Training in progress, step 129

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
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7086c1f05ca73dc743acb440e0b0951ec38af227a3ad8ad6222f9a093b9a486e
+oid sha256:f863f8ae9b58c5672f2b96ea1c1d3c4f9bb5fb4bbc4b7c31a199d07e5477ad64
 size 4986380064

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b46c456c36db7ec43114724f59a1c14cf80f9fa280e4fe7d260b27e2a51fcf8
+oid sha256:e865eaaaff5f14937b3afe899b33089a47236e9e6cc38f2a51b34c173b8e82c1
 size 399532808

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 sha256:03fd4283bf1b2dbecd300fe5826475cb456b5c67cfd046cd886a800f0926512f
-size 5368
+oid sha256:817cf3c103100544a8a412c6d5a7151056ce15df29e9e92b1814dfdfed826929
+size 5240