End of training
Browse files- README.md +63 -29
- config.json +2 -2
- generation_config.json +1 -1
- model.safetensors +1 -1
- tokenizer_config.json +7 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,26 +1,25 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- bleu
|
8 |
model-index:
|
9 |
-
- name: ft-t5-small-on-info-lg-
|
10 |
results: []
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
|
17 |
-
# ft-t5-small-on-info-lg-formal
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Bleu:
|
23 |
-
- Gen Len:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -45,32 +44,67 @@ The following hyperparameters were used during training:
|
|
45 |
- seed: 42
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
-
- num_epochs:
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
-
| Training Loss | Epoch | Step
|
53 |
-
|
54 |
-
|
|
55 |
-
|
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
|
70 |
|
71 |
### Framework versions
|
72 |
|
73 |
-
- Transformers 4.
|
74 |
-
- Pytorch 2.1.
|
75 |
-
- Datasets 2.
|
76 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: MubarakB/results
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- bleu
|
8 |
model-index:
|
9 |
+
- name: ft-t5-small-on-info-lg-informal-v1
|
10 |
results: []
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
+
# ft-t5-small-on-info-lg-informal-v1
|
|
|
17 |
|
18 |
+
This model is a fine-tuned version of [MubarakB/results](https://huggingface.co/MubarakB/results) on the Luganda informal Data dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6113
|
21 |
+
- Bleu: 0.3498
|
22 |
+
- Gen Len: 15.5287
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 50
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
53 |
+
| No log | 1.0 | 177 | 0.5880 | 0.3892 | 14.6975 |
|
54 |
+
| No log | 2.0 | 354 | 0.5876 | 0.3855 | 14.4873 |
|
55 |
+
| 0.5524 | 3.0 | 531 | 0.5870 | 0.5974 | 14.8217 |
|
56 |
+
| 0.5524 | 4.0 | 708 | 0.5866 | 0.3335 | 14.6975 |
|
57 |
+
| 0.5524 | 5.0 | 885 | 0.5867 | 0.3981 | 14.4013 |
|
58 |
+
| 0.529 | 6.0 | 1062 | 0.5848 | 0.5378 | 14.4618 |
|
59 |
+
| 0.529 | 7.0 | 1239 | 0.5863 | 0.3866 | 14.4618 |
|
60 |
+
| 0.529 | 8.0 | 1416 | 0.5861 | 0.3623 | 14.8471 |
|
61 |
+
| 0.5145 | 9.0 | 1593 | 0.5882 | 0.3559 | 15.0987 |
|
62 |
+
| 0.5145 | 10.0 | 1770 | 0.5875 | 0.3372 | 14.9395 |
|
63 |
+
| 0.5145 | 11.0 | 1947 | 0.5865 | 0.324 | 14.7516 |
|
64 |
+
| 0.5013 | 12.0 | 2124 | 0.5877 | 0.3969 | 14.5159 |
|
65 |
+
| 0.5013 | 13.0 | 2301 | 0.5875 | 0.4127 | 14.9299 |
|
66 |
+
| 0.5013 | 14.0 | 2478 | 0.5884 | 0.3532 | 14.5732 |
|
67 |
+
| 0.4907 | 15.0 | 2655 | 0.5890 | 0.3113 | 14.5478 |
|
68 |
+
| 0.4907 | 16.0 | 2832 | 0.5885 | 0.3364 | 14.8917 |
|
69 |
+
| 0.479 | 17.0 | 3009 | 0.5902 | 0.3211 | 14.5541 |
|
70 |
+
| 0.479 | 18.0 | 3186 | 0.5915 | 0.3916 | 14.8917 |
|
71 |
+
| 0.479 | 19.0 | 3363 | 0.5922 | 0.4469 | 15.1019 |
|
72 |
+
| 0.47 | 20.0 | 3540 | 0.5932 | 0.3724 | 14.5414 |
|
73 |
+
| 0.47 | 21.0 | 3717 | 0.5931 | 0.3376 | 15.3471 |
|
74 |
+
| 0.47 | 22.0 | 3894 | 0.5939 | 0.3501 | 14.4936 |
|
75 |
+
| 0.4546 | 23.0 | 4071 | 0.5964 | 0.4757 | 15.0287 |
|
76 |
+
| 0.4546 | 24.0 | 4248 | 0.5969 | 0.4039 | 14.8217 |
|
77 |
+
