Training in progress, step 500

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 3072,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 768,
+  "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": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "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:f46146db04fb2a4de14aa2f0b0b6098e84e373004d5443fcbb75d99b465e5a54
-size 891702929
+oid sha256:c66d6e25c086b9b0e4d37fc74e1f42e7319865f53df7d568b52d51982295dd3e
+size 242071641

runs/Jun25_16-50-41_c2d8b183f84c/events.out.tfevents.1687711847.c2d8b183f84c.445.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003a9daa3826ab29f03507215845cf1b548b169d8a718b898d322df43a6054dd
+size 5033

runs/Jun25_16-53-30_c2d8b183f84c/events.out.tfevents.1687712016.c2d8b183f84c.445.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9504d51100a4b9502e8924beb91e842f153f8fb50ee10bc2970c085933bd971
+size 5190

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6190e0fa4aabae43ee4cb17dbe7371992c52fa1d78fddf38b3a989a1e8fc6fd6
+oid sha256:03859401e7125a9966fc020ad8146ae1defe78a3cd1ef62bd067926475f15da5
 size 4091