SaiedAlshahrani
commited on
Commit
•
db1a30f
1
Parent(s):
a186628
Upload files manually
Browse files- README.md +3 -19
- adapter_model.bin +1 -1
- checkpoint-300/adapter_model.bin +1 -1
- checkpoint-300/optimizer.pt +1 -1
- checkpoint-300/trainer_state.json +3 -3
- checkpoint-300/training_args.bin +1 -1
- checkpoint-400/adapter_model.bin +1 -1
- checkpoint-400/optimizer.pt +1 -1
- checkpoint-400/trainer_state.json +4 -4
- checkpoint-400/training_args.bin +1 -1
- checkpoint-500/adapter_model.bin +1 -1
- checkpoint-500/optimizer.pt +1 -1
- checkpoint-500/trainer_state.json +5 -5
- checkpoint-500/training_args.bin +1 -1
- runs/Aug29_06-43-47_n7u3rzpi4b/events.out.tfevents.1693291468.n7u3rzpi4b.409.0 +3 -0
- runs/Aug29_06-48-06_n7u3rzpi4b/events.out.tfevents.1693291726.n7u3rzpi4b.596.0 +3 -0
- runs/Aug29_07-37-39_n7u3rzpi4b/events.out.tfevents.1693294700.n7u3rzpi4b.1425.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -5,12 +5,6 @@ tags:
|
|
5 |
model-index:
|
6 |
- name: bloom_7B_4bit_qlora
|
7 |
results: []
|
8 |
-
datasets:
|
9 |
-
- mlqa
|
10 |
-
language:
|
11 |
-
- ar
|
12 |
-
library_name: adapter-transformers
|
13 |
-
pipeline_tag: text-generation
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -18,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# bloom_7B_4bit_qlora
|
20 |
|
21 |
-
This model is a fine-tuned version of [
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -49,22 +43,12 @@ The following hyperparameters were used during training:
|
|
49 |
- training_steps: 500
|
50 |
|
51 |
### Training results
|
52 |
-
| Step | Training Loss |
|
53 |
-
|:-----:|:-------------:|
|
54 |
-
| 100 | 2.729700 |
|
55 |
-
| 200 | 1.575500 |
|
56 |
-
| 300 | 0.813200 |
|
57 |
-
| 400 | 0.423600 |
|
58 |
-
| 500 | 0.207000 |
|
59 |
|
60 |
-
| Train Runtime | Train Samples Per Second | Train Steps Per Second | Total Flos | Train Loss | Epoch |
|
61 |
-
|:--------------:|:------------------------:|:----------------------:|:-------------------------:|:----------:|:--------:|
|
62 |
-
| 3125.1136 | 2.56 | 0.16 | 6.276242983098778e+16 | 1.149795913696289 | 15.38 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
-
- Transformers 4.32.
|
68 |
- Pytorch 2.0.1+cu117
|
69 |
- Datasets 2.4.0
|
70 |
-
- Tokenizers 0.12.1
|
|
|
5 |
model-index:
|
6 |
- name: bloom_7B_4bit_qlora
|
7 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
12 |
|
13 |
# bloom_7B_4bit_qlora
|
14 |
|
15 |
+
This model is a fine-tuned version of [asas-ai/bloom_7B_8bit](https://huggingface.co/asas-ai/bloom_7B_8bit) on an unknown dataset.
|
16 |
|
17 |
## Model description
|
18 |
|
|
|
43 |
- training_steps: 500
|
44 |
|
45 |
### Training results
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
|
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
+
- Transformers 4.32.1
|
52 |
- Pytorch 2.0.1+cu117
|
53 |
- Datasets 2.4.0
|
54 |
+
- Tokenizers 0.12.1
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 503404621
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c955067533a49f7058ca8f1a7479ef964ebe1fae9338b0516b275cb8f599a22a
|
3 |
size 503404621
|
checkpoint-300/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 503404621
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73c20a5332383cf5267275ac50b653f14d95882c09bb554b514cb3075f12aaa2
|
3 |
size 503404621
|
checkpoint-300/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1006781317
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b4b899ff9d82304ed98e39549bce964dfaa3dc9d06285638a885c04c90dc2c8
|
3 |
size 1006781317
|
checkpoint-300/trainer_state.json
CHANGED
@@ -11,19 +11,19 @@
|
|
11 |
{
|
12 |
"epoch": 3.08,
|
13 |
"learning_rate": 0.0002,
|
14 |
-
"loss": 2.
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
"epoch": 6.15,
|
19 |
"learning_rate": 0.0002,
|
20 |
-
"loss": 1.
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
"epoch": 9.23,
|
25 |
"learning_rate": 0.0002,
|
26 |
-
"loss": 0.
|
27 |
"step": 300
|
28 |
}
|
29 |
],
|
|
|
11 |
{
|
12 |
"epoch": 3.08,
|
13 |
"learning_rate": 0.0002,
|
14 |
+
"loss": 2.728,
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
"epoch": 6.15,
|
19 |
"learning_rate": 0.0002,
|
20 |
+
"loss": 1.5741,
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
"epoch": 9.23,
|
25 |
"learning_rate": 0.0002,
|
26 |
+
"loss": 0.8154,
|
27 |
"step": 300
|
28 |
}
|
29 |
],
|
checkpoint-300/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcbe11d453059a1da6e399b6979c7a513acc1d4b4537290c880887bc82aee3db
|
3 |
size 4091
|
checkpoint-400/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 503404621
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4167b8d97a1057097f0916548b9e00fa291e4525bf7641fe069a3a55cc1ca8d9
|
3 |
size 503404621
|
checkpoint-400/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1006781317
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:414e93955493b76b174f30cc037e133526606756f30280cd3cbf0bfbf3a6c559
|
3 |
size 1006781317
|
checkpoint-400/trainer_state.json
CHANGED
@@ -11,25 +11,25 @@
|
|
11 |
{
|
12 |
"epoch": 3.08,
|
13 |
"learning_rate": 0.0002,
|
14 |
-
"loss": 2.
