Training in progress, step 500

config.json

@@ -40,7 +40,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.28.0",
   "use_cache": true,
   "vocab_size": 50257
 }

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ t
 Ġ a
 h e

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fdbe681fba2ed9c4cb52f2e276140b8c25c8abca04097f40abb8935bd2eb9e2
+oid sha256:de7110a3d19e0b57b0be0e9d5bf277ccaab52039659551371e74d971cd795075
 size 333968953

tokenizer.json

@@ -39,6 +39,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -1,9 +1,9 @@
 {
   "add_prefix_space": false,
   "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
-  "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba20d23523a92dcb30c36a62fffd6efdd40ec720982a41e84dc646b727f7c6c2
-size 3579
+oid sha256:e3fea97edbc95f9cb6c15bc3c8e95e12cf746a415d635c783250e93a6eb1f398
+size 3643