Training in progress, step 36

config.json

@@ -17,6 +17,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "pad_token_id": 50256,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ed3156f1a947f522bd4e90c9058fbc93efd5d5fc7f4bafb989d03c9ed13198
+oid sha256:e66f9ff0694ec30b618a9e8d10d53248ff3417772db830548736ae05b2149db4
 size 497774208

special_tokens_map.json

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

tokenizer_config.json

@@ -14,7 +14,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
-  "pad_token": "<p>",
+  "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 sha256:7982434d1b7eb8d81f97233732f427d1fa54949d8b5749aa8d706257817e5299
+oid sha256:dde9e26f29c05c06278a9aa275e453c30f7cf5703ad8f7f0ad319cff3e619e8f
 size 5432