llm/llama38binstruct-summary-100s
Browse files- README.md +21 -11
- adapter_config.json +6 -6
- adapter_model.safetensors +1 -1
- runs/Jun19_02-06-52_0113f146e29c/events.out.tfevents.1718762822.0113f146e29c.1122.0 +3 -0
- runs/Jun19_02-15-31_0113f146e29c/events.out.tfevents.1718763345.0113f146e29c.1122.1 +3 -0
- runs/Jun19_02-30-55_0113f146e29c/events.out.tfevents.1718764264.0113f146e29c.1122.2 +3 -0
- runs/Jun19_02-31-44_0113f146e29c/events.out.tfevents.1718764313.0113f146e29c.1122.3 +3 -0
- runs/Jun19_02-32-38_0113f146e29c/events.out.tfevents.1718764370.0113f146e29c.1122.4 +3 -0
- runs/Jun19_02-40-57_0113f146e29c/events.out.tfevents.1718764865.0113f146e29c.1122.5 +3 -0
- training_args.bin +2 -2
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 [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,23 +39,33 @@ 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: 42
|
|
|
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: constant
|
48 |
-
- lr_scheduler_warmup_steps:
|
49 |
-
- training_steps:
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch
|
54 |
-
|
55 |
-
|
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 3.2478
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.0001
|
43 |
+
- train_batch_size: 2
|
44 |
- eval_batch_size: 8
|
45 |
- seed: 42
|
46 |
+
- gradient_accumulation_steps: 4
|
47 |
+
- total_train_batch_size: 8
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: constant
|
50 |
+
- lr_scheduler_warmup_steps: 10
|
51 |
+
- training_steps: 300
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 0.0063 | 10.0 | 25 | 2.9544 |
|
58 |
+
| 0.0033 | 20.0 | 50 | 3.1133 |
|
59 |
+
| 0.0057 | 30.0 | 75 | 2.5821 |
|
60 |
+
| 0.0032 | 40.0 | 100 | 2.9857 |
|
61 |
+
| 0.0021 | 50.0 | 125 | 3.1502 |
|
62 |
+
| 0.0019 | 60.0 | 150 | 3.0546 |
|
63 |
+
| 0.0026 | 70.0 | 175 | 2.7894 |
|
64 |
+
| 0.0045 | 80.0 | 200 | 2.6616 |
|
65 |
+
| 0.0014 | 90.0 | 225 | 3.1916 |
|
66 |
+
| 0.0009 | 100.0 | 250 | 3.2146 |
|
67 |
+
| 0.0007 | 110.0 | 275 | 3.2346 |
|
68 |
+
| 0.0006 | 120.0 | 300 | 3.2478 |
|
69 |
|
70 |
|
71 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -11,7 +11,7 @@
|
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
"lora_alpha": 32,
|
14 |
-
"lora_dropout": 0.
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"k_proj",
|
25 |
-
"o_proj",
|
26 |
-
"up_proj",
|
27 |
"gate_proj",
|
|
|
28 |
"q_proj",
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.15,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
|
|
|
|
|
|
24 |
"gate_proj",
|
25 |
+
"up_proj",
|
26 |
"q_proj",
|
27 |
+
"down_proj",
|
28 |
+
"o_proj",
|
29 |
+
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef728538a619ab3e4f2aa024958451bbd939b654cde566a8a811535264e05487
|
3 |
size 167832240
|
runs/Jun19_02-06-52_0113f146e29c/events.out.tfevents.1718762822.0113f146e29c.1122.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:094df86ed11868930002e1c74849f41f0d70840b82c458b1532a133e949ac51c
|
3 |
+
size 17092
|
runs/Jun19_02-15-31_0113f146e29c/events.out.tfevents.1718763345.0113f146e29c.1122.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b53dd431bcb936ce2afafe7e31be680510d4fcc461ee0a43e5dda7179f86f6b
|
3 |
+
size 6851
|
runs/Jun19_02-30-55_0113f146e29c/events.out.tfevents.1718764264.0113f146e29c.1122.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4f7b77901cc418cfa4a0cda79380d198fe7eaeeb52cb3bc204e0cb06aee6bda
|
3 |
+
size 5758
|
runs/Jun19_02-31-44_0113f146e29c/events.out.tfevents.1718764313.0113f146e29c.1122.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2da19f81b750f56cfd1c1d4ca7f110582d7bbf59dcc4c328692e1838399cc3e4
|
3 |
+
size 5756
|
runs/Jun19_02-32-38_0113f146e29c/events.out.tfevents.1718764370.0113f146e29c.1122.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3e209dd08b935cacb92d4c27125ab2abbfe957487923be4af4e34122d356603
|
3 |
+
size 6171
|
runs/Jun19_02-40-57_0113f146e29c/events.out.tfevents.1718764865.0113f146e29c.1122.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eda9984f2289eeb32a8de11a244dd3bc1288c502ce42de818fbf429f8370f5b2
|
3 |
+
size 15618
|
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:da7ab063a3e2ac331c4fbea43e632b2ee7ef1029442c59327726294ac03a99a1
|
3 |
+
size 5432
|