Training in progress, step 5000
Browse files- .gitignore +1 -0
- config.json +31 -0
- 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 +84 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Nadav/PretrainedPHD-v3",
|
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/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Nadav/PretrainedPHD-v3",
|
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 sha256:426565ae7e122986bcb61feb0824a20d697e6e1d0d7ee61605f81249ac607053
|
3 |
+
size 893438545
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5975d5c14cb653070063ab664a542345e1d7b31d1f7f2691782cc33745d9b2b9
|
3 |
+
size 449471589
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b802e5910fd078d7354b6fbe97850b2f1ec26c0f43e7f9e349a96b25ed8f557
|
3 |
+
size 15587
|
last-checkpoint/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6775d0c71cbc2254c9932c38f18b38899f4e38dc0dfc75f710acd45f734e62b
|
3 |
+
size 559
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16ebe9ed2aebd8d40826f0d7b248340ae7726517e3fb98bf26aa87be67a5fb7a
|
3 |
+
size 623
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4353125544140693,
|
5 |
+
"global_step": 5000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"learning_rate": 0.00010077567264729574,
|
13 |
+
"loss": 0.5253,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.09,
|
18 |
+
"learning_rate": 0.00010075889723559493,
|
19 |
+
"loss": 0.5001,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.13,
|
24 |
+
"learning_rate": 0.00010073092788158004,
|
25 |
+
"loss": 0.4909,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.17,
|
30 |
+
"learning_rate": 0.00010069177148627061,
|
31 |
+
"loss": 0.4848,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.22,
|
36 |
+
"learning_rate": 0.0001006414377109213,
|
37 |
+
"loss": 0.4811,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.26,
|
42 |
+
"learning_rate": 0.00010057993897463803,
|
43 |
+
"loss": 0.4761,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3,
|
48 |
+
"learning_rate": 0.00010050729045131372,
|
49 |
+
"loss": 0.4736,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.35,
|
54 |
+
"learning_rate": 0.00010042351006588448,
|
55 |
+
"loss": 0.4712,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.39,
|
60 |
+
"learning_rate": 0.00010032861848990674,
|
61 |
+
"loss": 0.4694,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.44,
|
66 |
+
"learning_rate": 0.00010022263913645699,
|
67 |
+
"loss": 0.4675,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.44,
|
72 |
+
"eval_loss": 0.4460357427597046,
|
73 |
+
"eval_runtime": 24.6462,
|
74 |
+
"eval_samples_per_second": 202.871,
|
75 |
+
"eval_steps_per_second": 3.205,
|
76 |
+
"step": 5000
|
77 |
+
}
|
78 |
+
],
|
79 |
+
"max_steps": 100000,
|
80 |
+
"num_train_epochs": 9,
|
81 |
+
"total_flos": 2.354930673647616e+20,
|
82 |
+
"trial_name": null,
|
83 |
+
"trial_params": null
|
84 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eb00b29f032ade2a0345630cdf4cae059e8f7416f7bbd307613cfeb1aa3d144
|
3 |
+
size 5615
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5975d5c14cb653070063ab664a542345e1d7b31d1f7f2691782cc33745d9b2b9
|
3 |
+
size 449471589
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eb00b29f032ade2a0345630cdf4cae059e8f7416f7bbd307613cfeb1aa3d144
|
3 |
+
size 5615
|