Acc
commited on
Commit
•
1a5b926
1
Parent(s):
59ad1a3
End of training
Browse files- README.md +15 -59
- config.json +1 -1
- model.safetensors +1 -1
- runs/Apr06_21-02-34_df7953592bde/events.out.tfevents.1712437358.df7953592bde.168.8 +3 -0
- 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 |
|
@@ -40,68 +40,24 @@ The following hyperparameters were used during training:
|
|
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 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.0044 | 21.82 | 1200 | 0.0181 |
|
62 |
-
| 0.0035 | 23.64 | 1300 | 0.0230 |
|
63 |
-
| 0.0039 | 25.45 | 1400 | 0.0226 |
|
64 |
-
| 0.0028 | 27.27 | 1500 | 0.0234 |
|
65 |
-
| 0.0026 | 29.09 | 1600 | 0.0272 |
|
66 |
-
| 0.0023 | 30.91 | 1700 | 0.0261 |
|
67 |
-
| 0.0028 | 32.73 | 1800 | 0.0254 |
|
68 |
-
| 0.0018 | 34.55 | 1900 | 0.0268 |
|
69 |
-
| 0.0022 | 36.36 | 2000 | 0.0303 |
|
70 |
-
| 0.002 | 38.18 | 2100 | 0.0286 |
|
71 |
-
| 0.0018 | 40.0 | 2200 | 0.0299 |
|
72 |
-
| 0.0024 | 41.82 | 2300 | 0.0322 |
|
73 |
-
| 0.0019 | 43.64 | 2400 | 0.0328 |
|
74 |
-
| 0.0015 | 45.45 | 2500 | 0.0310 |
|
75 |
-
| 0.002 | 47.27 | 2600 | 0.0352 |
|
76 |
-
| 0.0015 | 49.09 | 2700 | 0.0361 |
|
77 |
-
| 0.0013 | 50.91 | 2800 | 0.0358 |
|
78 |
-
| 0.0011 | 52.73 | 2900 | 0.0368 |
|
79 |
-
| 0.0017 | 54.55 | 3000 | 0.0387 |
|
80 |
-
| 0.0012 | 56.36 | 3100 | 0.0384 |
|
81 |
-
| 0.0011 | 58.18 | 3200 | 0.0402 |
|
82 |
-
| 0.0016 | 60.0 | 3300 | 0.0394 |
|
83 |
-
| 0.0012 | 61.82 | 3400 | 0.0403 |
|
84 |
-
| 0.0013 | 63.64 | 3500 | 0.0392 |
|
85 |
-
| 0.0011 | 65.45 | 3600 | 0.0413 |
|
86 |
-
| 0.0015 | 67.27 | 3700 | 0.0400 |
|
87 |
-
| 0.0021 | 69.09 | 3800 | 0.0412 |
|
88 |
-
| 0.0009 | 70.91 | 3900 | 0.0410 |
|
89 |
-
| 0.0013 | 72.73 | 4000 | 0.0419 |
|
90 |
-
| 0.0009 | 74.55 | 4100 | 0.0415 |
|
91 |
-
| 0.0011 | 76.36 | 4200 | 0.0418 |
|
92 |
-
| 0.0008 | 78.18 | 4300 | 0.0422 |
|
93 |
-
| 0.0013 | 80.0 | 4400 | 0.0434 |
|
94 |
-
| 0.0011 | 81.82 | 4500 | 0.0436 |
|
95 |
-
| 0.0011 | 83.64 | 4600 | 0.0434 |
|
96 |
-
| 0.0008 | 85.45 | 4700 | 0.0434 |
|
97 |
-
| 0.0009 | 87.27 | 4800 | 0.0436 |
|
98 |
-
| 0.0006 | 89.09 | 4900 | 0.0442 |
|
99 |
-
| 0.0009 | 90.91 | 5000 | 0.0436 |
|
100 |
-
| 0.001 | 92.73 | 5100 | 0.0434 |
|
101 |
-
| 0.0008 | 94.55 | 5200 | 0.0433 |
|
102 |
-
| 0.0013 | 96.36 | 5300 | 0.0434 |
|
103 |
-
| 0.001 | 98.18 | 5400 | 0.0433 |
|
104 |
-
| 0.0008 | 100.0 | 5500 | 0.0432 |
|
105 |
|
106 |
|
107 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: google/flan-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 [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0153
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 20
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 17.0417 | 1.82 | 100 | 4.0933 |
|
51 |
+
| 2.66 | 3.64 | 200 | 0.3448 |
|
52 |
+
| 0.4315 | 5.45 | 300 | 0.0862 |
|
53 |
+
| 0.1 | 7.27 | 400 | 0.0291 |
|
54 |
+
| 0.0454 | 9.09 | 500 | 0.0219 |
|
55 |
+
| 0.0293 | 10.91 | 600 | 0.0176 |
|
56 |
+
| 0.0212 | 12.73 | 700 | 0.0165 |
|
57 |
+
| 0.0186 | 14.55 | 800 | 0.0155 |
|
58 |
+
| 0.0155 | 16.36 | 900 | 0.0155 |
|
59 |
+
| 0.0159 | 18.18 | 1000 | 0.0152 |
|
60 |
+
| 0.0137 | 20.0 | 1100 | 0.0153 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
62 |
|
63 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/flan-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 990345064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f4b8c55164dace8410732a460c81caaa18507a5b7771af315bb7f0ab3e61379
|
3 |
size 990345064
|
runs/Apr06_21-02-34_df7953592bde/events.out.tfevents.1712437358.df7953592bde.168.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1204b7bf22fe1bdd01a3f65c43a0ce569825d7917a43e98e4b2e2254779473d4
|
3 |
+
size 11263
|
tokenizer_config.json
CHANGED
@@ -930,16 +930,9 @@
|
|
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 |
"sp_model_kwargs": {},
|
940 |
-
"stride": 0,
|
941 |
"tokenizer_class": "T5Tokenizer",
|
942 |
-
"truncation_side": "right",
|
943 |
-
"truncation_strategy": "longest_first",
|
944 |
"unk_token": "<unk>"
|
945 |
}
|
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
|
|
933 |
"model_max_length": 128,
|
|
|
934 |
"pad_token": "<pad>",
|
|
|
|
|
935 |
"sp_model_kwargs": {},
|
|
|
936 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
937 |
"unk_token": "<unk>"
|
938 |
}
|
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:ead7e82110958dd17cdf6f4286954c9855174d651b7e318cfc571e901758dcd6
|
3 |
size 5048
|