Training in progress, step 500

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "google/mt5-small",
+  "_name_or_path": "frt5-base",
   "architectures": [
-    "MT5ForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 1024,
@@ -16,7 +16,7 @@
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
-  "model_type": "mt5",
+  "model_type": "t5",
   "num_decoder_layers": 8,
   "num_heads": 6,
   "num_layers": 8,
@@ -28,5 +28,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": true,
-  "vocab_size": 250112
+  "vocab_size": 10666
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29242a71fe19387f924b4a5da15a073c9b9fce424df18edc7aaf84c492316604
-size 1200729512
+oid sha256:463198ac43bc776ec376aa9a0124ab220e44e70a7bb8a4e26a9ab10acd905ce6
+size 219958696

runs/Mar16_22-20-15_5d4177ac2335/events.out.tfevents.1710627615.5d4177ac2335.11191.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90062438be22a724a8f33efa767340e752286c58c721db858b24caad12ddb026
+size 4840

runs/Mar16_22-20-56_5d4177ac2335/events.out.tfevents.1710627657.5d4177ac2335.11191.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac35e5d08fedd26e7d3054144d98a0b5d0651270ddff2c69ba7a8099d34badd
+size 5053

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
-size 4309802
+oid sha256:353d57e9d6e540b17f88d54025ea29a774aa4cfa953381fdeb0dd1e4dd7c2859
+size 426213

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c0f683ba7f00dc51ae6a2bcdbe6a34db570f0af328561c788b9a0d1aff1d8e
+oid sha256:3918e19caec8a47fc0af352020526af4be5783331f1e127eb09fdc9ae45e74a3
 size 5048