Training in progress, step 500

config.json

@@ -16,6 +16,9 @@
   "is_encoder_decoder": true,
   "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
+  "length_penalty": 1.2,
+  "max_length": 256,
+  "min_length": 50,
   "model_type": "t5",
   "n_positions": 512,
   "num_decoder_layers": 6,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8477ffccb2f65584a9828bdec314cb25a5bf011f9e701c5cc16856e59b87da
+oid sha256:b0f1dd5713705d931b43fe247dc2b3def522cfb01b634e007ee2af21ac143f8f
 size 242041896

runs/Feb05_12-25-02_1a6303fd8b33/events.out.tfevents.1707135909.1a6303fd8b33.317.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52796fca7b55ffebee13913ac303f14cc9c23c92c19569f30b75409ccf865312
+size 5475

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe4694096308948f08cd77aca734d8d7994a2c552021943ac056897f002fe03
+oid sha256:3caa355e9a6cdcd3592482c7fb1cbf957b126d3d6bfe124593a705b71b47a3d0
 size 4728