paragon-analytics
commited on
Commit
•
4e64fc6
1
Parent(s):
49b485d
paragon-analytics/Llama318bseries
Browse files- README.md +58 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- runs/Sep15_12-01-00_udc-an34-1/events.out.tfevents.1726416087.udc-an34-1.571518.0 +3 -0
- runs/Sep15_12-17-33_udc-an34-19/events.out.tfevents.1726417062.udc-an34-19.247014.0 +3 -0
- runs/Sep15_12-51-18_udc-an34-19/events.out.tfevents.1726419082.udc-an34-19.254018.0 +3 -0
- runs/Sep15_12-53-27_udc-an34-19/events.out.tfevents.1726419207.udc-an34-19.254018.1 +3 -0
- runs/Sep15_12-53-46_udc-an34-19/events.out.tfevents.1726419227.udc-an34-19.254018.2 +3 -0
- runs/Sep15_12-54-15_udc-an34-19/events.out.tfevents.1726419255.udc-an34-19.254018.3 +3 -0
- runs/Sep15_12-56-31_udc-an34-19/events.out.tfevents.1726419395.udc-an34-19.256617.0 +3 -0
- runs/Sep15_12-59-35_udc-an34-19/events.out.tfevents.1726419575.udc-an34-19.256617.1 +3 -0
- runs/Sep15_13-00-26_udc-an34-19/events.out.tfevents.1726419626.udc-an34-19.256617.2 +3 -0
- runs/Sep15_13-00-41_udc-an34-19/events.out.tfevents.1726419642.udc-an34-19.256617.3 +3 -0
- runs/Sep15_13-03-37_udc-an34-19/events.out.tfevents.1726419822.udc-an34-19.258412.0 +3 -0
- runs/Sep15_13-19-41_udc-an34-19/events.out.tfevents.1726420782.udc-an34-19.261680.0 +3 -0
- runs/Sep15_13-59-14_udc-an34-19/events.out.tfevents.1726423155.udc-an34-19.272078.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B
|
3 |
+
library_name: peft
|
4 |
+
license: llama3.1
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: results
|
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 |
+
# results
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the None 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: 5e-05
|
37 |
+
- train_batch_size: 1
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 16
|
41 |
+
- total_train_batch_size: 16
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: cosine
|
44 |
+
- lr_scheduler_warmup_steps: 100
|
45 |
+
- num_epochs: 1
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- PEFT 0.12.0
|
55 |
+
- Transformers 4.43.1
|
56 |
+
- Pytorch 2.3.1+cu121
|
57 |
+
- Datasets 3.0.0
|
58 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
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": 8,
|
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,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deb01f876db7f8ba653710e2be34de5346501ed4d0765350cca7e12558a875e5
|
3 |
+
size 13648432
|
runs/Sep15_12-01-00_udc-an34-1/events.out.tfevents.1726416087.udc-an34-1.571518.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:080e21f9c92d3161480cabee5159a234a8147341348ebdc256f97346de7c59a3
|
3 |
+
size 5890
|
runs/Sep15_12-17-33_udc-an34-19/events.out.tfevents.1726417062.udc-an34-19.247014.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fd03bbd3188c79a3b34d3fcf1550a9d7f2df42ca9716ad6109e7e0005a71a0e
|
3 |
+
size 5891
|
runs/Sep15_12-51-18_udc-an34-19/events.out.tfevents.1726419082.udc-an34-19.254018.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0a0443508e99c86e0e89c70aaafd340add503850acf3309b91b16cbc3f17022
|
3 |
+
size 5052
|
runs/Sep15_12-53-27_udc-an34-19/events.out.tfevents.1726419207.udc-an34-19.254018.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aec78fc4ce95117ab78581b92c2ddb44f45dd4cdd095ac470f3fe97db2943a3
|
3 |
+
size 5053
|
runs/Sep15_12-53-46_udc-an34-19/events.out.tfevents.1726419227.udc-an34-19.254018.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230fb3b5525296e67dc489a854a302beb4f415d139c608b7b6e2eacbc97bac67
|
3 |
+
size 5053
|
runs/Sep15_12-54-15_udc-an34-19/events.out.tfevents.1726419255.udc-an34-19.254018.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3d15d5ced4cde547de919c6a5b8127b4a60fa156a62c9c2f30a4b46b95c796e
|
3 |
+
size 5053
|
runs/Sep15_12-56-31_udc-an34-19/events.out.tfevents.1726419395.udc-an34-19.256617.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:378330c5daaad55f4db4d521316c20a070856efc17599bf4abf919e8ea59fd04
|
3 |
+
size 5053
|
runs/Sep15_12-59-35_udc-an34-19/events.out.tfevents.1726419575.udc-an34-19.256617.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bac8d5d5812c5a4232ef187b6e9d6302cae29d92ef01450fe6d5c19d464aaac6
|
3 |
+
size 5053
|
runs/Sep15_13-00-26_udc-an34-19/events.out.tfevents.1726419626.udc-an34-19.256617.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5dff877e9b61dfe62d11db089f7736ba220e38cf94ecc0ef50a9b4726b0df50
|
3 |
+
size 5053
|
runs/Sep15_13-00-41_udc-an34-19/events.out.tfevents.1726419642.udc-an34-19.256617.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38f98e869ab883571ec0677de2ce97b9d5875aec3a5d03f5046ad2341f5a9e6a
|
3 |
+
size 5053
|
runs/Sep15_13-03-37_udc-an34-19/events.out.tfevents.1726419822.udc-an34-19.258412.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3292eb91ff63874964c1c98a1e01d0f2c8eea08eecc5e859f7eb32ab9d593f3
|
3 |
+
size 5053
|
runs/Sep15_13-19-41_udc-an34-19/events.out.tfevents.1726420782.udc-an34-19.261680.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74237853b61e23fdf05488a932325042b078f8056409f913ce1be32215f1b600
|
3 |
+
size 5891
|
runs/Sep15_13-59-14_udc-an34-19/events.out.tfevents.1726423155.udc-an34-19.272078.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2225ffc39fd44e5ef2362aab68c1c3a19d697ea1f783a8004fedbb1e0b02218f
|
3 |
+
size 5891
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e5c9e4aea5635000aa5ad9c0e52775c3ff78235736ddd999ad785e31386327e
|
3 |
+
size 5176
|