Training in progress, step 100

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.2",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6fb67ebf2d7de4b6952e1089155915ae2409b9345757eb4555b1c54f2e7afa0
+oid sha256:5728e0c9a85095eef4a68762ce9017928216d42529454b4112e19ba087f31baf
 size 3087467144

special_tokens_map.json

@@ -21,11 +21,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|im_end|>"
 }

tokenizer_config.json

@@ -201,7 +201,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|im_end|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb1e097e43934932d30af58acb0d5c4a6ccdafecea01abc53520ad768a1d490
-size 7761
+oid sha256:dc6af2c026a61de501d4c57246bfa988e801895351b5f7a60dde6fe4c6cf189f
+size 8529