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:
|
21 |
-
- Rouge1:
|
22 |
- Rouge2: 47.0
|
23 |
-
- Rougel:
|
24 |
-
- Rougelsum:
|
25 |
-
- Gen Len: 14.
|
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 |
|
57 |
-
| No log | 2.0 | 10 |
|
58 |
-
| No log | 3.0 | 15 |
|
59 |
-
| No log | 4.0 | 20 |
|
60 |
-
| No log | 5.0 | 25 |
|
61 |
-
| No log | 6.0 | 30 |
|
62 |
-
| No log | 7.0 | 35 |
|
63 |
-
| No log | 8.0 | 40 |
|
64 |
-
| No log | 9.0 | 45 |
|
65 |
-
| No log | 10.0 | 50 |
|
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:
|
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":
|
105 |
-
|
106 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
}
|