End of training

README.md

@@ -14,6 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
 # kp-umt5-base
 
 This model is a fine-tuned version of [google/umt5-base](https://huggingface.co/google/umt5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.3565
+- eval_bleu: 32.2656
+- eval_gen_len: 38.1913
+- eval_runtime: 293.3922
+- eval_samples_per_second: 10.225
+- eval_steps_per_second: 0.32
+- step: 0
 
 ## Model description
 

config.json

@@ -21,7 +21,7 @@
   "num_heads": 12,
   "num_layers": 12,
   "output_past": true,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "scalable_attention": true,

runs/Feb01_21-36-08_3d9368cb1b31/events.out.tfevents.1706823668.3d9368cb1b31.28085.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135ffc2ede0826d95e6e21e06de868c9bd7e1aad047bbfca8770b451bec686e4
+size 390

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b6460dfcb4b9bda01bafee5c3d56197ffa4f67b655745480cb52015c10f53c
+oid sha256:ce82f90493e61474e08e782ef23cc12cc5ef554ea7fa6fe77c12d8b5be5324e6
 size 4792