Acc commited on
Commit
1a5b926
1 Parent(s): 59ad1a3

End of training

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: SpamAcc/ingredient_prune
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 [SpamAcc/ingredient_prune](https://huggingface.co/SpamAcc/ingredient_prune) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0432
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: 100
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 0.312 | 1.82 | 100 | 0.0295 |
51
- | 0.0533 | 3.64 | 200 | 0.0149 |
52
- | 0.0247 | 5.45 | 300 | 0.0136 |
53
- | 0.0149 | 7.27 | 400 | 0.0124 |
54
- | 0.0114 | 9.09 | 500 | 0.0127 |
55
- | 0.0086 | 10.91 | 600 | 0.0127 |
56
- | 0.0075 | 12.73 | 700 | 0.0145 |
57
- | 0.0061 | 14.55 | 800 | 0.0151 |
58
- | 0.0058 | 16.36 | 900 | 0.0161 |
59
- | 0.0044 | 18.18 | 1000 | 0.0169 |
60
- | 0.0039 | 20.0 | 1100 | 0.0199 |
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": "SpamAcc/ingredient_prune",
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:a48c17f9338e9a40b3bf27cce0bc38c84ea418e590bfc95237ceeda033e26faa
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 sha256:1e94952fd1a241da6a91d2143e1db7aca04a9dfb43c509bedad928a1c37d9c7f
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead7e82110958dd17cdf6f4286954c9855174d651b7e318cfc571e901758dcd6
3
  size 5048