Training in progress, step 500

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "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,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea81fa77c07165703229f52950f0ab0f4eab20619bb67807874b148f425c26a
-size 242041896
+oid sha256:a9623a566b55ba2d58123c9a48c74c758d421895b65680483f3892b14f8547a2
+size 891644712

runs/Dec17_13-34-53_40233d184a32/events.out.tfevents.1702820100.40233d184a32.42.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d82e73e104d034e7f3bf9f2abfac62129915214556bfb07a8715da8f3c20a1c
+size 6634

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>"
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c79aa1e0f618ef1bd8c80b60267698992bb097c30a070d16cacdbb49290e65e
-size 4856
+oid sha256:1fc0aeba04f2a8f2214b798dba7eb7a1c76e1584b92ce6170f92260118725ed1
+size 4411