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: 0.7928
-- Rouge1: 62.0833
-- Rouge2: 47.0
-- Rougel: 62.0952
-- Rougelsum: 61.2857
-- Gen Len: 14.2
+- Loss: 0.6312
+- Rouge1: 61.4286
+- Rouge2: 43.0
+- Rougel: 61.619
+- Rougelsum: 60.4762
+- Gen Len: 15.3
 
 ## Model description
 
@@ -51,18 +51,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 5    | 1.0434          | 55.9048 | 39.0   | 55.9048 | 55.7143   | 13.2    |
-| No log        | 2.0   | 10   | 0.9903          | 62.7619 | 47.0   | 62.6667 | 62.7619   | 14.8    |
-| No log        | 3.0   | 15   | 0.9273          | 56.4762 | 47.0   | 56.4762 | 56.1905   | 14.4    |
-| No log        | 4.0   | 20   | 0.9185          | 60.4762 | 47.0   | 60.4762 | 59.8095   | 13.5    |
-| No log        | 5.0   | 25   | 0.8703          | 64.5714 | 47.0   | 64.4762 | 64.4762   | 13.2    |
-| No log        | 6.0   | 30   | 0.8186          | 68.1429 | 50.0   | 68.5714 | 68.0238   | 14.6    |
-| No log        | 7.0   | 35   | 0.7856          | 64.7857 | 50.0   | 64.5714 | 64.0952   | 14.4    |
-| No log        | 8.0   | 40   | 0.7755          | 64.7857 | 50.0   | 64.5714 | 64.0952   | 14.2    |
-| No log        | 9.0   | 45   | 0.7864          | 64.7857 | 50.0   | 64.5714 | 64.0952   | 14.2    |
-| No log        | 10.0  | 50   | 0.7928          | 62.0833 | 47.0   | 62.0952 | 61.2857   | 14.2    |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 5    | 2.4435          | 17.3333 | 10.0    | 16.6667 | 16.6667   | 8.4     |
+| No log        | 2.0   | 10   | 1.7069          | 21.6364 | 10.0    | 20.3896 | 20.1039   | 8.7     |
+| No log        | 3.0   | 15   | 1.3074          | 30.5714 | 16.6667 | 26.5    | 26.5357   | 10.2    |
+| No log        | 4.0   | 20   | 1.0233          | 38.2857 | 22.381  | 38.0    | 37.7143   | 12.8    |
+| No log        | 5.0   | 25   | 0.8584          | 52.1905 | 35.7143 | 52.381  | 51.3452   | 13.9    |
+| No log        | 6.0   | 30   | 0.7716          | 55.2381 | 35.7143 | 55.2381 | 54.7619   | 14.6    |
+| No log        | 7.0   | 35   | 0.6936          | 55.2381 | 35.7143 | 55.2381 | 54.7619   | 15.9    |
+| No log        | 8.0   | 40   | 0.6447          | 61.4286 | 43.0    | 61.619  | 60.4762   | 15.1    |
+| No log        | 9.0   | 45   | 0.6323          | 61.4286 | 43.0    | 61.619  | 60.4762   | 15.3    |
+| No log        | 10.0  | 50   | 0.6312          | 61.4286 | 43.0    | 61.619  | 60.4762   | 15.3    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f99809e2d8febc661302df9ea87076d2e30e0ee609367643d57d2aec7679da
+oid sha256:8cdd200e51baf3e8d2f4fcf3b24595ce7d69af2ccbdd0a25af53568995c52812
 size 307867048

runs/Dec06_15-55-07_71a67548b374/events.out.tfevents.1701878129.71a67548b374.2291.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600d29ae25a420110060e125fe705045cbcc18b2458d97914d66f9566db8c824
+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_config.json

@@ -930,16 +930,9 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "max_length": 48,
   "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 sha256:2e6f79856928c7cafbd0d91f85bac2898e498cda748266dbeb800c555bb3eea8
-size 4792
+oid sha256:d563a3cd63731545bdfa9c442bbd37e96a9732f1cf48361393b998e65fbd64ff
+size 4728