zixianma commited on
Commit
d566840
1 Parent(s): 1fab62a

Model save

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: HuggingFaceM4/idefics2-8b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: idefics2_8b_cont_100k_8192
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # idefics2_8b_cont_100k_8192
15
+
16
+ This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-06
36
+ - train_batch_size: 1
37
+ - eval_batch_size: 1
38
+ - seed: 42
39
+ - distributed_type: multi-GPU
40
+ - num_devices: 16
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 128
43
+ - total_eval_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.03
47
+ - num_epochs: 5.0
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.43.3
56
+ - Pytorch 2.4.0+cu121
57
+ - Datasets 2.18.0
58
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 32000
6
+ ],
7
+ [
8
+ 32001
9
+ ]
10
+ ],
11
+ "bos_token_id": 1,
12
+ "eos_token_id": [
13
+ 2,
14
+ 32002
15
+ ],
16
+ "pad_token_id": 0,
17
+ "transformers_version": "4.43.3"
18
+ }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bca7c596a3ef6f55ed79ba896a46c71ba7e5350283728872e4dd97041a8f342
3
  size 4966706832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3169481181f98a1ddf67716279e3900cbd327c3b80e43d972bea02a8217d021f
3
  size 4966706832
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20b2ba66d118409e43228913663ef1f68ba6a2e90a588002b993eef290f902d8
3
  size 4915917232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d16c48043246a6c679201917874128f101237b74e25068a31c41f9a163992c65
3
  size 4915917232
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c04e10e44830d9a5bc2d7dcfba24354be9c2fedbb8e9c757af128c8c2baf794
3
  size 4999820504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a82a0538098f10501c514c465ce7abaedbce40517597df7a00585a169f81ec
3
  size 4999820504
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6916ed546bd4eae8b2ae85ced5fbdb0a0e54ea850e4347f82fcde937cc96795b
3
  size 1923190976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30bcbba49c003a89d6335f797cc14df741bbe20ce2cf7036650acaee83fa3569
3
  size 1923190976