| 0.4546 | 25.0 | 4425 | 0.5976 | 0.4478 | 14.9777 |
|
78 |
+
| 0.4483 | 26.0 | 4602 | 0.5998 | 0.4097 | 15.0573 |
|
79 |
+
| 0.4483 | 27.0 | 4779 | 0.5997 | 0.4217 | 15.0223 |
|
80 |
+
| 0.4483 | 28.0 | 4956 | 0.5998 | 0.4428 | 15.0032 |
|
81 |
+
| 0.4396 | 29.0 | 5133 | 0.6014 | 0.4109 | 15.0032 |
|
82 |
+
| 0.4396 | 30.0 | 5310 | 0.6033 | 0.4391 | 15.2611 |
|
83 |
+
| 0.4396 | 31.0 | 5487 | 0.6024 | 0.4444 | 14.9459 |
|
84 |
+
| 0.4359 | 32.0 | 5664 | 0.6030 | 0.4984 | 15.1401 |
|
85 |
+
| 0.4359 | 33.0 | 5841 | 0.6055 | 0.4665 | 15.4045 |
|
86 |
+
| 0.4261 | 34.0 | 6018 | 0.6056 | 0.4444 | 15.2994 |
|
87 |
+
| 0.4261 | 35.0 | 6195 | 0.6064 | 0.4323 | 15.1497 |
|
88 |
+
| 0.4261 | 36.0 | 6372 | 0.6065 | 0.458 | 15.172 |
|
89 |
+
| 0.4222 | 37.0 | 6549 | 0.6077 | 0.4317 | 15.2134 |
|
90 |
+
| 0.4222 | 38.0 | 6726 | 0.6080 | 0.3233 | 15.0764 |
|
91 |
+
| 0.4222 | 39.0 | 6903 | 0.6084 | 0.3266 | 15.4299 |
|
92 |
+
| 0.4158 | 40.0 | 7080 | 0.6081 | 0.3278 | 15.2197 |
|
93 |
+
| 0.4158 | 41.0 | 7257 | 0.6097 | 0.333 | 15.2675 |
|
94 |
+
| 0.4158 | 42.0 | 7434 | 0.6092 | 0.3557 | 15.3599 |
|
95 |
+
| 0.4121 | 43.0 | 7611 | 0.6098 | 0.3214 | 15.3185 |
|
96 |
+
| 0.4121 | 44.0 | 7788 | 0.6110 | 0.3224 | 15.3025 |
|
97 |
+
| 0.4121 | 45.0 | 7965 | 0.6105 | 0.3159 | 15.2994 |
|
98 |
+
| 0.4108 | 46.0 | 8142 | 0.6113 | 0.3109 | 15.3726 |
|
99 |
+
| 0.4108 | 47.0 | 8319 | 0.6112 | 0.3205 | 15.4904 |
|
100 |
+
| 0.4108 | 48.0 | 8496 | 0.6114 | 0.44 | 15.6433 |
|
101 |
+
| 0.4105 | 49.0 | 8673 | 0.6113 | 0.4321 | 15.6242 |
|
102 |
+
| 0.4105 | 50.0 | 8850 | 0.6113 | 0.3498 | 15.5287 |
|
103 |
|
104 |
|
105 |
### Framework versions
|
106 |
|
107 |
+
- Transformers 4.44.0
|
108 |
+
- Pytorch 2.1.0+cu118
|
109 |
+
- Datasets 2.21.0
|
110 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
@@ -55,7 +55,7 @@
|
|
55 |
}
|
56 |
},
|
57 |
"torch_dtype": "float32",
|
58 |
-
"transformers_version": "4.
|
59 |
"use_cache": true,
|
60 |
"vocab_size": 32128
|
61 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "MubarakB/results",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
55 |
}
|
56 |
},
|
57 |
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.44.0",
|
59 |
"use_cache": true,
|
60 |
"vocab_size": 32128
|
61 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.44.0"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69b193b0d61185f60ff6c5b6a01a2cb59e46ced4a0e34b56178cc177bbf3780d
|
3 |
size 242041896
|
tokenizer_config.json
CHANGED
@@ -930,8 +930,15 @@
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
|
|
933 |
"model_max_length": 512,
|
|
|
934 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
935 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
936 |
"unk_token": "<unk>"
|
937 |
}
|
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
933 |
+
"max_length": 128,
|
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 |
+
"stride": 0,
|
940 |
"tokenizer_class": "T5Tokenizer",
|
941 |
+
"truncation_side": "right",
|
942 |
+
"truncation_strategy": "longest_first",
|
943 |
"unk_token": "<unk>"
|
944 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8bf1e52a0538c1ed107fe15f7a641bbf53e57743b204022d2998b9b05957516
|
3 |
size 5240
|