Training in progress, epoch 1

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google/mt5-small",
+  "_name_or_path": "google/mt5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 1024,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -17,9 +17,10 @@
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
-  "num_decoder_layers": 8,
-  "num_heads": 6,
-  "num_layers": 8,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,

logs/events.out.tfevents.1728145202.b035966b8ee0.1106.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2942332dc608586e4c49d45a28551d291d8d3d5d114b758687b93e3bcaced1c
+size 5181

logs/events.out.tfevents.1728145765.b035966b8ee0.4495.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da90b4639a98cdee8d5ecd008a9ac19482a3fdc36a85e75b42a3465da11d6468
+size 5947

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:508158867d92f70b67ecdc55c85a17aa9c896a6c8508724895f38933b2b201e3
-size 1200729512
+oid sha256:cc11d16867b79d38aa40fedd123e63b046c0fe9a112a7e88f464fcf11213009a
+size 2329638768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cca3fca94145ea96e98fcb5bdc2816da830c6611ee29803b148a28ab2c167a9
+oid sha256:6781b0dafe79329b592bf7db20d75bcdcbf9fad9806cb96a36c9b242bdf7c86e
 size 5304