Training in progress, epoch 1

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "t5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 3072,
+  "d_ff": 4096,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 1024,
   "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": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f29b98186e6dabd984698798ddb11c5962af20d6b90339140842292f67f89bf
+size 2950734544

runs/Jan16_20-44-57_192168021136.tpgi.com.au/events.out.tfevents.1705409099.192168021136.tpgi.com.au.2926.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75c8cbce7a15dd20269dd5d1424c7d4b481e6f467424762d9199e57ae298123
+size 37024

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.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd991f854fb46c64f1fa9a5ffa32a90d83bb8b496a802ef8b64581c6c21e1255
-size 2422519
+oid sha256:04e7404608459e95fe67c3cf18a4c34369e15375a86e918d13644e5c7314699f
+size 2422444

tokenizer_config.json

@@ -930,10 +930,8 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "legacy": true,
   "model_max_length": 512,
   "pad_token": "<pad>",
-  "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 sha256:09de3c93a96f3eb996c13365796654b25c88d7f8959e7f4f10fc194a34430def
+oid sha256:24fc25fe6f4cc233921eee4e62238febbbcc0cad12117c39eae225089076b230
 size 4792