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
"epoch": 6.15,
|
19 |
"learning_rate": 0.0002,
|
20 |
-
"loss": 1.
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
"epoch": 9.23,
|
25 |
"learning_rate": 0.0002,
|
26 |
-
"loss": 0.
|
27 |
"step": 300
|
28 |
},
|
29 |
{
|
30 |
"epoch": 12.31,
|
31 |
"learning_rate": 0.0002,
|
32 |
-
"loss": 0.
|
33 |
"step": 400
|
34 |
}
|
35 |
],
|
|
|
11 |
{
|
12 |
"epoch": 3.08,
|
13 |
"learning_rate": 0.0002,
|
14 |
+
"loss": 2.728,
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
"epoch": 6.15,
|
19 |
"learning_rate": 0.0002,
|
20 |
+
"loss": 1.5741,
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
"epoch": 9.23,
|
25 |
"learning_rate": 0.0002,
|
26 |
+
"loss": 0.8154,
|
27 |
"step": 300
|
28 |
},
|
29 |
{
|
30 |
"epoch": 12.31,
|
31 |
"learning_rate": 0.0002,
|
32 |
+
"loss": 0.4314,
|
33 |
"step": 400
|
34 |
}
|
35 |
],
|
checkpoint-400/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcbe11d453059a1da6e399b6979c7a513acc1d4b4537290c880887bc82aee3db
|
3 |
size 4091
|
checkpoint-500/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 503404621
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c955067533a49f7058ca8f1a7479ef964ebe1fae9338b0516b275cb8f599a22a
|
3 |
size 503404621
|
checkpoint-500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1006781317
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c08f3a3309e9eb5acfbaadf9ba2acb00b50d2272b62abfe4592c721ac783255
|
3 |
size 1006781317
|
checkpoint-500/trainer_state.json
CHANGED
@@ -11,31 +11,31 @@
|
|
11 |
{
|
12 |
"epoch": 3.08,
|
13 |
"learning_rate": 0.0002,
|
14 |
-
"loss": 2.
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
"epoch": 6.15,
|
19 |
"learning_rate": 0.0002,
|
20 |
-
"loss": 1.
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
"epoch": 9.23,
|
25 |
"learning_rate": 0.0002,
|
26 |
-
"loss": 0.
|
27 |
"step": 300
|
28 |
},
|
29 |
{
|
30 |
"epoch": 12.31,
|
31 |
"learning_rate": 0.0002,
|
32 |
-
"loss": 0.
|
33 |
"step": 400
|
34 |
},
|
35 |
{
|
36 |
"epoch": 15.38,
|
37 |
"learning_rate": 0.0002,
|
38 |
-
"loss": 0.
|
39 |
"step": 500
|
40 |
}
|
41 |
],
|
|
|
11 |
{
|
12 |
"epoch": 3.08,
|
13 |
"learning_rate": 0.0002,
|
14 |
+
"loss": 2.728,
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
"epoch": 6.15,
|
19 |
"learning_rate": 0.0002,
|
20 |
+
"loss": 1.5741,
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
"epoch": 9.23,
|
25 |
"learning_rate": 0.0002,
|
26 |
+
"loss": 0.8154,
|
27 |
"step": 300
|
28 |
},
|
29 |
{
|
30 |
"epoch": 12.31,
|
31 |
"learning_rate": 0.0002,
|
32 |
+
"loss": 0.4314,
|
33 |
"step": 400
|
34 |
},
|
35 |
{
|
36 |
"epoch": 15.38,
|
37 |
"learning_rate": 0.0002,
|
38 |
+
"loss": 0.2123,
|
39 |
"step": 500
|
40 |
}
|
41 |
],
|
checkpoint-500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcbe11d453059a1da6e399b6979c7a513acc1d4b4537290c880887bc82aee3db
|
3 |
size 4091
|
runs/Aug29_06-43-47_n7u3rzpi4b/events.out.tfevents.1693291468.n7u3rzpi4b.409.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6508c510521534167693c2cd4daa33319231404362efd4b61852eb2c5dc93b2c
|
3 |
+
size 4637
|
runs/Aug29_06-48-06_n7u3rzpi4b/events.out.tfevents.1693291726.n7u3rzpi4b.596.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2857e51a44445739b51123432a93588f0e722ce336594b7f46b64c7314be4bb
|
3 |
+
size 4637
|
runs/Aug29_07-37-39_n7u3rzpi4b/events.out.tfevents.1693294700.n7u3rzpi4b.1425.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b677eb12868e8dc045d9b047a297c0af321877fa41fe6a5dd6cad1c6f186395a
|
3 |
+
size 5773
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcbe11d453059a1da6e399b6979c7a513acc1d4b4537290c880887bc82aee3db
|
3 |
size 4091
|