Training in progress, epoch 1

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "north/t5_small_NCC_lm",
+  "_name_or_path": "north/t5_large_NCC_lm",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 1024,
+  "d_ff": 2816,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -16,9 +16,10 @@
   "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": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "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:f388a5feaed0292cd9796a514b6a7dd8ce37fbcfaaee1efeea95973e4ab969ae
-size 1200772613
+oid sha256:f3b99de59bc42154fa9262578d498e77bf5e5e99778ffccb4b7208782fcde4b0
+size 4918519193

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6502d07619068a98aa2d3bb531332a694ffe108ca6c6fe62a467ccfe98d666b9
-size 16315219
+oid sha256:99cc999819aaabf74898a252863b10d86fbcd86e8b3f65c118ff334ff85c5ea5
+size 16315121

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e64c6a1dcca431f04d9138eca74c63fbdd031fcbc194258a175c1bacab06c69
+oid sha256:ac5595fa40d737be5fe38cca01d867b66220cfc226bd51078fe9417369ffd7a5
 size 3707