jordyvl commited on
Commit
028a07e
1 Parent(s): 8e623a4

Saving best model to hub

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "train_loss": 0.26981526770591735,
4
+ "train_runtime": 2946.7149,
5
+ "train_samples_per_second": 27.149,
6
+ "train_steps_per_second": 1.697
7
+ }
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/dit-base",
3
+ "architectures": [
4
+ "BeitForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auxiliary_channels": 256,
8
+ "auxiliary_concat_input": false,
9
+ "auxiliary_loss_weight": 0.4,
10
+ "auxiliary_num_convs": 1,
11
+ "drop_path_rate": 0.1,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.0,
14
+ "hidden_size": 384,
15
+ "id2label": {
16
+ "0": "ADVE",
17
+ "1": "Email",
18
+ "2": "Form",
19
+ "3": "Letter",
20
+ "4": "Memo",
21
+ "5": "News",
22
+ "6": "Note",
23
+ "7": "Report",
24
+ "8": "Resume",
25
+ "9": "Scientific"
26
+ },
27
+ "image_size": 224,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 1536,
30
+ "label2id": {
31
+ "ADVE": 0,
32
+ "Email": 1,
33
+ "Form": 2,
34
+ "Letter": 3,
35
+ "Memo": 4,
36
+ "News": 5,
37
+ "Note": 6,
38
+ "Report": 7,
39
+ "Resume": 8,
40
+ "Scientific": 9
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "layer_scale_init_value": 0.1,
44
+ "model_type": "beit",
45
+ "num_attention_heads": 8,
46
+ "num_channels": 3,
47
+ "num_hidden_layers": 12,
48
+ "out_indices": [
49
+ 3,
50
+ 5,
51
+ 7,
52
+ 11
53
+ ],
54
+ "patch_size": 16,
55
+ "pool_scales": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 6
60
+ ],
61
+ "problem_type": "single_label_classification",
62
+ "semantic_loss_ignore_index": 255,
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.28.0.dev0",
65
+ "use_absolute_position_embeddings": true,
66
+ "use_auxiliary_head": true,
67
+ "use_mask_token": true,
68
+ "use_mean_pooling": true,
69
+ "use_relative_position_bias": false,
70
+ "use_shared_relative_position_bias": false,
71
+ "vocab_size": 8192
72
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a6a3ea0f931c3d7ad2154a54ef60203acea0584fee967dd495d5b447e1732f2
3
+ size 86768215
runs/Jul10_12-07-50_jordy-OMEN/1688983676.2018106/events.out.tfevents.1688983676.jordy-OMEN.44521.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e2007d4bb917cc6684008231f8e96b1a70cfeefd188bf53327c812fb20c28f
3
+ size 5938
runs/Jul10_12-07-50_jordy-OMEN/events.out.tfevents.1688983676.jordy-OMEN.44521.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5363b026c836c7a2c9d5e4080f8255fdea44a3085fb0306cedfbf5d677b74fe0
3
+ size 69097
runs/Jul10_12-07-50_jordy-OMEN/events.out.tfevents.1688986677.jordy-OMEN.44521.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b08b239a5cb0813e57a18622cccfb9fc18c6e55ab0678bb6c96840424b4706f
3
+ size 663
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "train_loss": 0.26981526770591735,
4
+ "train_runtime": 2946.7149,
5
+ "train_samples_per_second": 27.149,
6
+ "train_steps_per_second": 1.697
7
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac0a5b7c16664ee6118be7ea6bc9b442f942d99d62730b00135ad5c5e5d5259
3
+ size 3695