jjovalle99
commited on
Commit
•
ede022b
1
Parent(s):
1924896
gemma7b-ft-lora-sql-v2adapters
Browse files- README.md +31 -15
- adapter_config.json +6 -6
- training_args.bin +1 -1
README.md
CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,29 +39,45 @@ More information needed
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
-
- learning_rate: 0.
|
43 |
-
- train_batch_size:
|
44 |
- eval_batch_size: 8
|
45 |
- seed: 1399
|
46 |
-
- gradient_accumulation_steps:
|
47 |
- total_train_batch_size: 32
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
-
- lr_scheduler_type:
|
50 |
-
- lr_scheduler_warmup_steps:
|
51 |
-
- training_steps:
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
|
66 |
|
67 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.4155
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.0003
|
43 |
+
- train_batch_size: 8
|
44 |
- eval_batch_size: 8
|
45 |
- seed: 1399
|
46 |
+
- gradient_accumulation_steps: 4
|
47 |
- total_train_batch_size: 32
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: cosine
|
50 |
+
- lr_scheduler_warmup_steps: 100
|
51 |
+
- training_steps: 500
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 16.1657 | 0.06 | 20 | 13.6485 |
|
58 |
+
| 7.8281 | 0.13 | 40 | 0.7808 |
|
59 |
+
| 0.6243 | 0.19 | 60 | 0.5270 |
|
60 |
+
| 0.5179 | 0.25 | 80 | 0.4859 |
|
61 |
+
| 0.4908 | 0.32 | 100 | 0.4754 |
|
62 |
+
| 0.4752 | 0.38 | 120 | 0.4600 |
|
63 |
+
| 0.4877 | 0.45 | 140 | 0.4584 |
|
64 |
+
| 0.4626 | 0.51 | 160 | 0.4560 |
|
65 |
+
| 0.4569 | 0.57 | 180 | 0.4428 |
|
66 |
+
| 0.4504 | 0.64 | 200 | 0.4354 |
|
67 |
+
| 0.4432 | 0.7 | 220 | 0.4348 |
|
68 |
+
| 0.4395 | 0.76 | 240 | 0.4317 |
|
69 |
+
| 0.4338 | 0.83 | 260 | 0.4256 |
|
70 |
+
| 0.4308 | 0.89 | 280 | 0.4260 |
|
71 |
+
| 0.4283 | 0.95 | 300 | 0.4210 |
|
72 |
+
| 0.4146 | 1.02 | 320 | 0.4225 |
|
73 |
+
| 0.3848 | 1.08 | 340 | 0.4186 |
|
74 |
+
| 0.3812 | 1.14 | 360 | 0.4185 |
|
75 |
+
| 0.38 | 1.21 | 380 | 0.4200 |
|
76 |
+
| 0.3795 | 1.27 | 400 | 0.4171 |
|
77 |
+
| 0.3766 | 1.34 | 420 | 0.4174 |
|
78 |
+
| 0.3772 | 1.4 | 440 | 0.4136 |
|
79 |
+
| 0.3777 | 1.46 | 460 | 0.4148 |
|
80 |
+
| 0.379 | 1.53 | 480 | 0.4155 |
|
81 |
|
82 |
|
83 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -10,22 +10,22 @@
|
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
"lora_alpha": 32,
|
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 |
"v_proj",
|
|
|
|
|
23 |
"o_proj",
|
24 |
"up_proj",
|
25 |
-
"gate_proj"
|
26 |
-
"k_proj",
|
27 |
-
"q_proj",
|
28 |
-
"down_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_dora": false,
|
|
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
"v_proj",
|
24 |
+
"down_proj",
|
25 |
+
"q_proj",
|
26 |
"o_proj",
|
27 |
"up_proj",
|
28 |
+
"gate_proj"
|
|
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_dora": false,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f90e03f124eede9ebe92ac2a7cb4cd187068b1c799e0422942648c31ca3de583
|
3 |
size 4920
|