Model save

README.md

@@ -1,8 +1,8 @@
 ---
+license: apache-2.0
+base_model: t5-small
 tags:
 - generated_from_trainer
-metrics:
-- rouge
 model-index:
 - name: t5-small-finetuned-feedback
   results: []
@@ -13,14 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # t5-small-finetuned-feedback
 
-This model was trained from scratch on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.6219
-- Rouge1: 50.8511
-- Rouge2: 26.8493
-- Rougel: 48.4905
-- Rougelsum: 48.5418
-- Gen Len: 10.0496
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 
 ## Model description
 
@@ -45,23 +38,14 @@ 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: 10
+- 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   | 61   | 2.1472          | 36.9176 | 16.7706 | 34.7237 | 34.8094   | 11.3802 |
-| No log        | 2.0   | 122  | 1.9311          | 45.014  | 22.0586 | 42.7869 | 42.7636   | 10.6694 |
-| No log        | 3.0   | 183  | 1.8201          | 49.8661 | 25.8069 | 47.7022 | 47.7394   | 10.3223 |
-| No log        | 4.0   | 244  | 1.7519          | 51.0514 | 27.3576 | 48.9062 | 48.9733   | 10.4132 |
-| No log        | 5.0   | 305  | 1.7028          | 51.377  | 27.9206 | 49.4673 | 49.4886   | 10.0992 |
-| No log        | 6.0   | 366  | 1.6731          | 50.702  | 27.4872 | 48.7413 | 48.7108   | 10.2066 |
-| No log        | 7.0   | 427  | 1.6496          | 50.8295 | 27.4685 | 48.8267 | 48.7703   | 10.0    |
-| No log        | 8.0   | 488  | 1.6334          | 50.7437 | 26.9485 | 48.4296 | 48.4472   | 10.0496 |
-| 2.0857        | 9.0   | 549  | 1.6239          | 50.7779 | 26.9387 | 48.5702 | 48.619    | 10.0331 |
-| 2.0857        | 10.0  | 610  | 1.6219          | 50.8511 | 26.8493 | 48.4905 | 48.5418   | 10.0496 |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 61   | 3.6183          | 23.4714 | 9.0363 | 20.5954 | 20.9234   | 17.6529 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "t5-small-finetuned-feedback",
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec6f2d5bc088d33dcf46c6c0642af32b41875e125e062d02b659c71bb6940c19
+oid sha256:71e2e75f6888eca9a56bed689f0345c32b0fd606e7c18ece00420e438d020e8f
 size 242041896

runs/May01_06-48-28_f2d32a93a370/events.out.tfevents.1714546109.f2d32a93a370.1748.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83fd3b6a1f4c3b00299e759c217ec602369a4eeab13d2b8f951c7c033897c1c2
+size 5688

runs/May01_08-16-33_f2d32a93a370/events.out.tfevents.1714551393.f2d32a93a370.37027.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a48709d0da69b9111d45a9996bc2a95d1893e29f3b78352e193fcda398ddca5
+size 6548

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e1c1eed3eca63eb423b3a83594a93393350a010e8d3774f161bf4c4e5acbe6
+oid sha256:998a825f8e1d6a5348b14bc50d0d875e7401482592a6f5cea9b00c6aee16ae4c
 size 5176