End of training

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "google/flan-t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 2048,
+  "d_ff": 1024,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
   "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:a9c41f877fe0e15973fabd60eebe3564b42af1d4ff106ce50b28fe6c667b6cb6
-size 990408885
+oid sha256:d11d45f5d5e529e57c24a7a2454d860c50aae608b31be38e180cab72d05f4442
+size 307910149

runs/Jul18_23-49-21_2365c9b6949f/events.out.tfevents.1689724406.2365c9b6949f.409.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b37550d0347c70b873eb6ca347a7d6ac6df9c94e1c789e439288e52a8c79e90
+size 7544

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fa62e3277e4ce87b53a931cde194cdabab0404467abee7a403c4b67044fda4
-size 4155
+oid sha256:e77a8da0008737b7bf0640dbcc1d85b1ad9149004cd5bed402a08271c5db85bc
+size 4219