Model save

README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: t5-small
 tags:
 - generated_from_trainer
 metrics:
@@ -15,14 +13,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # denoice-finetuned-xsum
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7794
-- Rouge1: 71.0141
-- Rouge2: 53.0457
-- Rougel: 71.0918
-- Rougelsum: 71.0572
-- Gen Len: 16.5681
+- Loss: 0.7176
+- Rouge1: 72.4979
+- Rouge2: 55.09
+- Rougel: 72.5668
+- Rougelsum: 72.5151
+- Gen Len: 16.5209
 
 ## Model description
 
@@ -47,17 +45,15 @@ 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: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 76   | 0.8037          | 70.2689 | 52.2689 | 70.2756 | 70.2269   | 16.5707 |
-| No log        | 2.0   | 152  | 0.7922          | 70.7975 | 52.7278 | 70.8142 | 70.8439   | 16.5576 |
-| No log        | 3.0   | 228  | 0.7846          | 70.8221 | 52.6361 | 70.9459 | 70.8784   | 16.5314 |
-| No log        | 4.0   | 304  | 0.7805          | 71.0252 | 53.0551 | 71.0992 | 71.0725   | 16.5576 |
-| No log        | 5.0   | 380  | 0.7794          | 71.0141 | 53.0457 | 71.0918 | 71.0572   | 16.5681 |
+| No log        | 1.0   | 76   | 0.7237          | 72.7109 | 55.346  | 72.7556 | 72.7163   | 16.4921 |
+| No log        | 2.0   | 152  | 0.7188          | 72.4823 | 55.1403 | 72.5559 | 72.5034   | 16.5288 |
+| No log        | 3.0   | 228  | 0.7176          | 72.4979 | 55.09   | 72.5668 | 72.5151   | 16.5209 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "./denoice-en-decoder.pt/",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -54,7 +54,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.36.2",
   "use_cache": true,
   "vocab_size": 32128

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d5275952f252ade0dc40af67210bf2ab984ef5084b8bb994cb41b03336f7e6
-size 121028528
+oid sha256:54b5baccce3239cc39ad3f8f999d8c4808ccc068d59add918292a0312a0b9439
+size 242041896

tokenizer.json

@@ -2,12 +2,14 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 20,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
-    "strategy": "BatchLongest",
+    "strategy": {
+      "Fixed": 20
+    },
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae791766be47cce07d2ca7d0d9f1606c27b3feded8f1d4b33d89bd37e39fe22a
+oid sha256:96ffdaa01be2f0027d1bc2d3fe8a7909e7cd78dfac347001e4746cd37ac857b3
 size 4411