Training in progress, epoch 1

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:ca355f6b4faa4746c2e5673327e6f134e73c3715005aeaffe7fded9cf99da808
-size 242071641
+oid sha256:ed69d613e80d87fdff69178fd66ada1df340a659e180925cc4b4e6ec4d1029bd
+size 891702929

runs/Jun09_08-41-27_b816c7661e3c/events.out.tfevents.1686300154.b816c7661e3c.5867.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568a60e64530bd003f563870d6d98495be261171aec51f9d52ac9f3bd93d1b81
+size 5885

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1fd57f1483a07452e0dd499a7b043a10dbec428f82aa07fa3395e91b825e17
+oid sha256:47a795fb8554ff00244933b83e99971215ec7d017c9aed58606cdf0fe5196d65
 size 4091