Training in progress, step 500

config.json

@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0.dev0",
+  "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c002bc128c5287bb109b739072e41599ba2c725cfaa28ada4ac401838925b2f
+oid sha256:981e80027b33da4f4a0601fcba83709aa63ffc732030ccb9ec8f00a9d3a1b09f
 size 497807197

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -9,7 +14,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     }
   ],

tokenizer_config.json

@@ -4,17 +4,17 @@
     "50256": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "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,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ed5d9ea05069e4637f86b3eb830506f5faf3d7a1d1861c9ffd7835691d8d14
+oid sha256:785513a6cc64a18d567f012e741e41bddfa83436f1178e4febeaac4cf2b1eb87
 size 4027