Training in progress, step 500

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google/flan-t5-xl",
+  "_name_or_path": "google/flan-t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 5120,
+  "d_ff": 1024,
   "d_kv": 64,
-  "d_model": 2048,
+  "d_model": 512,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 24,
-  "num_heads": 32,
-  "num_layers": 24,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495fa51e204676f1a857a9fc13c4c89f3f5ba9f480b898cebca02add25e6d749
+size 307867048

runs/Mar04_05-12-10_e4c303e51743/events.out.tfevents.1709529131.e4c303e51743.928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3c487ab3097661b3de082f84a9126fb779fbf0dc641f0ed91d5ad3e7b2ef82
+size 5547

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:310e53dfd78a1fe4b0d3c51c95547552769d0f3c3c4d1962adb96bcfbb34ae1a
+oid sha256:681111e142b5ab2ed831af1fd043db7695326d13d312a4243ddd62536369ac81
 size 4856