Training in progress, epoch 1

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "t5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 3072,
+  "d_ff": 4096,
   "d_kv": 64,
-  "d_model": 768,
+  "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": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "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 sha256:8a532d93d4798e9a9ae207752124004b27fdf551f5bfa63d2476fe6b64297dce
-size 891700799
+oid sha256:48ddb1aa7ea8b5c4cfafc2932822514b1d8f2f4bae19cdbc451fd127d6119a38
+size 2950844807

runs/Aug15_17-11-10_7b93ce7f3e1e/1660583864.9632442/events.out.tfevents.1660583864.7b93ce7f3e1e.958.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156cabfb3f67e1b403bcc0bdc322ccf8ac2d9a5fee9ea67d64fa2a24b8043747
+size 5653

runs/Aug15_17-11-10_7b93ce7f3e1e/events.out.tfevents.1660583864.7b93ce7f3e1e.958.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065cffdcfeb41f3c2e03d3b81afdf70e4974e0b5f8021f03e7df45d2fd6fc8d6
+size 5395

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5c50062af9664e2604a09b124c86b0e9a8b0857b0e2537615fd2700eb73192f
+oid sha256:e343e445a1f9795140eae083a0a6b07b7e0ea63c41b7130914a4c2f1afe69be6
 size 3439