Training complete

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Rouge1
       type: rouge
-      value: 6.6836
+      value: 7.724
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,11 +33,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the scientific_papers dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3907
-- Rouge1: 6.6836
-- Rouge2: 2.1098
-- Rougel: 5.9425
-- Rougelsum: 6.2054
+- Loss: 3.2193
+- Rouge1: 7.724
+- Rouge2: 2.4363
+- Rougel: 6.5816
+- Rougelsum: 7.1778
 
 ## Model description
 
@@ -57,30 +57,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5.6e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 9
+- eval_batch_size: 9
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 3.3325        | 1.0   | 12   | 3.5225          | 6.9207 | 2.3311 | 6.028  | 6.4698    |
-| 3.3103        | 2.0   | 24   | 3.4962          | 6.9034 | 2.2066 | 6.0665 | 6.4077    |
-| 3.2897        | 3.0   | 36   | 3.4641          | 7.0201 | 2.2613 | 6.062  | 6.5273    |
-| 3.2407        | 4.0   | 48   | 3.4282          | 6.4635 | 2.1254 | 5.7649 | 6.0343    |
-| 3.2215        | 5.0   | 60   | 3.4146          | 6.4631 | 2.1677 | 5.7642 | 6.0335    |
-| 3.2053        | 6.0   | 72   | 3.3985          | 6.5894 | 1.8804 | 5.8527 | 6.1158    |
-| 3.2009        | 7.0   | 84   | 3.3924          | 6.5894 | 1.8804 | 5.8527 | 6.1158    |
-| 3.1939        | 8.0   | 96   | 3.3907          | 6.6836 | 2.1098 | 5.9425 | 6.2054    |
+| 7.4171        | 1.0   | 56   | 5.4323          | 6.503  | 1.9358 | 5.4592 | 5.9976    |
+| 4.4771        | 2.0   | 112  | 3.8285          | 6.8941 | 2.2332 | 5.8067 | 6.3885    |
+| 3.7139        | 3.0   | 168  | 3.4540          | 7.6879 | 2.3106 | 6.4302 | 7.1194    |
+| 3.517         | 4.0   | 224  | 3.3068          | 7.7419 | 2.521  | 6.6036 | 7.1943    |
+| 3.4113        | 5.0   | 280  | 3.2193          | 7.724  | 2.4363 | 6.5816 | 7.1778    |
 
 
 ### Framework versions
 
-- Transformers 4.41.0
+- Transformers 4.41.1
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -55,7 +55,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.41.0",
+  "transformers_version": "4.41.1",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.41.0"
+  "transformers_version": "4.41.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1bfd6fe3159c97c4da2637657ee57ad8d9c64ce711b3d44d882b0f31207aa90
+oid sha256:d27cb4852bd9427a6a44a0d3ed48fff6a04e826d5116957a5335814fa7ef018f
 size 242041896

runs/May29_01-16-16_dc21b5969f4b/events.out.tfevents.1716945415.dc21b5969f4b.546.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080eb08c1354f087a7a9a084e446f4482aafba555d420c33b230ff414a00eaa0
+size 11674

runs/May29_01-26-42_dc21b5969f4b/events.out.tfevents.1716946010.dc21b5969f4b.546.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dfc13665d128792f8e8ee3c0b16455831b28010d8e59ef0f648507a76285ece
+size 9649

runs/May29_01-39-02_dc21b5969f4b/events.out.tfevents.1716946757.dc21b5969f4b.546.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c49fdd485d2b63602ca6b8edd3203ed7377a7139e6217c66be6c7b3a49600c2
+size 17518

runs/May29_01-44-15_dc21b5969f4b/events.out.tfevents.1716947060.dc21b5969f4b.546.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8036c76cf158d6213c242fe15f29db05a468575a2eee53f5d413bb43a0747846
+size 5896

runs/May29_01-50-31_dc21b5969f4b/events.out.tfevents.1716947451.dc21b5969f4b.9928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8cedeed262ca21c99bbc2f53d6762d60d3376b6615dcc46c671e9c37bd4ed7
+size 5870

runs/May29_01-51-34_dc21b5969f4b/events.out.tfevents.1716947509.dc21b5969f4b.9928.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ea9a5fd2e3f359f97905f4108f2721c8453a515fa4aad6f7d3067f72a999ea
+size 5868

runs/May29_01-57-53_dc21b5969f4b/events.out.tfevents.1716947885.dc21b5969f4b.12033.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e5e18d2504836c1d94a8b98f9996caeb56efb4efe941434cab3da075be790c
+size 9621

runs/May29_01-57-53_dc21b5969f4b/events.out.tfevents.1716948231.dc21b5969f4b.12033.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82b40e531830781e7229d72cc016c04b63123e91274fe68d0d8a91eddbc36ae
+size 562

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8810d98a6e71ec71d097ed2501aee57ccbe1d1e73b0b5e64b4b816e8c6d6ac
+oid sha256:6cbb23c96b61b86798f854e018d06801bbfb8c5d73bc276bc377f86daf9324e0
 size 5304