Training in progress, step 500

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 sha256:44bdca985aa6dab185dbbb387df67eb6834166c50511fcb2cee255dc33de6e8d
-size 242071641
+oid sha256:e5e766a0903993eb28969924cbd56169a7db6e9887d9d8549245e997f708fad1
+size 891702929

runs/May19_23-19-15_solide/1684531177.543046/events.out.tfevents.1684531177.solide.4133983.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e371c29c9b9b66f8f0caec68ba36dfb71d10cf558f02f6c123ed63c03259d4f7
+size 6120

runs/May19_23-19-15_solide/events.out.tfevents.1684531177.solide.4133983.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419f04e08f8d43d747559d75e1482a18cb0c81efaa843bbc9e1b2362071b0a78
+size 5047

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5827b8a41896015031b9ac69bae87b3f8a980913c9c77c24a3618ef0037b3f8
+oid sha256:60d64ad9f4e28fa41c2aa034574fa3612e627b4afe3284967c61ca10b897368c
 size 4091