VampeeHuntee
commited on
Commit
•
6d97f07
1
Parent(s):
ca596db
End of training
Browse files- README.md +56 -0
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- vi
|
4 |
+
license: bigscience-bloom-rail-1.0
|
5 |
+
library_name: peft
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: bigscience/bloomz-7b1
|
9 |
+
model-index:
|
10 |
+
- name: bloomz-7b1_llms_subtask_1
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# bloomz-7b1_llms_subtask_1
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [bigscience/bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1) on the somd dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 2e-05
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 2
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 1
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- PEFT 0.11.1
|
53 |
+
- Transformers 4.41.2
|
54 |
+
- Pytorch 2.1.2
|
55 |
+
- Datasets 2.19.2
|
56 |
+
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -20,10 +20,10 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"dense",
|
24 |
-
"dense_4h_to_h",
|
25 |
"query_key_value",
|
26 |
-
"dense_h_to_4h"
|
|
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"query_key_value",
|
24 |
+
"dense_h_to_4h",
|
25 |
+
"dense",
|
26 |
+
"dense_4h_to_h"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 62948128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de0f14c160ed296266754df64ec3e74289c2694e1205b25b8e7407e3e821110d
|
3 |
size 62948128
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57a0555c68377b6fd8934d653f41902a50743caefb5707c9738a35070a4d4813
|
3 |
size 5176
|