Jaykumaran17
commited on
Commit
·
0cb9e1b
1
Parent(s):
91cde3f
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: HuggingFaceH4/zephyr-7b-beta
|
7 |
+
model-index:
|
8 |
+
- name: Zephyr-Try2-17-12
|
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 |
+
# Zephyr-Try2-17-12
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) 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: 0.0003
|
37 |
+
- train_batch_size: 16
|
38 |
+
- eval_batch_size: 16
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: cosine
|
42 |
+
- lr_scheduler_warmup_steps: 150
|
43 |
+
- num_epochs: 2
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.36.1
|
53 |
+
- Pytorch 2.0.0
|
54 |
+
- Datasets 2.15.0
|
55 |
+
- Tokenizers 0.15.0
|
56 |
+
## Training procedure
|
57 |
+
|
58 |
+
|
59 |
+
The following `bitsandbytes` quantization config was used during training:
|
60 |
+
- quant_method: bitsandbytes
|
61 |
+
- load_in_8bit: False
|
62 |
+
- load_in_4bit: True
|
63 |
+
- llm_int8_threshold: 6.0
|
64 |
+
- llm_int8_skip_modules: None
|
65 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
66 |
+
- llm_int8_has_fp16_weight: False
|
67 |
+
- bnb_4bit_quant_type: nf4
|
68 |
+
- bnb_4bit_use_double_quant: True
|
69 |
+
- bnb_4bit_compute_dtype: bfloat16
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
|
74 |
+
- PEFT 0.6.2
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:338b655f203dec30ddb81a568864f44696b5627692e82032db5793439a304856
|
3 |
+
size 113314765
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 113271504
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34219819c440bba175b392a94731b266a2c00144993a2c707e6554d1ded861df
|
3 |
size 113271504
|
runs/Dec17_09-54-11_c514349ff8e8/events.out.tfevents.1702806873.c514349ff8e8.42.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c87bae8511a927da37f195a39704961a2827d5dcae83b7669f1e4888352ce02
|
3 |
+
size 13765
|