Training in progress, epoch 1

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google/mt5-base",
+  "_name_or_path": "google/mt5-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,
@@ -17,10 +17,9 @@
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,

logs/events.out.tfevents.1727601056.5a76963310a4.1310.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d7d5e270aacf59d906dbc3a7fa752277f7ddedf0010bc92de1d55825c90e29
+size 4184

logs/events.out.tfevents.1727601218.5a76963310a4.2696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2792a18b1ec898024c8e5c09c160ab517221588c0a1b1756736e64a6be34302e
+size 5922

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9619780674612f9308494ff5211b64db7ee3a672966977690217bab22a14a31
-size 2329638768
+oid sha256:7dd126d9cf1b35fbd97abfa2eb9f4c74d5d7465cd442be172b361d3ccc9d4d98
+size 1200729512