t5-qg

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "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,
@@ -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": 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:b4519a0a301b271a4aff30155c6bc958072df977587a29852161b73351a7ee3f
-size 242016345
+oid sha256:145414a7e4c60cad9ada1bc978c9dc3d109acea373cd4253f0c5d1e9b2165423
+size 891619985

runs/Feb23_22-59-46_a362d227330c/1677193199.5576441/events.out.tfevents.1677193199.a362d227330c.2861.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eed55ce2f5ebb566c82bc5930c19c625c7b0bc7af1e308ffb7bbd5d3100386a
+size 5700

runs/Feb23_22-59-46_a362d227330c/events.out.tfevents.1677193199.a362d227330c.2861.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b3ddd5ebf6662f01fbbf83b1feefa4918cf3576e1f25b0ceec5197dcaac34c
+size 4654

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152d5cdf5bcb65ce45f0917d5bd67526a42c75da10045dff9fbc02c67c8ca799
+oid sha256:b0ea9e5431ae4f4bf35c27f0ee702ac53202bb7069d92234ccc288f3ba688fd8
 size 3451