CennetOguz
commited on
Commit
•
c74c105
1
Parent(s):
fbc0355
Training in progress, step 6000
Browse files- README.md +58 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- runs/Sep10_23-13-42_serv-9221/events.out.tfevents.1726002825.serv-9221 +3 -0
- runs/Sep10_23-26-48_serv-9222/events.out.tfevents.1726003612.serv-9222 +3 -0
- runs/Sep11_00-10-23_serv-9222/events.out.tfevents.1726006227.serv-9222 +3 -0
- runs/Sep11_12-28-05_serv-3337/events.out.tfevents.1726050489.serv-3337 +3 -0
- runs/Sep11_20-28-05_serv-9222/events.out.tfevents.1726079288.serv-9222 +3 -0
- runs/Sep11_21-24-33_serv-9222/events.out.tfevents.1726082676.serv-9222 +3 -0
- runs/Sep11_21-25-50_serv-9222/events.out.tfevents.1726082752.serv-9222 +3 -0
- runs/Sep11_21-26-40_serv-9222/events.out.tfevents.1726082803.serv-9222 +3 -0
- runs/Sep11_21-27-39_serv-9222/events.out.tfevents.1726082862.serv-9222 +3 -0
- runs/Sep11_21-29-06_serv-9222/events.out.tfevents.1726082948.serv-9222 +3 -0
- runs/Sep12_13-28-38_serv-9222/events.out.tfevents.1726140523.serv-9222 +3 -0
- runs/Sep12_13-32-44_serv-9222/events.out.tfevents.1726140767.serv-9222 +3 -0
- runs/Sep12_13-38-47_serv-9222/events.out.tfevents.1726141130.serv-9222 +3 -0
- runs/Sep12_13-41-22_serv-9222/events.out.tfevents.1726141285.serv-9222 +3 -0
- runs/Sep12_13-51-04_serv-3338/events.out.tfevents.1726141869.serv-3338 +3 -0
- runs/Sep12_14-15-16_serv-9222/events.out.tfevents.1726143319.serv-9222 +3 -0
- runs/Sep12_22-56-52_serv-3334/events.out.tfevents.1726174617.serv-3334 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: google/paligemma-3b-mix-224
|
3 |
+
library_name: peft
|
4 |
+
license: gemma
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: paligemma_yc3
|
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 |
+
# paligemma_yc3
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [google/paligemma-3b-mix-224](https://huggingface.co/google/paligemma-3b-mix-224) 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: 2e-05
|
37 |
+
- train_batch_size: 1
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- distributed_type: multi-GPU
|
41 |
+
- gradient_accumulation_steps: 4
|
42 |
+
- total_train_batch_size: 4
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 2
|
46 |
+
- num_epochs: 5
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- PEFT 0.12.0
|
55 |
+
- Transformers 4.44.2
|
56 |
+
- Pytorch 2.4.1+cu121
|
57 |
+
- Datasets 2.21.0
|
58 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/paligemma-3b-mix-224",
|
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": 8,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"up_proj",
|
26 |
+
"o_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj",
|
29 |
+
"k_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e40cd0946c7a25a449ef5078e0b00f4673d5b29452c89892c1feef03599b3e07
|
3 |
+
size 45258384
|
runs/Sep10_23-13-42_serv-9221/events.out.tfevents.1726002825.serv-9221
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:791bd6576bb872bf138860305fd8acfa9b884deaeb42d08509332ca36f97e833
|
3 |
+
size 6219
|
runs/Sep10_23-26-48_serv-9222/events.out.tfevents.1726003612.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35d961276407d8c13a3891da397cde253fbd1846f4aaf493eafccdc7d12410ad
|
3 |
+
size 5665
|
runs/Sep11_00-10-23_serv-9222/events.out.tfevents.1726006227.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6395a01b01703eb74b0eb12f46a33975cd741608ef89f540266dbb48408e6b3e
|
3 |
+
size 20641
|
runs/Sep11_12-28-05_serv-3337/events.out.tfevents.1726050489.serv-3337
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53eb8a78697a36f657b774015a74bc388be0fbcf996256aa835a0468038e1685
|
3 |
+
size 50518
|
runs/Sep11_20-28-05_serv-9222/events.out.tfevents.1726079288.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66f7eb92cc90b6b062af4a5be17737443722b7a6d902d71f1bada1bb63a90701
|
3 |
+
size 6219
|
runs/Sep11_21-24-33_serv-9222/events.out.tfevents.1726082676.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9765a247b1172a1fe38c1d48393e756dfc94dedf5b2babfbe6082edeb84b86b4
|
3 |
+
size 5664
|
runs/Sep11_21-25-50_serv-9222/events.out.tfevents.1726082752.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bbb1ec7a76df451d98ae1cddd733d344013b3943dd708121312644ebff9146d
|
3 |
+
size 5664
|
runs/Sep11_21-26-40_serv-9222/events.out.tfevents.1726082803.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:358dee1d1f2327cda84ee2eb9ffb075e858d63bc39e0e96694620850a8681960
|
3 |
+
size 5664
|
runs/Sep11_21-27-39_serv-9222/events.out.tfevents.1726082862.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8121e23fa95e5e5b7a85d117c83481c9eebdc42ee0096d75d1f7f39f3d18ef92
|
3 |
+
size 5664
|
runs/Sep11_21-29-06_serv-9222/events.out.tfevents.1726082948.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a8c546df60094ab1c51586f244d33efabef0b3d4715bd34a07d51f2b0bb3006
|
3 |
+
size 5664
|
runs/Sep12_13-28-38_serv-9222/events.out.tfevents.1726140523.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da9d079a4b9326ce907e91f0eefb8242b5a0b48cc9257fb88e47e69128cb1d01
|
3 |
+
size 5664
|
runs/Sep12_13-32-44_serv-9222/events.out.tfevents.1726140767.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ec75ab000bf73f90f1a9a03923808f5556ea0166bbd9334a2140550f45b425c
|
3 |
+
size 5664
|
runs/Sep12_13-38-47_serv-9222/events.out.tfevents.1726141130.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9b24a3479cf6f6c28b562c63f580a2d473191ec64511011877b2fe2004c067d
|
3 |
+
size 5664
|
runs/Sep12_13-41-22_serv-9222/events.out.tfevents.1726141285.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b65815a52cf77747566099d463aa5532f8e364c232a29b64e210206e6ed605a3
|
3 |
+
size 6082
|
runs/Sep12_13-51-04_serv-3338/events.out.tfevents.1726141869.serv-3338
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4476f0d304615fc1aaaa535fcca8af91b7d90fb7930725d5580c10896f358852
|
3 |
+
size 7770
|
runs/Sep12_14-15-16_serv-9222/events.out.tfevents.1726143319.serv-9222
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e052c88ec3ada8b63262ca4a882993cb7dc4d8f83886ebfc74ff764bae375ac2
|
3 |
+
size 28659
|
runs/Sep12_22-56-52_serv-3334/events.out.tfevents.1726174617.serv-3334
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e47046b987f1f9252411855d67a511b245a1f70b6b9ba6a3c4e082739eccfbc5
|
3 |
+
size 18143
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be562583223b735e28f39575afb7fbc83b03d98fa0f38eb9619b321199cac67f
|
3 |
+
size 5176
|