Hugging Face's logo

browndw
/
morphoseg-en-byt5

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
browndw commited on
Commit
e5913e4
·
verified ·
1 Parent(s): 63757f8

End of training

Browse files
Files changed (1) hide show
  1. README.md +23 -17
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0119
20
- - Exact Match: 0.9230
21
 
22
  ## Model description
23
 
@@ -45,24 +45,30 @@ The following hyperparameters were used during training:
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
- - num_epochs: 12
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Exact Match |
53
- |:-------------:|:-----:|:-----:|:---------------:|:-----------:|
54
- | 0.0197 | 1.0 | 7645 | 0.0145 | 0.8277 |
55
- | 0.0141 | 2.0 | 15290 | 0.0117 | 0.8622 |
56
- | 0.0103 | 3.0 | 22935 | 0.0100 | 0.8791 |
57
- | 0.0086 | 4.0 | 30580 | 0.0094 | 0.8893 |
58
- | 0.0063 | 5.0 | 38225 | 0.0089 | 0.8977 |
59
- | 0.0054 | 6.0 | 45870 | 0.0086 | 0.9055 |
60
- | 0.0043 | 7.0 | 53515 | 0.0087 | 0.9109 |
61
- | 0.0032 | 8.0 | 61160 | 0.0090 | 0.9135 |
62
- | 0.0023 | 9.0 | 68805 | 0.0098 | 0.9179 |
63
- | 0.0018 | 10.0 | 76450 | 0.0105 | 0.9202 |
64
- | 0.0015 | 11.0 | 84095 | 0.0108 | 0.9228 |
65
- | 0.0012 | 12.0 | 91740 | 0.0119 | 0.9230 |
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0142
20
+ - Exact Match: 0.9244
21
 
22
  ## Model description
23
 
 
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 18
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Exact Match |
53
+ |:-------------:|:-----:|:------:|:---------------:|:-----------:|
54
+ | 0.0195 | 1.0 | 7646 | 0.0148 | 0.8325 |
55
+ | 0.0139 | 2.0 | 15292 | 0.0115 | 0.8618 |
56
+ | 0.0114 | 3.0 | 22938 | 0.0102 | 0.8764 |
57
+ | 0.009 | 4.0 | 30584 | 0.0093 | 0.8874 |
58
+ | 0.007 | 5.0 | 38230 | 0.0093 | 0.8965 |
59
+ | 0.0056 | 6.0 | 45876 | 0.0090 | 0.9021 |
60
+ | 0.0049 | 7.0 | 53522 | 0.0093 | 0.9059 |
61
+ | 0.004 | 8.0 | 61168 | 0.0095 | 0.9101 |
62
+ | 0.0034 | 9.0 | 68814 | 0.0096 | 0.9112 |
63
+ | 0.0028 | 10.0 | 76460 | 0.0101 | 0.9150 |
64
+ | 0.0023 | 11.0 | 84106 | 0.0108 | 0.9175 |
65
+ | 0.0018 | 12.0 | 91752 | 0.0108 | 0.9185 |
66
+ | 0.0015 | 13.0 | 99398 | 0.0112 | 0.9209 |
67
+ | 0.0011 | 14.0 | 107044 | 0.0121 | 0.9213 |
68
+ | 0.001 | 15.0 | 114690 | 0.0123 | 0.9220 |
69
+ | 0.0008 | 16.0 | 122336 | 0.0128 | 0.9237 |
70
+ | 0.0005 | 17.0 | 129982 | 0.0137 | 0.9245 |
71
+ | 0.0005 | 18.0 | 137628 | 0.0142 | 0.9244 |
72
 
73
 
74
  ### Framework versions