Training complete

README.md

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
 tags:
+- summarization
 - generated_from_trainer
 datasets:
 - null
@@ -15,7 +16,7 @@ model-index:
     metrics:
     - name: Rouge1
       type: rouge
-      value: 10.8752
+      value: 12.4927
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -25,12 +26,12 @@ 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: 3.1491
-- Rouge1: 10.8752
-- Rouge2: 3.8695
-- Rougel: 10.6991
-- Rougelsum: 10.6616
-- Gen Len: 5.6085
+- Loss: 2.9894
+- Rouge1: 12.4927
+- Rouge2: 4.847
+- Rougel: 12.4387
+- Rougelsum: 12.4383
+- Gen Len: 6.1675
 
 ## Model description
 
@@ -49,29 +50,31 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 4e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 8
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| 9.1733        | 1.0   | 2202  | 3.4863          | 6.3629  | 1.4637 | 6.2501  | 6.2752    | 3.3302  |
-| 4.4547        | 2.0   | 4404  | 3.2809          | 9.1283  | 2.992  | 8.9851  | 9.0487    | 4.7642  |
-| 4.0581        | 3.0   | 6606  | 3.2108          | 10.5207 | 3.7411 | 10.2595 | 10.234    | 5.3208  |
-| 3.8821        | 4.0   | 8808  | 3.1701          | 10.8636 | 4.0944 | 10.6462 | 10.6468   | 5.2453  |
-| 3.7857        | 5.0   | 11010 | 3.1600          | 10.9456 | 4.5187 | 10.784  | 10.7542   | 5.691   |
-| 3.7273        | 6.0   | 13212 | 3.1491          | 10.8752 | 3.8695 | 10.6991 | 10.6616   | 5.6085  |
+| 6.5619        | 1.0   | 2202  | 3.2749          | 9.2423  | 3.2813 | 9.2013  | 9.1698    | 5.0354  |
+| 3.8525        | 2.0   | 4404  | 3.1296          | 11.1883 | 4.047  | 11.1545 | 11.1885   | 6.4033  |
+| 3.5419        | 3.0   | 6606  | 3.0478          | 11.4905 | 4.4465 | 11.3538 | 11.3805   | 6.6462  |
+| 3.4045        | 4.0   | 8808  | 3.0174          | 11.5798 | 4.4426 | 11.5372 | 11.571    | 6.6816  |
+| 3.3091        | 5.0   | 11010 | 3.0080          | 12.0207 | 4.5622 | 11.9232 | 11.9476   | 6.4976  |
+| 3.2457        | 6.0   | 13212 | 2.9981          | 12.2459 | 4.6924 | 12.2306 | 12.2375   | 6.1533  |
+| 3.2179        | 7.0   | 15414 | 2.9943          | 12.3927 | 4.6072 | 12.2888 | 12.2848   | 6.3561  |
+| 3.1898        | 8.0   | 17616 | 2.9894          | 12.4927 | 4.847  | 12.4387 | 12.4383   | 6.1675  |
 
 
 ### Framework versions
 
 - Transformers 4.10.3
-- Pytorch 1.9.1+cu102
+- Pytorch 1.9.1+cu111
 - Datasets 1.12.1
 - Tokenizers 0.10.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc1cebaa89d1bddeb41b5c3a2014bfc2d70cde4af9bb38ac8c5e578f61bcf22
+oid sha256:f0e675e00cd36206c8add82fb2725faaa4cadb2ebf15a60cfc984dbdae04abd3
 size 1200770885

runs/Sep29_14-23-20_vorace/1632918487.4283721/events.out.tfevents.1632918487.vorace.2673642.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a371d693df8c7de443878962b865d2c5d666bb8218d013ae6936ff06128fe65
+size 4434

runs/Sep29_14-23-20_vorace/events.out.tfevents.1632918487.vorace.2673642.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b328dbf4d725d49d47961f7ac961dfe9b710674373705b97556491239cdaf478
+size 3253

runs/Sep29_14-34-02_vorace/1632918914.4980953/events.out.tfevents.1632918914.vorace.2677037.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e61ea87cf71d6aea0fe0aa106bfb74fbe5493f1cba1f849860b3d0abdb62e7
+size 4434

runs/Sep29_14-34-02_vorace/events.out.tfevents.1632918892.vorace.2677037.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba8e0d8321230d4ad06b7397eedf35b2e4fbce322f9bf6fa3b80c267b3012a33
+size 488

runs/Sep29_14-34-02_vorace/events.out.tfevents.1632918914.vorace.2677037.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee23e12afafaa563b4869dc01790d1bbb34436b14000d6b085748d4a8ee4de
+size 8925

tokenizer_config.json

@@ -1 +1 @@
-{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/lewtun/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/data/.cache/hf/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c696d829fb994c3c16fe17700311c5b844cb2570a26fe27827c9598487fe10
-size 2735
+oid sha256:be2fdab9ad79e6ab4510ff0df9f9ea943c75e6872fc392dfa2aeca1e26a2e148
+size 2799