End of training

README.md

@@ -19,12 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [muchad/idt5-base](https://huggingface.co/muchad/idt5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7027
-- Rouge1: 0.4239
-- Rouge2: 0.2060
-- Rougel: 0.3971
-- Rougelsum: 0.3972
-- Bleu: 0.1464
+- Loss: 1.7050
+- Rouge1: 0.4251
+- Rouge2: 0.2075
+- Rougel: 0.3983
+- Rougelsum: 0.3984
+- Bleu: 0.1471
 
 ## Model description
 
@@ -55,11 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu   |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|
-| 2.4175        | 1.0   | 7645  | 1.8247          | 0.3744 | 0.1658 | 0.3462 | 0.3463    | 0.1167 |
-| 2.2718        | 2.0   | 15290 | 1.7606          | 0.4119 | 0.1957 | 0.3842 | 0.3843    | 0.1393 |
-| 2.2144        | 3.0   | 22935 | 1.7280          | 0.4211 | 0.2042 | 0.3939 | 0.3940    | 0.1450 |
-| 2.1661        | 4.0   | 30580 | 1.7066          | 0.4221 | 0.2050 | 0.3955 | 0.3956    | 0.1452 |
-| 2.1563        | 5.0   | 38225 | 1.7027          | 0.4239 | 0.2060 | 0.3971 | 0.3972    | 0.1464 |
+| 2.4083        | 1.0   | 7645  | 1.8277          | 0.3795 | 0.1682 | 0.3512 | 0.3512    | 0.1180 |
+| 2.2612        | 2.0   | 15290 | 1.7645          | 0.4158 | 0.1983 | 0.3882 | 0.3884    | 0.1400 |
+| 2.2144        | 3.0   | 22935 | 1.7297          | 0.4230 | 0.2058 | 0.3963 | 0.3965    | 0.1453 |
+| 2.1663        | 4.0   | 30580 | 1.7051          | 0.4232 | 0.2064 | 0.3970 | 0.3971    | 0.1461 |
+| 2.1538        | 5.0   | 38225 | 1.7050          | 0.4251 | 0.2075 | 0.3983 | 0.3984    | 0.1471 |
 
 
 ### Framework versions

adapter_config.json

@@ -16,7 +16,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dcd9dad8c369542a3f1b02ca2a34cec8d39ded7de06757d54f873a42107fc5d
-size 28331904
+oid sha256:11beb159f57a2952dc4d2d7c5a7eb5c23f9a6eea2ee5fcc82c27ac9ebf63109c
+size 3558888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:249271d15f9918e19acead2f2765838e4e4860743b7d117b113538a148549988
+oid sha256:cf61eaf6018902aabcfee7f0911d37f6a1981317f4d33b468cca7aac979e05a9
 size 5368