Training in progress, step 5000
Browse files- config.json +1 -1
- last-checkpoint/config.json +31 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scaler.pt +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +0 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/projects/copenlu/data/nadav/pixel/PretarinedPHD_v5/checkpoint-
|
3 |
"architectures": [
|
4 |
"PIXELForPreTraining"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/projects/copenlu/data/nadav/pixel/PretarinedPHD_v5/checkpoint-1800000",
|
3 |
"architectures": [
|
4 |
"PIXELForPreTraining"
|
5 |
],
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/projects/copenlu/data/nadav/pixel/PretarinedPHD_v5/checkpoint-1800000",
|
3 |
+
"architectures": [
|
4 |
+
"PIXELForPreTraining"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"decoder_hidden_size": 512,
|
8 |
+
"decoder_intermediate_size": 2048,
|
9 |
+
"decoder_num_attention_heads": 16,
|
10 |
+
"decoder_num_hidden_layers": 8,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"image_size": [
|
15 |
+
368,
|
16 |
+
368
|
17 |
+
],
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"mask_ratio": 0.29,
|
22 |
+
"model_type": "pixel",
|
23 |
+
"norm_pix_loss": true,
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_channels": 3,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"patch_size": 16,
|
28 |
+
"qkv_bias": true,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.17.0"
|
31 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7799791aec36f61f2ef6f2aefce8b35a1856153b13c717ce46a7f72410b994bd
|
3 |
+
size 893438545
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d87d4251419285b82323349a677c4bf9083a6f1197c42082c54fc5645fade81
|
3 |
+
size 449471589
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83eb1bb636ae77ffefaf890e099e36fe7fd8ef3f00230c0686edd8fc7ce218b4
|
3 |
+
size 19603
|
last-checkpoint/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54e88afae9d767cdfd93373c4fb2ad34e64b3c348725a37125bffdbfbbcbd70f
|
3 |
+
size 559
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06ac8e1527bf32c3e318ea058e0960d53f45c6c9a2121e892062bad3352d5ec0
|
3 |
+
size 623
|
last-checkpoint/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a438d3758fcfa636e08463e84b78cbfd4ecffe466a1209b9e325894f489f5b
|
3 |
+
size 5615
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d87d4251419285b82323349a677c4bf9083a6f1197c42082c54fc5645fade81
|
3 |
size 449471589
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5615
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a438d3758fcfa636e08463e84b78cbfd4ecffe466a1209b9e325894f489f5b
|
3 |
size 5615
|