anyiwang/data_experiment
Browse files- README.md +7 -6
- adapter_config.json +6 -9
- adapter_model.safetensors +2 -2
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,10 +1,11 @@
|
|
1 |
---
|
|
|
2 |
library_name: peft
|
3 |
tags:
|
4 |
- trl
|
5 |
- sft
|
6 |
- generated_from_trainer
|
7 |
-
base_model:
|
8 |
model-index:
|
9 |
- name: data_experiment
|
10 |
results: []
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# data_experiment
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -39,9 +40,9 @@ The following hyperparameters were used during training:
|
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
-
- lr_scheduler_type:
|
43 |
-
-
|
44 |
-
-
|
45 |
|
46 |
### Training results
|
47 |
|
@@ -51,6 +52,6 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
- PEFT 0.7.1
|
53 |
- Transformers 4.36.2
|
54 |
-
- Pytorch 2.1
|
55 |
- Datasets 2.16.1
|
56 |
- Tokenizers 0.15.0
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
9 |
model-index:
|
10 |
- name: data_experiment
|
11 |
results: []
|
|
|
16 |
|
17 |
# data_experiment
|
18 |
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: constant
|
44 |
+
- lr_scheduler_warmup_ratio: 0.1
|
45 |
+
- training_steps: 5
|
46 |
|
47 |
### Training results
|
48 |
|
|
|
52 |
|
53 |
- PEFT 0.7.1
|
54 |
- Transformers 4.36.2
|
55 |
+
- Pytorch 2.0.1
|
56 |
- Datasets 2.16.1
|
57 |
- Tokenizers 0.15.0
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -9,24 +9,21 @@
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
-
"lora_alpha":
|
13 |
-
"lora_dropout": 0.
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
-
"r":
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"gate_proj",
|
23 |
-
"down_proj",
|
24 |
"q_proj",
|
|
|
25 |
"v_proj",
|
26 |
"o_proj",
|
27 |
-
"k_proj"
|
28 |
-
"up_proj",
|
29 |
-
"lm_head"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM"
|
32 |
}
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
+
"r": 64,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
22 |
"q_proj",
|
23 |
+
"gate_proj",
|
24 |
"v_proj",
|
25 |
"o_proj",
|
26 |
+
"k_proj"
|
|
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM"
|
29 |
}
|
adapter_model.safetensors
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:ed120ac8d7522db4f9101829c975460bda398cefd4b44970d8106bf785117f50
|
3 |
+
size 369142184
|
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:e80e558428c4c40d7b80999899b890f6315f923a048e345b84618930fa60b130
|
3 |
+
size 4219
|