End of training

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:b030a6ea7de7fd5dd7d11c86abe060ed3156acb9647918b35fc220e0da0221f1
-size 242071641
+oid sha256:3f34f4c4995c013126442d3540b4b0e00ac2c47c6b56911753dfc64cf37fef4a
+size 2950848513

runs/Jun26_18-01-24_ubb4-rack-07/events.out.tfevents.1687802488.ubb4-rack-07.190932.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3ab75c961d876bb3df5ad703a0a31e7aae76b4c3000b2aef8347f8b794ae72
+size 6044

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ff826997ef618786ad37d505d3bf35f53844caa84248436681f5ffeed8bcdb
+oid sha256:248c18bd409b1ff866e656125caeea78d4973fd7c583d55e8b648b710563798a
 size 4091