Training in progress, step 500
Browse files
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BridgeTower/bridgetower-large-itm-mlm-itc",
|
3 |
+
"architectures": [
|
4 |
+
"BridgeTowerForContrastiveLearning"
|
5 |
+
],
|
6 |
+
"contrastive_hidden_size": 512,
|
7 |
+
"drop_rate": 0.1,
|
8 |
+
"head_hidden_scale": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"init_layernorm_from_vision_encoder": false,
|
12 |
+
"initializer_factor": 1,
|
13 |
+
"layer_norm_eps": 1e-05,
|
14 |
+
"link_tower_type": "add",
|
15 |
+
"logit_scale_init_value": 2.6592,
|
16 |
+
"model_type": "bridgetower",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"share_cross_modal_transformer_layers": true,
|
20 |
+
"share_link_tower_layers": false,
|
21 |
+
"text_config": {
|
22 |
+
"architectures": [
|
23 |
+
"BridgeTowerTextModel"
|
24 |
+
],
|
25 |
+
"classifier_dropout": null,
|
26 |
+
"hidden_size": 1024,
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 4096,
|
29 |
+
"model_type": "bridgetower_text_model",
|
30 |
+
"num_attention_heads": 16,
|
31 |
+
"num_hidden_layers": 24
|
32 |
+
},
|
33 |
+
"tie_word_embeddings": false,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.43.4",
|
36 |
+
"vision_config": {
|
37 |
+
"architectures": [
|
38 |
+
"BridgeTowerVisionModel"
|
39 |
+
],
|
40 |
+
"hidden_size": 1024,
|
41 |
+
"image_size": 294,
|
42 |
+
"model_type": "bridgetower_vision_model",
|
43 |
+
"num_hidden_layers": 24,
|
44 |
+
"patch_size": 14
|
45 |
+
}
|
46 |
+
}
|
gaudi_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"autocast_bf16_ops": null,
|
3 |
+
"autocast_fp32_ops": null,
|
4 |
+
"optimum_version": "1.23.1",
|
5 |
+
"transformers_version": "4.43.4",
|
6 |
+
"use_dynamic_shapes": true,
|
7 |
+
"use_fused_adam": true,
|
8 |
+
"use_fused_clip_norm": true,
|
9 |
+
"use_torch_autocast": true
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62267308dc0dfc1cd693dc5e0aefd597441428ade7c3385e09774c90259cc25d
|
3 |
+
size 3462397716
|
runs/Oct14_22-43-32_workload-ai-workshop/events.out.tfevents.1728945829.workload-ai-workshop.3947.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b81fd62ac8061dc44df0f27d6da66667b7ce21333817bf1399956519154fa580
|
3 |
+
size 26794
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cefd04cd2f66ca3f4d8dc275cce721601bc71dfc6d7221c880524b6c40fbd412
|
3 |
+
size 4984
|