End of training

config.json

@@ -14,7 +14,7 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 4,
   "num_key_value_heads": 8,
-  "pad_token_id": 32000,
+  "pad_token_id": 2,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 768,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46cdb792d23ebd5f6a9e90d73f029d33201876446e72fa196ce1e068434bf820
+oid sha256:2da1ec7d61ea32e93b946fbeb1ec82cc7c8586a92b18a8f22d1d12181bb1c21f
 size 239899848

special_tokens_map.json

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -41,7 +41,7 @@
   "max_length": 30000,
   "model_max_length": 1000000000000000019884624838656,
   "pad_to_multiple_of": null,
-  "pad_token": "<pad>",
+  "pad_token": "</s>",
   "pad_token_type_id": 0,
   "padding_side": "left",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686a3d770bde84792a2efe3476d3f2485c0bcf9848651de478752bbf74363953
+oid sha256:7e3a5cf066e13c6e29ef19291b1a8f7ca39f9ac86246cb326aa3bbc9b42ffc9e
 size 4536