Training in progress, epoch 1

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "t5-large",
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 4096,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 1024,
+  "d_model": 512,
   "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": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
   "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 sha256:0bf314497b90637b40c05a5b1de9aac936ba97311d68d84d288d0f1f8bdf1b6b
-size 2950844807
+oid sha256:3015b2fba10ac3b568f848b25ffec7acc36862c59e3a3c02e7955f97c855a30a
+size 242070267

runs/Aug16_14-35-02_f94b6edc6539/1660661666.6902423/events.out.tfevents.1660661666.f94b6edc6539.77.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6a2698f5e3d705ba487d698168a82413d2ec054161754906d556c381c3ebf9
+size 5653

runs/Aug16_14-35-02_f94b6edc6539/events.out.tfevents.1660661660.f94b6edc6539.77.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6f5915d55c2bf3b7a21224fa542bd18fc986d6709244f6dcc7c4d0c0909202
+size 5393

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f773853eaec07ab485ee49fb703ecb27492d60759815095a829298ad10984c
+oid sha256:e664655229c8f1f46b1f1540747efd884b205f4d90965615022d9107c9908d4c
 size 3439