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:e1a33f4a9d586d1088d9c4518ad07fc2c9f8d0f692b86189fd1f5e13703cebdd
-size 990408885
+oid sha256:2c4524537d7721ded48d52b79e7aaad1272563e9194c26afb48e971c11016bb8
+size 307910149

runs/Jul18_23-42-20_2365c9b6949f/events.out.tfevents.1689723984.2365c9b6949f.409.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed80af5200773970f8ec144a58d25859c9426d1f14d1d9707498a063ecf9faf
+size 7501

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55da2227195ace6c94d9b8f6c8566af2eb7e93dfa7228fa20a3f73b35800d6c6
-size 4091
+oid sha256:34fae78500948cfbb8b88f119b2c348b40969f42406eea4451279f1ae3a0884c
+size 4219