srihariEmids
commited on
Commit
•
a7de9b6
1
Parent(s):
a794de4
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: microsoft/phi-1_5
|
7 |
+
model-index:
|
8 |
+
- name: phi-1_5-finetuned-emids-text
|
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 |
+
# phi-1_5-finetuned-emids-text
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) 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 |
+
|
34 |
+
The following `bitsandbytes` quantization config was used during training:
|
35 |
+
- quant_method: bitsandbytes
|
36 |
+
- load_in_8bit: False
|
37 |
+
- load_in_4bit: True
|
38 |
+
- llm_int8_threshold: 6.0
|
39 |
+
- llm_int8_skip_modules: None
|
40 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
41 |
+
- llm_int8_has_fp16_weight: False
|
42 |
+
- bnb_4bit_quant_type: nf4
|
43 |
+
- bnb_4bit_use_double_quant: True
|
44 |
+
- bnb_4bit_compute_dtype: float16
|
45 |
+
|
46 |
+
### Training hyperparameters
|
47 |
+
|
48 |
+
The following hyperparameters were used during training:
|
49 |
+
- learning_rate: 0.0002
|
50 |
+
- train_batch_size: 4
|
51 |
+
- eval_batch_size: 8
|
52 |
+
- seed: 42
|
53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
+
- lr_scheduler_type: cosine
|
55 |
+
- training_steps: 1000
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- PEFT 0.7.0
|
64 |
+
- Transformers 4.36.0
|
65 |
+
- Pytorch 2.1.0+cu118
|
66 |
+
- Datasets 2.15.0
|
67 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/phi-1_5",
|
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": 16,
|
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": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"out_proj",
|
23 |
+
"Wqkv"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e6916b49b9ea7cd6c1cdabc6c06567661709e53898f425f46fa69d93de77a97
|
3 |
+
size 18886928
|
runs/Dec12_12-21-27_84381c7146fb/events.out.tfevents.1702383690.84381c7146fb.277.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6d1aa39e5d8e51323e4f74bf40194267bc65fb52ce18ab3a22e24c6d305cb63
|
3 |
+
size 6815
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7f98495648da8ac12ba63aa85f462329221bd40d4e44383488fc97bbeefb3fe
|
3 |
+
size 4728
|