Hugging Face's logo

G-R-A-V-I-T-Y
/
flan-t5-base-AR-LORA-V1

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
G-R-A-V-I-T-Y commited on
Commit
1d6ced1
•
1 Parent(s): 27a5696

End of training

Browse files
Files changed (6) hide show
  1. README.md +34 -24
  2. adapter_model.safetensors +1 -1
  3. logs/events.out.tfevents.1717278471.Chris_PC.28696.2 +3 -0
  4. logs/events.out.tfevents.1717295939.Chris_PC.28696.3 +3 -0
  5. tokenizer_config.json +7 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.7342
20
- - Exact Match: 30.9591
21
- - Gen Len: 3.6062
22
 
23
  ## Model description
24
 
@@ -43,32 +43,42 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 20
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | Gen Len |
51
  |:-------------:|:-----:|:-----:|:---------------:|:-----------:|:-------:|
52
- | 0.8221 | 1.0 | 4246 | 0.8269 | 20.5823 | 3.8789 |
53
- | 0.7459 | 2.0 | 8492 | 0.7917 | 26.3525 | 3.6663 |
54
- | 0.7727 | 3.0 | 12738 | 0.7775 | 30.8587 | 3.4217 |
55
- | 0.758 | 4.0 | 16984 | 0.7652 | 26.5946 | 3.7380 |
56
- | 0.7465 | 5.0 | 21230 | 0.7551 | 28.2601 | 3.6873 |
57
- | 0.6693 | 6.0 | 25476 | 0.7524 | 30.0201 | 3.6045 |
58
- | 0.6364 | 7.0 | 29722 | 0.7529 | 28.7208 | 3.6432 |
59
- | 0.6907 | 8.0 | 33968 | 0.7474 | 29.9965 | 3.6177 |
60
- | 0.8167 | 9.0 | 38214 | 0.7400 | 30.528 | 3.5908 |
61
- | 0.7631 | 10.0 | 42460 | 0.7407 | 31.095 | 3.5620 |
62
- | 0.7106 | 11.0 | 46706 | 0.7374 | 31.3962 | 3.5518 |
63
- | 0.7018 | 12.0 | 50952 | 0.7383 | 30.4394 | 3.6223 |
64
- | 0.6446 | 13.0 | 55198 | 0.7360 | 29.4354 | 3.6789 |
65
- | 0.7872 | 14.0 | 59444 | 0.7355 | 30.2209 | 3.6359 |
66
- | 0.8111 | 15.0 | 63690 | 0.7364 | 30.2622 | 3.6182 |
67
- | 0.7027 | 16.0 | 67936 | 0.7346 | 29.8429 | 3.6637 |
68
- | 0.7077 | 17.0 | 72182 | 0.7371 | 30.5398 | 3.6260 |
69
- | 0.7806 | 18.0 | 76428 | 0.7342 | 31.03 | 3.5911 |
70
- | 0.762 | 19.0 | 80674 | 0.7354 | 31.095 | 3.6043 |
71
- | 0.6805 | 20.0 | 84920 | 0.7342 | 30.9591 | 3.6062 |
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.7887
20
+ - Exact Match: 28.3
21
+ - Gen Len: 3.592
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 30
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | Gen Len |
51
  |:-------------:|:-----:|:-----:|:---------------:|:-----------:|:-------:|
52
+ | 1.1717 | 1.0 | 625 | 0.9465 | 18.9 | 3.82 |
53
+ | 0.8167 | 2.0 | 1250 | 0.8975 | 17.9 | 3.923 |
54
+ | 0.9046 | 3.0 | 1875 | 0.8691 | 25.4 | 3.338 |
55
+ | 0.9501 | 4.0 | 2500 | 0.8624 | 17.8 | 3.978 |
56
+ | 0.884 | 5.0 | 3125 | 0.8469 | 19.9 | 3.917 |
57
+ | 0.8418 | 6.0 | 3750 | 0.8356 | 24.8 | 3.596 |
58
+ | 0.877 | 7.0 | 4375 | 0.8261 | 19.0 | 3.926 |
59
+ | 0.804 | 8.0 | 5000 | 0.8147 | 23.0 | 3.732 |
60
+ | 0.8267 | 9.0 | 5625 | 0.8123 | 26.0 | 3.629 |
61
+ | 0.8979 | 10.0 | 6250 | 0.8132 | 24.5 | 3.685 |
62
+ | 0.8165 | 11.0 | 6875 | 0.8084 | 28.4 | 3.517 |
63
+ | 0.891 | 12.0 | 7500 | 0.8034 | 28.1 | 3.548 |
64
+ | 0.768 | 13.0 | 8125 | 0.8095 | 29.1 | 3.45 |
65
+ | 0.6895 | 14.0 | 8750 | 0.8018 | 27.7 | 3.553 |
66
+ | 0.7796 | 15.0 | 9375 | 0.7996 | 30.1 | 3.49 |
67
+ | 0.787 | 16.0 | 10000 | 0.8013 | 26.0 | 3.665 |
68
+ | 0.811 | 17.0 | 10625 | 0.7979 | 28.5 | 3.563 |
69
+ | 0.7858 | 18.0 | 11250 | 0.7991 | 26.4 | 3.64 |
70
+ | 0.8608 | 19.0 | 11875 | 0.7955 | 24.8 | 3.733 |
71
+ | 0.9044 | 20.0 | 12500 | 0.7913 | 25.9 | 3.662 |
72
+ | 0.9171 | 21.0 | 13125 | 0.7905 | 25.9 | 3.708 |
73
+ | 0.8093 | 22.0 | 13750 | 0.7918 | 28.1 | 3.596 |
74
+ | 0.7653 | 23.0 | 14375 | 0.7940 | 28.3 | 3.586 |
75
+ | 0.9361 | 24.0 | 15000 | 0.7887 | 28.3 | 3.592 |
76
+ | 0.6999 | 25.0 | 15625 | 0.7921 | 29.6 | 3.552 |
77
+ | 0.728 | 26.0 | 16250 | 0.7918 | 27.8 | 3.621 |
78
+ | 0.7169 | 27.0 | 16875 | 0.7908 | 27.2 | 3.628 |
79
+ | 0.6388 | 28.0 | 17500 | 0.7920 | 28.9 | 3.572 |
80
+ | 0.7302 | 29.0 | 18125 | 0.7920 | 28.8 | 3.573 |
81
+ | 0.7651 | 30.0 | 18750 | 0.7917 | 28.0 | 3.599 |
82
 
83
 
84
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f65cc1a73390191cd078d52107a69347db3739da602527483ce11ab015b85ab
3
  size 7098016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7084494c37b56576e77b837f885e896b54cc5529eea41f2f46b26e16f995432e
3
  size 7098016
logs/events.out.tfevents.1717278471.Chris_PC.28696.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55294629f0c5adaa9f455abb82b63e9bcc20ee2b6a4df88d53dcaa35aa460c18
3
+ size 414564
logs/events.out.tfevents.1717295939.Chris_PC.28696.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd03c61a4c60a10b9553ffc91756c26202025cd600496829905bc64c08cff996
3
+ size 472
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": 10,
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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71e93ce59499b429e73c2cd993db27045ad34c650968d94bc3aaa389c7281edf
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ced01d49a8c68fb3ab347f07665c5a0b78e6c85785d2d7dd72b91379a34ba4
3
  size 5304