Training in progress, step 500

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google-t5/t5-small",
+  "_name_or_path": "google-t5/t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82faa07a4815c47f13744858291aba9410b21d07b991b26b23e5f25c15e3e80a
-size 242072086
+oid sha256:1c19d67a62590ee6391a9f91a9df91d17c318784cd8e04825f2ec5b4cb9423f7
+size 891703374

runs/Oct24_15-27-04_d4afecba7390/events.out.tfevents.1729783754.d4afecba7390.358.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0a4f678a1ecc2c6db9fe6b73adc6e699647aa98de3095c7cca13fa368d31dd
+size 88

runs/Oct24_15-29-43_d4afecba7390/events.out.tfevents.1729783793.d4afecba7390.358.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b37851cc2b45771b54cb6fcfba01f77a85bbf694277acfffb3c10a38ccdda661
+size 88

runs/Oct24_15-33-40_01eb67b6d89e/events.out.tfevents.1729784036.01eb67b6d89e.494.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f2915a1e96409f0c3aa4d9e006a94a1d13ede4556157919e07b63d27eb18af5
+size 6052

runs/Oct24_15-34-37_01eb67b6d89e/events.out.tfevents.1729784091.01eb67b6d89e.494.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e9d8fe600b9d82b1cf8d82a13baac8d3bda69277635718b85674db32df5aba
+size 6052

runs/Oct24_15-39-19_ac31b9486969/events.out.tfevents.1729784362.ac31b9486969.1295.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e131f76bc6603204bdddcccbde2a85edadd00374c5a8a8cfb27191e1939b3889
+size 6052

special_tokens_map.json

@@ -101,25 +101,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -930,7 +930,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a516301509a6b6000e42c3722b2b1e5b5f66fcac5ced440b8f696656f3436263
+oid sha256:992556fcce0a21eb861c20611c5893a7148b687129fe208e2a7c4474009bb4c6
 size 5432