Training in progress, step 500

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "RazinAleks/working",
+  "_name_or_path": "google/mt5-base",
   "architectures": [
     "MT5ForConditionalGeneration"
   ],
   "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": "mt5",
-  "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,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb552b98ce77b877d709d47149f2e846f2e5eaf879927a8281f116988f0ddbb
-size 1200772613
+oid sha256:e2ca6d2561d7c2deb19e574d655a10408dbe061ceafcc98d3791baf9fd99f2d8
+size 2329702581

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6502d07619068a98aa2d3bb531332a694ffe108ca6c6fe62a467ccfe98d666b9
-size 16315219
+oid sha256:faaa6405f5f79c9e788c7980874a9a3b5b0aea07b53bd9243bf1abb8f5c49c81
+size 16330467

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf9140b977dc411227766975c5d390856c3e0bbdb77a961f700ccd866a4177c
+oid sha256:1136933e6bf6ca3b53df15e2a6ec6fccb2c35c4b8954641f204a38e8ba3868b9
 size 4219