Training in progress, step 500

config.json

@@ -16,6 +16,7 @@
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
+  "max_position_embeddings": 1024,
   "model_type": "t5",
   "n_positions": 512,
   "num_decoder_layers": 8,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40766344757d929044d875caca99c346c03a6da38cff41d082c6ffd93c8f7f3
+oid sha256:cea496ea6f12a9f68f2c825de15bc8ecd55b344f2410cfa4e59e9da842f07b6d
 size 307867048

runs/Dec31_18-23-30_d44b6d7edf02/events.out.tfevents.1704047014.d44b6d7edf02.1137.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbedb950befd72caa8b1fbc1f84e1a80ec083911ab789cbbe035f260dcabde1b
+size 6026

special_tokens_map.json

@@ -102,6 +102,6 @@
     "<extra_id_99>"
   ],
   "eos_token": "</s>",
-  "pad_token": "<pad>",
+  "pad_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer.json

@@ -12,9 +12,9 @@
     },
     "direction": "Right",
     "pad_to_multiple_of": null,
-    "pad_id": 0,
+    "pad_id": 1,
     "pad_type_id": 0,
-    "pad_token": "<pad>"
+    "pad_token": "</s>"
   },
   "added_tokens": [
     {

tokenizer_config.json

@@ -930,8 +930,8 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "model_max_length": 512,
-  "pad_token": "<pad>",
+  "model_max_length": 1024,
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc55100b439264dcbfd1ca4bfd856975a2d093db78993b4477163052caadcfcf
+oid sha256:f59576eee11e695ef78771f3c0980673e2c736677e9c343de4968bab1bc0b6c7
 size 4792