pszemraj commited on
Commit
12ca3b8
1 Parent(s): 8f85cbb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +61 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigscience-bloom-rail-1.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bloom-1b1-emailgen-v1
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # bloom-1b1-emailgen-v1
14
+
15
+ This model is a fine-tuned version of [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.7396
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 7e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 1
39
+ - seed: 42
40
+ - distributed_type: multi-GPU
41
+ - gradient_accumulation_steps: 64
42
+ - total_train_batch_size: 128
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_ratio: 0.03
46
+ - num_epochs: 2.0
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.8465 | 1.0 | 256 | 1.8656 |
53
+ | 1.4903 | 2.0 | 512 | 1.7396 |
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.25.0.dev0
59
+ - Pytorch 1.13.0+cu117
60
+ - Datasets 2.6.1
61
+ - Tokenizers 0.13.1