Training complete

README.md

@@ -16,14 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 20.2908
-- eval_rouge1: 2.7497
-- eval_rouge2: 0.7622
-- eval_rougeL: 2.5892
-- eval_rougeLsum: 2.6148
-- eval_runtime: 77.5672
-- eval_samples_per_second: 32.23
-- eval_steps_per_second: 4.035
+- eval_loss: 20.5681
+- eval_rouge1: 2.8676
+- eval_rouge2: 0.8599
+- eval_rougeL: 2.7183
+- eval_rougeLsum: 2.7447
+- eval_runtime: 80.5817
+- eval_samples_per_second: 31.024
+- eval_steps_per_second: 3.884
 - step: 0
 
 ## Model description

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a8cb386be4d5836ea5cb556fcc59cbccc2e406538125f36c41e89b65c5d82ea
+oid sha256:6269d929dadc1bdb739eb0b4b46eea4778d27e780b0c1aa5b2f89cfedea3bef1
 size 4399