Training in progress, step 1

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -27,7 +28,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.0.dev0",
+  "transformers_version": "4.45.0",
   "use_cache": false,
   "vocab_size": 32256
 }

tokenizer_config.json

@@ -183,12 +183,11 @@
   "bos_token": "<｜begin▁of▁sentence｜>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<｜end▁of▁sentence｜>",
-  "extra_special_tokens": {},
   "legacy": true,
   "model_max_length": 16384,
   "pad_token": "<｜end▁of▁sentence｜>",
   "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizerFast",
+  "tokenizer_class": "LlamaTokenizer",
   "unk_token": null,
   "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d59a5a16ed26c0d7af0c99fa6d5413fd1a93bbb28edb45403639d8d1b1703c9
-size 5368
+oid sha256:cdf687aacdd70232dbb5a88cea332d24c5890f4c91d7b25cab83b2c675f99649
+size 5240