End of training
Browse files
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: LDCC/LDCC-SOLAR-10.7B
|
7 |
+
model-index:
|
8 |
+
- name: outputs
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# outputs
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B) on an unknown dataset.
|
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: 0.0001
|
37 |
+
- train_batch_size: 2
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 3.0
|
43 |
+
- mixed_precision_training: Native AMP
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- PEFT 0.8.2
|
52 |
+
- Transformers 4.37.2
|
53 |
+
- Pytorch 2.1.0+cu121
|
54 |
+
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"gate_proj",
|
23 |
"k_proj",
|
24 |
"v_proj",
|
25 |
-
"o_proj",
|
26 |
-
"q_proj",
|
27 |
"down_proj",
|
28 |
-
"
|
|
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"k_proj",
|
23 |
"v_proj",
|
|
|
|
|
24 |
"down_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"o_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 125918320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:814cd7fc987a45d99b0bb5494ac86c466a003de2dfa0d1b8da1eab3fe7ba6b0c
|
3 |
size 125918320
|
runs/Feb25_13-10-17_5e0dc09f315d/events.out.tfevents.1708866617.5e0dc09f315d.4182.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8060105a2f42d0211a5c5edae920d44d2b3111d9539df98bd5469c5e52b552c6
|
3 |
+
size 28657
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a10d726c566d8555ce6f82ca13feba86e9960e1f12e1b55458cf43a4ca94ad61
|
3 |
+
size 4728
|