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: 14.5641
-- eval_rouge1: 0.8652
-- eval_rouge2: 0.0
-- eval_rougeL: 0.8652
-- eval_rougeLsum: 0.871
-- eval_runtime: 1.7103
-- eval_samples_per_second: 16.956
-- eval_steps_per_second: 2.339
+- eval_loss: 24.6430
+- eval_rouge1: 1.3112
+- eval_rouge2: 0.0339
+- eval_rougeL: 1.2102
+- eval_rougeLsum: 1.201
+- eval_runtime: 51.8577
+- eval_samples_per_second: 19.284
+- eval_steps_per_second: 2.41
 - step: 0
 
 ## Model description

runs/Jan22_14-58-02_0384111a60f2/events.out.tfevents.1705935561.0384111a60f2.3956.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f406aa0c47190b6afa7ba570be9e6d9642e792a06859b0b9d6969936a252c243
+size 488

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03fc67f7ec61eb4ba5a9cd2c82a7038f625dadcd88445c044cec3220d529ec97
+oid sha256:8b76e6bfbdc32c658a35c862ea5fca56aaaa4bcd38d12402373cce14d8d78c4e
 size 4856