Training in progress, epoch 1

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
-  "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 sha256:0460cfe9050de966b6db416d119b0e839a1c5939a6715533eb60b6cf903193b9
+oid sha256:0ba961e4239d67a3f12bd1cc1d6b6f12edcb2bfb1e1d477a569e989e9922212a
 size 3087467144

special_tokens_map.json

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

tokenizer_config.json

@@ -201,7 +201,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,
-  "pad_token": "<|im_end|>",
+  "pad_token": "<|endoftext|>",
   "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:f2570fefb19e376784ffc2affca3b5dd3c838a314e3a384912b22fb1b83088a4
+oid sha256:524f1c3aa225ec1fc5c5ccb3e0c4bf4aa07cb3548586aff95a7ae286f45613e4
 size 7480