Training in progress, step 500

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "t5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 2048,
+  "d_ff": 4096,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -17,9 +17,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
   "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:e48b3847454d4c27ed0c1bde4922d3712c53b7846ff4232f892b14f0cd3f1b4c
-size 242069785
+oid sha256:31ab40a3638b252be0b880b0b396a7718adab0b01a047681613be38945bffe36
+size 2950841345

runs/Jun12_09-19-57_5f07fe1612f6/events.out.tfevents.1686561806.5f07fe1612f6.5756.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab8aa415cb4a691dcbbfbbcc5edde0168bae24d798e7d3185474ab98926efcd5
-size 7025
+oid sha256:649bd8181421285b2dd144c5d656e9346ac4089ccb9317d5279bf589684b8422
+size 7182

runs/Jun12_10-08-26_5f07fe1612f6/events.out.tfevents.1686564553.5f07fe1612f6.20935.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55df3228e483dfe893d8e5c336c75a4beca7fcbd72c7c7da9da7c9262b82e17
+size 5146

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c62ce46bdb8434e536fd47a9b27d7dbb28c9f2aaf40156959c64f0491931fae2
+oid sha256:f5e1e78b7151160719a7d2ace2cdaa84d2548b2d363cdac26ef5ebfe4e1120be
 size 4091