37c7f16fc238b4526503cf79ec2fe8e
+oid sha256:ea66d2732ab798c93d366b85588b5ed13c8c7ee1117c8d877832982cd9f734a8
 size 6840