Training in progress, step 1000
Browse files
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/paligemma-3b-pt-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": "4.42.0.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/May23_10-52-45_52805fca3fd5/events.out.tfevents.1716461571.52805fca3fd5.1530.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f2b9e19b7b044a4056eba291085377fe1cf551fa4f33f2c355274ce1a362b19
|
3 |
+
size 7278
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07a9a758a14ce13ed22cceba4e3bb76d00942c3e1da6a18c2a3b7e447a0fb8ab
|
3 |
+
size 5112
|