Upload folder using huggingface_hub
Browse files- README.md +54 -0
- all_results.json +8 -0
- model-00001-of-00019.safetensors +3 -0
- model-00002-of-00019.safetensors +3 -0
- model-00003-of-00019.safetensors +3 -0
- model-00004-of-00019.safetensors +3 -0
- model-00005-of-00019.safetensors +3 -0
- model-00006-of-00019.safetensors +3 -0
- model-00007-of-00019.safetensors +3 -0
- model-00008-of-00019.safetensors +3 -0
- model-00009-of-00019.safetensors +3 -0
- model-00010-of-00019.safetensors +3 -0
- model-00011-of-00019.safetensors +3 -0
- model-00012-of-00019.safetensors +3 -0
- model-00013-of-00019.safetensors +3 -0
- model-00014-of-00019.safetensors +3 -0
- model-00015-of-00019.safetensors +3 -0
- model-00016-of-00019.safetensors +3 -0
- model-00017-of-00019.safetensors +3 -0
- model-00018-of-00019.safetensors +3 -0
- model-00019-of-00019.safetensors +3 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
tags:
|
4 |
+
- llama-factory
|
5 |
+
- full
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: scaleup_STEM_merged_10M_MOE_sft_0428_256
|
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 |
+
## Model description
|
16 |
+
|
17 |
+
More information needed
|
18 |
+
|
19 |
+
## Intended uses & limitations
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Training and evaluation data
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training procedure
|
28 |
+
|
29 |
+
### Training hyperparameters
|
30 |
+
|
31 |
+
The following hyperparameters were used during training:
|
32 |
+
- learning_rate: 5e-06
|
33 |
+
- train_batch_size: 4
|
34 |
+
- eval_batch_size: 8
|
35 |
+
- seed: 42
|
36 |
+
- distributed_type: multi-GPU
|
37 |
+
- num_devices: 256
|
38 |
+
- total_train_batch_size: 1024
|
39 |
+
- total_eval_batch_size: 2048
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: cosine
|
42 |
+
- lr_scheduler_warmup_ratio: 0.05
|
43 |
+
- num_epochs: 3.0
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.40.0
|
52 |
+
- Pytorch 2.3.0a0+40ec155e58.nv24.03
|
53 |
+
- Datasets 2.18.0
|
54 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 4.271915416263066e+16,
|
4 |
+
"train_loss": 0.3954192769085303,
|
5 |
+
"train_runtime": 93126.1025,
|
6 |
+
"train_samples_per_second": 70.83,
|
7 |
+
"train_steps_per_second": 0.069
|
8 |
+
}
|
model-00001-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5e52a34a2bbaf221fa35a10e5b52ef022fe32d45373d0664347ddd2fa221836
|
3 |
+
size 4892809584
|
model-00002-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0d33ea27253324c37d83c13a84779bfdbb78f08676c53e7af6fe1daef0a2820
|
3 |
+
size 4983004016
|
model-00003-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c659d265df682f0c04f74417b454577055a96408dd2c299e8ff8ebef9e8fe814
|
3 |
+
size 4983004016
|
model-00004-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c3cf01845abde048c2e09f3f58993b472b4dc6fe6b13e0657ad438e0d04fb41
|
3 |
+
size 4899035200
|
model-00005-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d4de45bf4528839cfce148cc578f9f5f5f3cf627e29ee0060c9102a73ddecec
|
3 |
+
size 4983004016
|
model-00006-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8705e4049624af211290d6d92870409fe9dc8524f97b480eafd234437cc5c99
|
3 |
+
size 4983004016
|
model-00007-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbc56f0029e4a923e7cd23377073b5f7dae62a3e65b536736a77cb05e8a77cce
|
3 |
+
size 4899035248
|
model-00008-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b0a037d215e9403d731182400eee370c48379cba2313b0c2798f374aed6bb76
|
3 |
+
size 4983004072
|
model-00009-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:749a46ea190874a99bfdb88abb59a05ba567046adbd66540ac24a699b4c88e5e
|
3 |
+
size 4983004072
|
model-00010-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8945749230c93f506d22dcf0c27b25976346eb143ebe9071acffdcc5dc5257e1
|
3 |
+
size 4899035248
|
model-00011-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01069c00a98ad1cdc711e823b961471584c3fbaf5b5c867fcc7be7f79b6f3f0e
|
3 |
+
size 4983004072
|
model-00012-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c88b407b327438b6bfa7489ec33102d7988b4c03935033b6ff2bcc001a10089
|
3 |
+
size 4983004072
|
model-00013-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb7da155beb3cc6a8d12b2ad8c5988f84d2afc62ab29f940e6d702a59dbbfd84
|
3 |
+
size 4983004072
|
model-00014-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d81012ed05e2945ca6519eed4da07f39869b0d8c6a41da49dbd24a5522fd552
|
3 |
+
size 4899035248
|
model-00015-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4f6a0e1b984d69d25823dab2fcff806d2a99787c4ffeb22e3d2dd05bfe923b6
|
3 |
+
size 4983004072
|
model-00016-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b762c941e33ad82c04e0b14e4ecf5249f05e9d9323d56e058f3cd25651741b2a
|
3 |
+
size 4983004072
|
model-00017-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de252cd0286e7882d9bd3e737373dc00baad61309786dd43b5f2cf2867a6c6d6
|
3 |
+
size 4899035248
|
model-00018-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1e224c6ad506c91a2b4e5752c04334a17f7a4eb17703adea2a0ce2c7c52bc0d
|
3 |
+
size 4983004072
|
model-00019-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad58f83d0dd4d67228c85cbe1f354cb0c2b7a91b7e80a3c375c4356b0eb73c70
|
3 |
+
size 4221679088
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 4.271915416263066e+16,
|
4 |
+
"train_loss": 0.3954192769085303,
|
5 |
+
"train_runtime": 93126.1025,
|
6 |
+
"train_samples_per_second": 70.83,
|
7 |
+
"train_steps_per_second": 0.069
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2bbf7579ab389ada54152ffdc3c45fda213695f93e668f3c5f733a613f44767
|
3 |
+
size 6904
|