Training in progress, epoch 4

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "google/flan-t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "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,
@@ -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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
   "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 sha256:8a92cb6d025ef379ca8c09effc1143f94a1abdab6697fabb4f359fb833c09508
-size 990345064
+oid sha256:570007a1dc39c0adeef5077674c452d082a28f16af699fe9ebdf3dd68ab8256d
+size 307867048

runs/Feb27_15-42-50_16b108c97436/events.out.tfevents.1709048570.16b108c97436.26153.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c3e3c12aa7dfbd4d4f4418553e62a092f831c7c414bee2872debd57cf7b4d73
+size 45116

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e395a5ff8c42e15da705d7fce7e6e5932adcb614f9145744b818aca97db4151
+oid sha256:565b0ff54b43587c630ff64b0a39e2c3e1b4bf64941fe6c4a492fd9df6dc9d54
 size 5048