End of training
Browse files- README.md +79 -0
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: microsoft/phi-2
|
7 |
+
model-index:
|
8 |
+
- name: phi2-dolly-sum-finetune
|
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 |
+
# phi2-dolly-sum-finetune
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.0505
|
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: 2.5e-05
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 1
|
45 |
+
- training_steps: 500
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 2.9329 | 0.05 | 25 | 2.4178 |
|
52 |
+
| 2.4832 | 0.09 | 50 | 2.1541 |
|
53 |
+
| 2.1688 | 0.14 | 75 | 2.0774 |
|
54 |
+
| 2.2247 | 0.18 | 100 | 2.0725 |
|
55 |
+
| 2.225 | 0.23 | 125 | 2.0652 |
|
56 |
+
| 2.2217 | 0.27 | 150 | 2.0635 |
|
57 |
+
| 2.2282 | 0.32 | 175 | 2.0611 |
|
58 |
+
| 2.1104 | 0.37 | 200 | 2.0608 |
|
59 |
+
| 2.1583 | 0.41 | 225 | 2.0569 |
|
60 |
+
| 2.1197 | 0.46 | 250 | 2.0565 |
|
61 |
+
| 2.1257 | 0.5 | 275 | 2.0559 |
|
62 |
+
| 2.0018 | 0.55 | 300 | 2.0512 |
|
63 |
+
| 2.0203 | 0.6 | 325 | 2.0546 |
|
64 |
+
| 2.1332 | 0.64 | 350 | 2.0519 |
|
65 |
+
| 2.1585 | 0.69 | 375 | 2.0503 |
|
66 |
+
| 2.1287 | 0.73 | 400 | 2.0510 |
|
67 |
+
| 2.1431 | 0.78 | 425 | 2.0515 |
|
68 |
+
| 2.1601 | 0.82 | 450 | 2.0522 |
|
69 |
+
| 2.088 | 0.87 | 475 | 2.0481 |
|
70 |
+
| 2.0462 | 0.92 | 500 | 2.0505 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- PEFT 0.8.1
|
76 |
+
- Transformers 4.37.2
|
77 |
+
- Pytorch 2.2.0+cu121
|
78 |
+
- Datasets 2.16.1
|
79 |
+
- Tokenizers 0.15.1
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/phi-2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 64,
|
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": 32,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"fc2",
|
23 |
+
"fc1",
|
24 |
+
"Wqkv"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0b9c1d7cb0c6fa99c432b0173229690709caf247979a056e5a32c4f195849f6
|
3 |
+
size 104873776
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd369a7da5eeea6d26b76d19c3ef05842502b1643cf4465f0b9d6c02c3e20404
|
3 |
+
size 4664
|