SaiedAlshahrani commited on
Commit
db1a30f
1 Parent(s): a186628

Upload files manually

Browse files
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 [ASAS-AI/bloom_7B_8bit](https://huggingface.co/asas-ai/bloom_7B_8bit) on [MLQA](https://huggingface.co/datasets/mlqa) dataset.
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 4.32.0
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 sha256:95b60d813aaea50db66df6c1d0e3da678aadfc3d629d56f946a3c186a80f64f3
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:a0d6a79e64d88073086c42a876fd1a49a41125c776045a5e9dc4d56d5deabf99
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 sha256:8d87765df6a31377ad19b312912444648dd9ad63b3d8e62abdf8d78153b28300
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": 2.7297,
15
  "step": 100
16
  },
17
  {
18
  "epoch": 6.15,
19
  "learning_rate": 0.0002,
20
- "loss": 1.5755,
21
  "step": 200
22
  },
23
  {
24
  "epoch": 9.23,
25
  "learning_rate": 0.0002,
26
- "loss": 0.8132,
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 sha256:4967eb5a58aafa69774e2237894fc54a23f04d90361ad618dea1ded5abf97c2a
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 sha256:3f0128352566139359dae58a49786d586e1e031b838b9e8ae08eea9904c0944a
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 sha256:257f7048f99f95d82084328e5214c55f8f28692fecaa13d471f1145f97d443f8
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": 2.7297,
15
  "step": 100
16
  },
17
  {
18
  "epoch": 6.15,
19
  "learning_rate": 0.0002,
20
- "loss": 1.5755,
21
  "step": 200
22
  },
23
  {
24
  "epoch": 9.23,
25
  "learning_rate": 0.0002,
26
- "loss": 0.8132,
27
  "step": 300
28
  },
29
  {
30
  "epoch": 12.31,
31
  "learning_rate": 0.0002,
32
- "loss": 0.4236,
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 sha256:4967eb5a58aafa69774e2237894fc54a23f04d90361ad618dea1ded5abf97c2a
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 sha256:95b60d813aaea50db66df6c1d0e3da678aadfc3d629d56f946a3c186a80f64f3
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:f49422abc5f554289b38c55030e2ce82017f8b2f8131a8634f5cc824edaab733
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": 2.7297,
15
  "step": 100
16
  },
17
  {
18
  "epoch": 6.15,
19
  "learning_rate": 0.0002,
20
- "loss": 1.5755,
21
  "step": 200
22
  },
23
  {
24
  "epoch": 9.23,
25
  "learning_rate": 0.0002,
26
- "loss": 0.8132,
27
  "step": 300
28
  },
29
  {
30
  "epoch": 12.31,
31
  "learning_rate": 0.0002,
32
- "loss": 0.4236,
33
  "step": 400
34
  },
35
  {
36
  "epoch": 15.38,
37
  "learning_rate": 0.0002,
38
- "loss": 0.207,
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 sha256:4967eb5a58aafa69774e2237894fc54a23f04d90361ad618dea1ded5abf97c2a
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 sha256:4967eb5a58aafa69774e2237894fc54a23f04d90361ad618dea1ded5abf97c2a
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcbe11d453059a1da6e399b6979c7a513acc1d4b4537290c880887bc82aee3db
3
  size 4091