End of training

README.md

@@ -2,8 +2,6 @@
 base_model: csebuetnlp/mT5_multilingual_XLSum
 tags:
 - generated_from_trainer
-metrics:
-- rouge
 model-index:
 - name: mT5_multilingual_XLSum-finetuned-wiki-lingua
   results: []
@@ -15,13 +13,6 @@ should probably proofread and complete it, then remove this comment. -->
 # mT5_multilingual_XLSum-finetuned-wiki-lingua
 
 This model is a fine-tuned version of [csebuetnlp/mT5_multilingual_XLSum](https://huggingface.co/csebuetnlp/mT5_multilingual_XLSum) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: nan
-- Rouge1: 0.0
-- Rouge2: 0.0
-- Rougel: 0.0
-- Rougelsum: 0.0
-- Gen Len: 83.0
 
 ## Model description
 
@@ -46,18 +37,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 160  | 3.5827          | 13.3527 | 3.7474 | 10.2363 | 12.3399   | 29.4615 |
-| No log        | 2.0   | 320  | 3.5827          | 13.3637 | 3.7687 | 10.2693 | 12.3497   | 29.3223 |
-| No log        | 3.0   | 480  | nan             | 0.0     | 0.0    | 0.0     | 0.0       | 83.0    |
-| 3.9813        | 4.0   | 640  | nan             | 0.0     | 0.0    | 0.0     | 0.0       | 83.0    |
-| 3.9813        | 5.0   | 800  | nan             | 0.0     | 0.0    | 0.0     | 0.0       | 83.0    |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
+| No log        | 1.0   | 160  | 3.6384          | 11.8921 | 3.1437 | 9.029  | 10.7853   | 28.4615 |
 
 
 ### Framework versions

generation_config.json

@@ -1,6 +1,10 @@
 {
-  "do_sample": true,
+  "decoder_start_token_id": 0,
   "eos_token_id": 1,
-  "max_new_tokens": 50,
+  "length_penalty": 0.6,
+  "max_length": 84,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "pad_token_id": 0,
   "transformers_version": "4.40.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ca2a1c31c01f7f5847cc44ac97ab8aca5ad3c907d799fbe90bb5c45392a5f8
+oid sha256:d72e54f189c8c935d74005b2807a7669f2da43136648bd3ea7265fd6df1a3b20
 size 2329638768

runs/May12_09-39-07_36723006b0fb/events.out.tfevents.1715506779.36723006b0fb.4735.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac5bf3b9d4ffb8740dbce34cee64a849c5f50c0cbac0a2f1da210c200026e512
+size 6048

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ec7ac09e74719df0d7ac26684f6bb9939553133a2b7916d91c08ff9d959a2f
+oid sha256:573929f8d971fbe24f97f5e5dfb47d7e6e7f9ba43ae8dd35b424d61767660c6f
 size 16330638

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f624d65cdcfa4673f05a14d38feccb6f96f5857b4da6e7e2f1bd21c182fbdc5f
+oid sha256:f7f7234b6dee15832fee763229852c4ef24c8ba092470c7cefce39b025c030e8
 size 5176