Training in progress, step 500

config.json

@@ -16,11 +16,7 @@
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
-  "length_penalty": 0.6,
-  "max_length": 128,
   "model_type": "mt5",
-  "no_repeat_ngram_size": 2,
-  "num_beams": 15,
   "num_decoder_layers": 8,
   "num_heads": 6,
   "num_layers": 8,

runs/May03_11-38-51_DESKTOP-2U4BJQD/events.out.tfevents.1714725588.DESKTOP-2U4BJQD.13460.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da86a7ff115ff23f5ede4e86b7c916e1fc603f676d48e6b3a7a061121d73934d
+size 4887

tensorboard/logs/events.out.tfevents.1714725531.DESKTOP-2U4BJQD.13460.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c709b69e903e518b5b521cb2f1238aaf4986f01ba6f65208101baffaccf9a503
+size 88

tensorboard/logs/events.out.tfevents.1714725587.DESKTOP-2U4BJQD.13460.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe28a31e4d4cc32cbbff098e69410ba1ebc7794e0798300878f7abe671654636
+size 88

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d73615d2096feac46adb3a7bda379197623f53931ceabbfe674bafb4e6b8b20
+oid sha256:3365dc4eecbc0e95c521c40c0f18786be528f6251fb43936120515ed4d1d7f18
 size 5112