Training in progress, step 500

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50256
+}

config.json

@@ -40,7 +40,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.34.0",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335ffa7e97fe3f3ce8e75a791ddfc78db826ff07bc664c63fd9b5fbcd4be7cc9
+oid sha256:33670b4a63cd94a6ede4dfffef34a914df7d078ea68e9c72cdf4dc8a07a8b041
 size 327675282

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdfa97faea3313cc5c56d9b38cd7e2a32722ee310238abd9bf753542275a1ef
+oid sha256:55a4e87324845f5151203af835f695f8d9d380364ad66784713c56d3a22498a8
 size 4536