Acc
commited on
Commit
•
513aafc
1
Parent(s):
760b7cb
End of training
Browse files- README.md +33 -41
- config.json +1 -1
- model.safetensors +1 -1
- runs/Apr06_16-27-51_df7953592bde/events.out.tfevents.1712420877.df7953592bde.34.0 +3 -0
- runs/Apr06_16-28-56_df7953592bde/events.out.tfevents.1712420945.df7953592bde.34.1 +3 -0
- runs/Apr06_16-41-52_df7953592bde/events.out.tfevents.1712421713.df7953592bde.168.0 +3 -0
- special_tokens_map.json +3 -21
- tokenizer_config.json +0 -7
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# ingredient_prune
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,53 +35,45 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 2e-05
|
38 |
-
- train_batch_size:
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
|
|
51 |
-
|
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.1097 | 8.0 | 280 | 0.0433 |
|
78 |
-
| 0.1347 | 8.29 | 290 | 0.0421 |
|
79 |
-
| 0.0953 | 8.57 | 300 | 0.0406 |
|
80 |
-
| 0.0967 | 8.86 | 310 | 0.0393 |
|
81 |
-
| 0.0956 | 9.14 | 320 | 0.0383 |
|
82 |
-
| 0.117 | 9.43 | 330 | 0.0376 |
|
83 |
-
| 0.0974 | 9.71 | 340 | 0.0372 |
|
84 |
-
| 0.1094 | 10.0 | 350 | 0.0371 |
|
85 |
|
86 |
|
87 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: t5-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# ingredient_prune
|
15 |
|
16 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.2021
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 5
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 13.8901 | 0.18 | 10 | 13.5101 |
|
51 |
+
| 11.2216 | 0.36 | 20 | 9.6935 |
|
52 |
+
| 8.9001 | 0.55 | 30 | 6.9317 |
|
53 |
+
| 6.9158 | 0.73 | 40 | 4.3383 |
|
54 |
+
| 4.5333 | 0.91 | 50 | 2.5113 |
|
55 |
+
| 3.3307 | 1.09 | 60 | 1.5023 |
|
56 |
+
| 2.3644 | 1.27 | 70 | 1.1537 |
|
57 |
+
| 1.8483 | 1.45 | 80 | 0.7876 |
|
58 |
+
| 1.5672 | 1.64 | 90 | 0.6205 |
|
59 |
+
| 1.1184 | 1.82 | 100 | 0.4843 |
|
60 |
+
| 0.9273 | 2.0 | 110 | 0.4324 |
|
61 |
+
| 0.7881 | 2.18 | 120 | 0.4005 |
|
62 |
+
| 0.7159 | 2.36 | 130 | 0.3644 |
|
63 |
+
| 0.6495 | 2.55 | 140 | 0.3373 |
|
64 |
+
| 0.5903 | 2.73 | 150 | 0.3155 |
|
65 |
+
| 0.5114 | 2.91 | 160 | 0.2980 |
|
66 |
+
| 0.5107 | 3.09 | 170 | 0.2800 |
|
67 |
+
| 0.4718 | 3.27 | 180 | 0.2669 |
|
68 |
+
| 0.4285 | 3.45 | 190 | 0.2542 |
|
69 |
+
| 0.429 | 3.64 | 200 | 0.2422 |
|
70 |
+
| 0.4065 | 3.82 | 210 | 0.2320 |
|
71 |
+
| 0.4087 | 4.0 | 220 | 0.2244 |
|
72 |
+
| 0.3597 | 4.18 | 230 | 0.2166 |
|
73 |
+
| 0.3515 | 4.36 | 240 | 0.2106 |
|
74 |
+
| 0.3453 | 4.55 | 250 | 0.2065 |
|
75 |
+
| 0.3563 | 4.73 | 260 | 0.2036 |
|
76 |
+
| 0.3492 | 4.91 | 270 | 0.2021 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
|
79 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "t5-base",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891644712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4d2d2b99f6ff36ae036cde9a73fcb1bcd4b107db55e86bc9fa2bb5d54c3dc3c
|
3 |
size 891644712
|
runs/Apr06_16-27-51_df7953592bde/events.out.tfevents.1712420877.df7953592bde.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3b558f141f3fdc8942f2fd524936ae2821b0a88a7111529fee167fc7b405172
|
3 |
+
size 5561
|
runs/Apr06_16-28-56_df7953592bde/events.out.tfevents.1712420945.df7953592bde.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:204e06b7c0d8a5e5bd7f96850787da731046964cc05f876e97bb618aeae05c5b
|
3 |
+
size 11239
|
runs/Apr06_16-41-52_df7953592bde/events.out.tfevents.1712421713.df7953592bde.168.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ac52d3a63587e2a4d1af52dad8d5397f3729723bd1e6be09e56ad9ea74a07e1
|
3 |
+
size 18820
|
special_tokens_map.json
CHANGED
@@ -101,25 +101,7 @@
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
-
"eos_token":
|
105 |
-
|
106 |
-
|
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 |
}
|
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
107 |
}
|
tokenizer_config.json
CHANGED
@@ -930,15 +930,8 @@
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
933 |
-
"max_length": 128,
|
934 |
"model_max_length": 128,
|
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 |
}
|
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
|
|
933 |
"model_max_length": 128,
|
|
|
934 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
935 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
936 |
"unk_token": "<unk>"
|
937 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e24eb1200ae4c986e921750f7baeedb709068cf3e3fd0294ba5080450d869661
|
3 |
size 5048
|