mklissarov commited on
Commit
6a922eb
1 Parent(s): 12a3a93

Training in progress, step 14

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/paligemma-3b-mix-224",
3
+ "architectures": [
4
+ "PaliGemmaForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 2,
7
+ "eos_token_id": 1,
8
+ "hidden_size": 2048,
9
+ "ignore_index": -100,
10
+ "image_token_index": 257152,
11
+ "model_type": "paligemma",
12
+ "pad_token_id": 0,
13
+ "projection_dim": 2048,
14
+ "text_config": {
15
+ "hidden_size": 2048,
16
+ "intermediate_size": 16384,
17
+ "model_type": "gemma",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 18,
20
+ "num_image_tokens": 256,
21
+ "num_key_value_heads": 1,
22
+ "torch_dtype": "float32",
23
+ "vocab_size": 257216
24
+ },
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.43.0.dev0",
27
+ "vision_config": {
28
+ "hidden_size": 1152,
29
+ "intermediate_size": 4304,
30
+ "model_type": "siglip_vision_model",
31
+ "num_attention_heads": 16,
32
+ "num_hidden_layers": 27,
33
+ "num_image_tokens": 256,
34
+ "patch_size": 14,
35
+ "projection_dim": 2048,
36
+ "projector_hidden_act": "gelu_fast",
37
+ "vision_use_head": false
38
+ },
39
+ "vocab_size": 257216
40
+ }
runs/Jun27_22-25-33_6ecc2ffdea89/events.out.tfevents.1719527135.6ecc2ffdea89.281.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d00af70b164d01e934d27097c68ad1a3f2481c1c9d374b14ff36a277a95279
3
+ size 5604
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4b37b5ed7db9aed83fa2c40fc5b3a706a2a0a743273dcab2853faa25c7acdf
3
+ size 5176