Training in progress, step 500

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "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,
@@ -18,9 +18,9 @@
   "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,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:452d3f5f014a83ff97ce2ab23a6fc943eebe84f39914eddb7f194d93af975c34
-size 891644712
+oid sha256:118759dcde8446ddca23ab2483c974666decb793efb6a4164690a429f3e9a7c0
+size 242041896

runs/Nov28_02-07-42_6dd5a0142e44/events.out.tfevents.1701137263.6dd5a0142e44.2636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c2fbbb07f5ad6ae1d5b801c8ba79a2f9ddb765a42be99ee598b03dcd8499346
+size 5392

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7cc54f5390376b4ce2ebec7698cb73a52e1e32c7d453b7e34cd1f26141e0e9f
+oid sha256:a84283cc704121751387da0e8d24584b89477897940f1f97b74e8854e83b971c
 size 4728