Training complete

README.md

@@ -18,11 +18,11 @@ 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 18.8001
-- Rouge1: 3.8595
-- Rouge2: 0.1818
-- Rougel: 3.7365
-- Rougelsum: 3.8153
+- Loss: 18.5420
+- Rouge1: 5.4719
+- Rouge2: 1.348
+- Rougel: 4.9456
+- Rougelsum: 4.9853
 
 ## Model description
 
@@ -53,14 +53,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 31.5627       | 1.0   | 10   | 24.0916         | 3.7836 | 0.2995 | 3.7121 | 3.8524    |
-| 28.0542       | 2.0   | 20   | 22.2574         | 3.8804 | 0.1818 | 3.7308 | 3.9019    |
-| 26.3796       | 3.0   | 30   | 20.8777         | 3.8768 | 0.1818 | 3.7551 | 3.8953    |
-| 24.3508       | 4.0   | 40   | 20.0165         | 3.8613 | 0.1818 | 3.7448 | 3.9015    |
-| 23.6133       | 5.0   | 50   | 19.5434         | 3.8899 | 0.1818 | 3.7532 | 3.8538    |
-| 22.8281       | 6.0   | 60   | 19.0390         | 3.8639 | 0.1818 | 3.7076 | 3.9124    |
-| 22.4095       | 7.0   | 70   | 18.8079         | 3.8884 | 0.1818 | 3.7607 | 3.9093    |
-| 22.5243       | 8.0   | 80   | 18.8001         | 3.8483 | 0.1818 | 3.7517 | 3.8898    |
+| 31.6413       | 1.0   | 10   | 24.0170         | 3.8323 | 0.2047 | 3.7904 | 3.8284    |
+| 27.8266       | 2.0   | 20   | 23.3707         | 3.1294 | 0.2047 | 3.1291 | 3.1228    |
+| 26.1653       | 3.0   | 30   | 22.3135         | 3.4676 | 0.3738 | 3.4903 | 3.4927    |
+| 24.5148       | 4.0   | 40   | 21.0853         | 3.9753 | 0.7238 | 3.8535 | 3.7906    |
+| 24.3813       | 5.0   | 50   | 20.0264         | 4.4993 | 0.9797 | 4.2104 | 4.1768    |
+| 23.2283       | 6.0   | 60   | 19.1784         | 5.1955 | 1.1276 | 4.8347 | 4.8356    |
+| 23.186        | 7.0   | 70   | 18.7094         | 5.3472 | 1.2564 | 4.787  | 4.8648    |
+| 22.0852       | 8.0   | 80   | 18.5420         | 5.5064 | 1.3106 | 4.907  | 4.9318    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ea5165bc013bf5645d1b011cc24a20883d78788f2ede838061321b8721f32d
+oid sha256:a2c5f84e63dae5282a3b6c465fcf37e0afc04d79223dc83ceac8206757d25c2d
 size 1200729512

runs/Apr23_16-04-44_c4ea92c1ff40/events.out.tfevents.1713888319.c4ea92c1ff40.52352.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c9cd766da8b79701bbc940d3718092c2af2660a6e7b23bee9271cf67934c1e
+size 10676

runs/Apr23_16-04-44_c4ea92c1ff40/events.out.tfevents.1713888363.c4ea92c1ff40.52352.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3011cc8f23f6df26e89263875f055beb6a6103f4e3f8326804b317988766bd2f
+size 553

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ec675358641fa866e054d4a50c3b8a7737c77b0014e8dd85a9ef901b238c3f
+oid sha256:5c7b0d0d7b8b1d4795cbdea25e42304ffe58cdc5701756d0944d5c8894d58d8c
 size 5112