mrm8488 commited on
Commit
1b85036
1 Parent(s): d77de96

End of training

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigscience-bloom-rail-1.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bloom-560m-finetuned-unnatural-instructions-6k-steps
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-560m-finetuned-unnatural-instructions-6k-steps
14
+
15
+ This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.4037
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: 5e-05
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 2
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - training_steps: 6000
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 1.6758 | 0.32 | 1000 | 1.6487 |
50
+ | 1.512 | 0.63 | 2000 | 1.5360 |
51
+ | 1.4658 | 0.95 | 3000 | 1.4580 |
52
+ | 1.0616 | 1.26 | 4000 | 1.4510 |
53
+ | 1.0291 | 1.58 | 5000 | 1.4199 |
54
+ | 0.9906 | 1.89 | 6000 | 1.4037 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.25.1
60
+ - Pytorch 1.13.0+cu116
61
+ - Datasets 2.8.0
62
+ - Tokenizers 0.13.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8cabafe8fd323b4ad53b74b48926a647204a10632e33f303516f41db1158043
3
  size 2236957537
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01cad473944b9a29ef8310c6fe781dee4e6a0c4642713ca9eb8dd364706e17f
3
  size 2236957537
runs/Dec22_13-26-45_831dea14c3ea/events.out.tfevents.1671715636.831dea14c3ea.6859.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00fb96089f03b6a81c01ebc4b131d4657ebf5552273ad06b1f5bd6c59c763474
3
- size 5778
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5790a3fafd2f2026e7beca2ea468fe843d447823ac9a2c1c4c0cdba9ef816b3
3
+ size 15337
runs/Dec22_13-26-45_831dea14c3ea/events.out.tfevents.1671717829.831dea14c3ea.6859.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4158570850ef1b6c738f131b2d24ab36b8fee4a2ebdd15845f567c2187e8104f
3
+ size 311