maxadmin commited on
Commit
7e9d656
1 Parent(s): 1e03501

End of training

Browse files
README.md CHANGED
@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.1056
21
- - Rouge1: 59.8095
22
  - Rouge2: 47.0
23
- - Rougel: 59.8095
24
- - Rougelsum: 59.8095
25
- - Gen Len: 14.6
26
 
27
  ## Model description
28
 
@@ -53,16 +53,16 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
56
- | No log | 1.0 | 5 | 2.8921 | 15.7143 | 0.0 | 15.7143 | 15.0 | 7.2 |
57
- | No log | 2.0 | 10 | 2.1172 | 19.0 | 0.0 | 19.1905 | 18.5714 | 8.2 |
58
- | No log | 3.0 | 15 | 1.7513 | 33.7143 | 20.0 | 34.0 | 33.3333 | 7.8 |
59
- | No log | 4.0 | 20 | 1.4905 | 46.7143 | 34.0 | 47.0476 | 46.7143 | 12.3 |
60
- | No log | 5.0 | 25 | 1.3527 | 55.5714 | 39.0 | 55.4762 | 54.5714 | 12.9 |
61
- | No log | 6.0 | 30 | 1.3376 | 58.0952 | 39.0 | 58.0952 | 57.4286 | 13.6 |
62
- | No log | 7.0 | 35 | 1.2002 | 58.5714 | 39.0 | 58.5714 | 57.8095 | 13.3 |
63
- | No log | 8.0 | 40 | 1.1349 | 55.0476 | 39.0 | 54.5714 | 54.5714 | 14.3 |
64
- | No log | 9.0 | 45 | 1.1106 | 59.8095 | 47.0 | 59.8095 | 59.8095 | 14.6 |
65
- | No log | 10.0 | 50 | 1.1056 | 59.8095 | 47.0 | 59.8095 | 59.8095 | 14.6 |
66
 
67
 
68
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7928
21
+ - Rouge1: 62.0833
22
  - Rouge2: 47.0
23
+ - Rougel: 62.0952
24
+ - Rougelsum: 61.2857
25
+ - Gen Len: 14.2
26
 
27
  ## Model description
28
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
56
+ | No log | 1.0 | 5 | 1.0434 | 55.9048 | 39.0 | 55.9048 | 55.7143 | 13.2 |
57
+ | No log | 2.0 | 10 | 0.9903 | 62.7619 | 47.0 | 62.6667 | 62.7619 | 14.8 |
58
+ | No log | 3.0 | 15 | 0.9273 | 56.4762 | 47.0 | 56.4762 | 56.1905 | 14.4 |
59
+ | No log | 4.0 | 20 | 0.9185 | 60.4762 | 47.0 | 60.4762 | 59.8095 | 13.5 |
60
+ | No log | 5.0 | 25 | 0.8703 | 64.5714 | 47.0 | 64.4762 | 64.4762 | 13.2 |
61
+ | No log | 6.0 | 30 | 0.8186 | 68.1429 | 50.0 | 68.5714 | 68.0238 | 14.6 |
62
+ | No log | 7.0 | 35 | 0.7856 | 64.7857 | 50.0 | 64.5714 | 64.0952 | 14.4 |
63
+ | No log | 8.0 | 40 | 0.7755 | 64.7857 | 50.0 | 64.5714 | 64.0952 | 14.2 |
64
+ | No log | 9.0 | 45 | 0.7864 | 64.7857 | 50.0 | 64.5714 | 64.0952 | 14.2 |
65
+ | No log | 10.0 | 50 | 0.7928 | 62.0833 | 47.0 | 62.0952 | 61.2857 | 14.2 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a4e757066a16cbdea075ad0690a8bb8b2c067cfbda800feed03940145b544cf
3
  size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f99809e2d8febc661302df9ea87076d2e30e0ee609367643d57d2aec7679da
3
  size 307867048
runs/Dec06_09-23-29_7bb9bb6007a1/events.out.tfevents.1701860367.7bb9bb6007a1.626.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ab79c624238634b39001e6a1218811a2ae5790beeebdbad5430c167fd73ca40
3
+ size 10817
special_tokens_map.json CHANGED
@@ -101,7 +101,25 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
- "eos_token": "</s>",
105
- "pad_token": "<pad>",
106
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  }
 
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
  }
tokenizer_config.json CHANGED
@@ -930,9 +930,16 @@
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
 
933
  "model_max_length": 512,
 
934
  "pad_token": "<pad>",
 
 
935
  "sp_model_kwargs": {},
 
936
  "tokenizer_class": "T5Tokenizer",
 
 
937
  "unk_token": "<unk>"
938
  }
 
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
933
+ "max_length": 48,
934
  "model_max_length": 512,
935
+ "pad_to_multiple_of": null,
936
  "pad_token": "<pad>",
937
+ "pad_token_type_id": 0,
938
+ "padding_side": "right",
939
  "sp_model_kwargs": {},
940
+ "stride": 0,
941
  "tokenizer_class": "T5Tokenizer",
942
+ "truncation_side": "right",
943
+ "truncation_strategy": "longest_first",
944
  "unk_token": "<unk>"
945
  }