Commit
•
937ed2a
1
Parent(s):
248877e
AHS_SPO_FAQ_LM_V_2.0
Browse files- README.md +58 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720112904.2d713d9f225b.96.0 +3 -0
- runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113148.2d713d9f225b.96.1 +3 -0
- runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113348.2d713d9f225b.96.2 +3 -0
- runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113552.2d713d9f225b.96.3 +3 -0
- runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113756.2d713d9f225b.96.4 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.1
|
7 |
+
model-index:
|
8 |
+
- name: peft-InstructionTuning-training-1720112861
|
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 |
+
# peft-InstructionTuning-training-1720112861
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.1](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.1) on an unknown 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: 0.0003
|
37 |
+
- train_batch_size: 4
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 4
|
41 |
+
- total_train_batch_size: 16
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 100
|
45 |
+
- num_epochs: 3
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- PEFT 0.11.1
|
55 |
+
- Transformers 4.41.2
|
56 |
+
- Pytorch 2.1.2
|
57 |
+
- Datasets 2.19.2
|
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": "TinyLlama/TinyLlama-1.1B-Chat-v0.1",
|
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": 16,
|
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 sha256:02ba21fe3af48ae984ad31bb081440e69e2579470eb3083f92f43d9c6be4d724
|
3 |
+
size 9022864
|
runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720112904.2d713d9f225b.96.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed5fd67561401d215286bb5ad1e817434a3190aeb12121d8569c808fd7e6c00a
|
3 |
+
size 6411
|
runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113148.2d713d9f225b.96.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:840bdac9e2969412866f7e6286fe542ca3b64aad16aeac0508be3d2c74e31f76
|
3 |
+
size 6411
|
runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113348.2d713d9f225b.96.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf812100c52bd67dfc454fdb4935aea709dd842a5e8b476dcd11599d1b147a5a
|
3 |
+
size 6411
|
runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113552.2d713d9f225b.96.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd50541512b3483542c49d186b30505c3ec50ffcd8d52b6e9fe54c4bdca64051
|
3 |
+
size 6411
|
runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113756.2d713d9f225b.96.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8e35424ace99a92c4eb42cc064436437cb2e2ac934298959a4f8c7ee9ade596
|
3 |
+
size 6411
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:973019056e78d13cc5f3e6112379d4abca2ae58cb5e4c5959373f0bdb431d083
|
3 |
+
size 5368
|