SFT fine-tuned model - 1 epochs, LR=2e-05

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0a75778dfdb7e39b0ad298f169dc80246d1e4f53e43099b2c9b18ee8bc7ec1
+oid sha256:763c718f735c004b3a50a76b757202816b2614a8fc92b3927ee3bb6f8094c121
 size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a3b28ded675c419eccbc43215f26c7127ea5a1a5e54f0544c8eb481630c3f80
+oid sha256:6460e29425130ea65f21cdf6970e3ca45c1e6fc68e8490628cb22340d81a71e7
 size 3077766632

tokenizer_config.json

@@ -231,10 +231,16 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "max_length": 2048,
   "model_max_length": 262144,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
   "padding_side": "left",
   "split_special_tokens": false,
+  "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": null
 }