Yatinginging
commited on
Commit
•
87b2bcf
1
Parent(s):
d99c37c
Model save
Browse files- README.md +4 -4
- adapter_config.json +4 -4
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -35,15 +35,15 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- learning_rate:
|
39 |
- train_batch_size: 16
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
-
- gradient_accumulation_steps:
|
43 |
-
- total_train_batch_size:
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 1e-05
|
39 |
- train_batch_size: 16
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 64
|
43 |
+
- total_train_batch_size: 1024
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 4.0
|
47 |
|
48 |
### Training results
|
49 |
|
adapter_config.json
CHANGED
@@ -10,18 +10,18 @@
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
-
"lora_alpha":
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff04d359bd3f3884f76a699008110bfb5dba0f39495d199c3a1a8c675a76f436
|
3 |
+
size 109069176
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cd0176290873c5f31a9f07c67d182e12ee94c5ead73e09323e5bbc58f07094f
|
3 |
size 5432
|