End of training

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1443
-- Rouge1: 27.8954
-- Rouge2: 7.9325
-- Rougel: 27.8954
-- Rougelsum: 27.0723
-- Gen Len: 12.5
+- Loss: 1.1056
+- Rouge1: 59.8095
+- Rouge2: 47.0
+- Rougel: 59.8095
+- Rougelsum: 59.8095
+- Gen Len: 14.6
 
 ## Model description
 
@@ -53,16 +53,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 3    | 2.8565          | 15.4762 | 2.439  | 15.0794 | 15.4762   | 16.1667 |
-| No log        | 2.0   | 6    | 2.5544          | 13.0291 | 2.439  | 12.6323 | 13.0291   | 16.1667 |
-| No log        | 3.0   | 9    | 2.4527          | 14.6825 | 2.439  | 14.2857 | 14.2857   | 10.8333 |
-| No log        | 4.0   | 12   | 2.3570          | 20.2381 | 2.439  | 19.8413 | 19.8413   | 11.1667 |
-| No log        | 5.0   | 15   | 2.2745          | 27.1017 | 7.9325 | 27.1017 | 26.2787   | 11.3333 |
-| No log        | 6.0   | 18   | 2.2170          | 27.8954 | 7.9325 | 27.8954 | 27.0723   | 13.1667 |
-| No log        | 7.0   | 21   | 2.1860          | 27.8954 | 7.9325 | 27.8954 | 27.0723   | 12.6667 |
-| No log        | 8.0   | 24   | 2.1568          | 27.8954 | 7.9325 | 27.8954 | 27.0723   | 12.5    |
-| No log        | 9.0   | 27   | 2.1445          | 27.8954 | 7.9325 | 27.8954 | 27.0723   | 12.5    |
-| No log        | 10.0  | 30   | 2.1443          | 27.8954 | 7.9325 | 27.8954 | 27.0723   | 12.5    |
+| No log        | 1.0   | 5    | 2.8921          | 15.7143 | 0.0    | 15.7143 | 15.0      | 7.2     |
+| No log        | 2.0   | 10   | 2.1172          | 19.0    | 0.0    | 19.1905 | 18.5714   | 8.2     |
+| No log        | 3.0   | 15   | 1.7513          | 33.7143 | 20.0   | 34.0    | 33.3333   | 7.8     |
+| No log        | 4.0   | 20   | 1.4905          | 46.7143 | 34.0   | 47.0476 | 46.7143   | 12.3    |
+| No log        | 5.0   | 25   | 1.3527          | 55.5714 | 39.0   | 55.4762 | 54.5714   | 12.9    |
+| No log        | 6.0   | 30   | 1.3376          | 58.0952 | 39.0   | 58.0952 | 57.4286   | 13.6    |
+| No log        | 7.0   | 35   | 1.2002          | 58.5714 | 39.0   | 58.5714 | 57.8095   | 13.3    |
+| No log        | 8.0   | 40   | 1.1349          | 55.0476 | 39.0   | 54.5714 | 54.5714   | 14.3    |
+| No log        | 9.0   | 45   | 1.1106          | 59.8095 | 47.0   | 59.8095 | 59.8095   | 14.6    |
+| No log        | 10.0  | 50   | 1.1056          | 59.8095 | 47.0   | 59.8095 | 59.8095   | 14.6    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4367079d068ae4a90dad689e370cea4267c9bd0aaf158078596d1a469e3e9783
+oid sha256:7a4e757066a16cbdea075ad0690a8bb8b2c067cfbda800feed03940145b544cf
 size 307867048

runs/Dec06_09-23-29_7bb9bb6007a1/events.out.tfevents.1701854615.7bb9bb6007a1.626.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2e817a71d1ec137accda5d5af51868878999409243928f6378c4d750deeb47
+size 10789

special_tokens_map.json

@@ -101,25 +101,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 48,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 48
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -930,16 +930,9 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "max_length": 134,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a161e0b6388ab1227fa88a6277b82c5f6d8ec1d1f75a018734741917d9db803
+oid sha256:2e6f79856928c7cafbd0d91f85bac2898e498cda748266dbeb800c555bb3eea8
 size 4792