Fine-tuned model configurations for incident response playbooks model
Browse files- README.md +76 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- runs/Jul25_12-17-34_TRj226-IW-Dell/events.out.tfevents.1721906270.TRj226-IW-Dell.25260.0 +3 -0
- runs/Jul25_13-32-21_TRj226-IW-Dell/events.out.tfevents.1721910755.TRj226-IW-Dell.17200.0 +3 -0
- runs/Jul25_13-43-30_TRj226-IW-Dell/events.out.tfevents.1721911427.TRj226-IW-Dell.26764.0 +3 -0
- runs/Jul25_18-26-15_TRj226-IW-Dell/events.out.tfevents.1721928395.TRj226-IW-Dell.45664.0 +3 -0
- runs/Jul25_18-41-46_TRj226-IW-Dell/events.out.tfevents.1721929314.TRj226-IW-Dell.45664.1 +3 -0
- runs/Jul25_20-01-21_TRj226-IW-Dell/events.out.tfevents.1721934105.TRj226-IW-Dell.16720.0 +3 -0
- runs/Jul25_20-48-37_TRj226-IW-Dell/events.out.tfevents.1721936957.TRj226-IW-Dell.41908.0 +3 -0
- runs/Jul25_21-43-28_TRj226-IW-Dell/events.out.tfevents.1721940219.TRj226-IW-Dell.10072.0 +3 -0
- runs/Jul29_13-48-04_TRj226-IW-Dell/events.out.tfevents.1722257285.TRj226-IW-Dell.45964.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Llama-2-7b-chat-hf
|
3 |
+
library_name: peft
|
4 |
+
license: llama2
|
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/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.0651
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0002
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 8
|
43 |
+
- total_train_batch_size: 8
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 2
|
47 |
+
- training_steps: 75
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
53 |
+
| 1.9743 | 0.8163 | 5 | 1.9198 |
|
54 |
+
| 1.8581 | 1.6327 | 10 | 1.7523 |
|
55 |
+
| 1.5766 | 2.4490 | 15 | 1.5925 |
|
56 |
+
| 1.4205 | 3.2653 | 20 | 1.4522 |
|
57 |
+
| 1.3769 | 4.0816 | 25 | 1.3597 |
|
58 |
+
| 1.1971 | 4.8980 | 30 | 1.2998 |
|
59 |
+
| 1.1704 | 5.7143 | 35 | 1.2477 |
|
60 |
+
| 1.128 | 6.5306 | 40 | 1.2061 |
|
61 |
+
| 1.0483 | 7.3469 | 45 | 1.1649 |
|
62 |
+
| 1.017 | 8.1633 | 50 | 1.1308 |
|
63 |
+
| 0.8937 | 8.9796 | 55 | 1.1093 |
|
64 |
+
| 0.8445 | 9.7959 | 60 | 1.0892 |
|
65 |
+
| 0.8322 | 10.6122 | 65 | 1.0763 |
|
66 |
+
| 0.926 | 11.4286 | 70 | 1.0652 |
|
67 |
+
| 0.7692 | 12.2449 | 75 | 1.0651 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- PEFT 0.11.2.dev0
|
73 |
+
- Transformers 4.43.0.dev0
|
74 |
+
- Pytorch 2.3.1+cu121
|
75 |
+
- Datasets 2.20.0
|
76 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
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": 4,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj",
|
25 |
+
"k_proj",
|
26 |
+
"o_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5441926541e35c9a647561e3e4c58a0f053c72e0fa1d4cd9cd3f48f7e5114fb5
|
3 |
+
size 16811144
|
runs/Jul25_12-17-34_TRj226-IW-Dell/events.out.tfevents.1721906270.TRj226-IW-Dell.25260.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e934f95a81bba4c782b264884b7d5acfec2ce40de7a4a160c1b4d25cfcdedc72
|
3 |
+
size 9928
|
runs/Jul25_13-32-21_TRj226-IW-Dell/events.out.tfevents.1721910755.TRj226-IW-Dell.17200.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0524f7b70e7e35b2e334b225e2e7bfadbf6dd0ac7ded07c11d88fc9099e3628e
|
3 |
+
size 5440
|
runs/Jul25_13-43-30_TRj226-IW-Dell/events.out.tfevents.1721911427.TRj226-IW-Dell.26764.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e46796fed5ee73bd604113847a6ff2809ccb94320945e56dc345516e4ad9ff04
|
3 |
+
size 5440
|
runs/Jul25_18-26-15_TRj226-IW-Dell/events.out.tfevents.1721928395.TRj226-IW-Dell.45664.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05f19c342516cffb17cd99ad9776d542b8b754056c2b213592579e7b3b15362c
|
3 |
+
size 5440
|
runs/Jul25_18-41-46_TRj226-IW-Dell/events.out.tfevents.1721929314.TRj226-IW-Dell.45664.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:047ab7a8d0e99bf581c0f74eb517a51c75a3254da775227ab0c71d7e2ecb91da
|
3 |
+
size 9928
|
runs/Jul25_20-01-21_TRj226-IW-Dell/events.out.tfevents.1721934105.TRj226-IW-Dell.16720.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6918eb14ad12b9fc75c672a883ee9d2a5d825ed96dc5df9d3b95c788466f62b
|
3 |
+
size 9928
|
runs/Jul25_20-48-37_TRj226-IW-Dell/events.out.tfevents.1721936957.TRj226-IW-Dell.41908.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00ccf2414ea4ff95861eeb344b2a4b39eabdec564cc8685a948e25af8e9e13af
|
3 |
+
size 9928
|
runs/Jul25_21-43-28_TRj226-IW-Dell/events.out.tfevents.1721940219.TRj226-IW-Dell.10072.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:927239ba42265d09760b904ae9bcc87950a8ad55e8cf0d67c68decc17299972c
|
3 |
+
size 9928
|
runs/Jul29_13-48-04_TRj226-IW-Dell/events.out.tfevents.1722257285.TRj226-IW-Dell.45964.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f18ca431542299bdc89996d68a61fb549451836e72360b0c899e50c7351dfd5
|
3 |
+
size 7858
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": false,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:606aa44cff209d1320d4f8bfacc24d94f559327eff8822693be21a27d18585d9
|
3 |
+
size 5112
|