Saving best model to hub
Browse files- .gitignore +1 -0
- all_results.json +7 -0
- config.json +60 -0
- pytorch_model.bin +3 -0
- train_results.json +7 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.283862659664154,
|
| 4 |
+
"train_runtime": 136485.8094,
|
| 5 |
+
"train_samples_per_second": 23.446,
|
| 6 |
+
"train_steps_per_second": 0.366
|
| 7 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "letter",
|
| 13 |
+
"1": "form",
|
| 14 |
+
"2": "email",
|
| 15 |
+
"3": "handwritten",
|
| 16 |
+
"4": "advertisement",
|
| 17 |
+
"5": "scientific_report",
|
| 18 |
+
"6": "scientific_publication",
|
| 19 |
+
"7": "specification",
|
| 20 |
+
"8": "file_folder",
|
| 21 |
+
"9": "news_article",
|
| 22 |
+
"10": "budget",
|
| 23 |
+
"11": "invoice",
|
| 24 |
+
"12": "presentation",
|
| 25 |
+
"13": "questionnaire",
|
| 26 |
+
"14": "resume",
|
| 27 |
+
"15": "memo"
|
| 28 |
+
},
|
| 29 |
+
"image_size": 224,
|
| 30 |
+
"initializer_range": 0.02,
|
| 31 |
+
"intermediate_size": 3072,
|
| 32 |
+
"label2id": {
|
| 33 |
+
"advertisement": 4,
|
| 34 |
+
"budget": 10,
|
| 35 |
+
"email": 2,
|
| 36 |
+
"file_folder": 8,
|
| 37 |
+
"form": 1,
|
| 38 |
+
"handwritten": 3,
|
| 39 |
+
"invoice": 11,
|
| 40 |
+
"letter": 0,
|
| 41 |
+
"memo": 15,
|
| 42 |
+
"news_article": 9,
|
| 43 |
+
"presentation": 12,
|
| 44 |
+
"questionnaire": 13,
|
| 45 |
+
"resume": 14,
|
| 46 |
+
"scientific_publication": 6,
|
| 47 |
+
"scientific_report": 5,
|
| 48 |
+
"specification": 7
|
| 49 |
+
},
|
| 50 |
+
"layer_norm_eps": 1e-12,
|
| 51 |
+
"model_type": "vit",
|
| 52 |
+
"num_attention_heads": 12,
|
| 53 |
+
"num_channels": 3,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"patch_size": 16,
|
| 56 |
+
"problem_type": "single_label_classification",
|
| 57 |
+
"qkv_bias": true,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.26.1"
|
| 60 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b8198fb769d6fde5e60573ac96f2dbef436cd2cc2a56cb11bf059d68de05761
|
| 3 |
+
size 343311789
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.283862659664154,
|
| 4 |
+
"train_runtime": 136485.8094,
|
| 5 |
+
"train_samples_per_second": 23.446,
|
| 6 |
+
"train_steps_per_second": 0.366
|
| 7 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db25317b0ed69892f5df6b9a25baa8c271e0f8f45a51fa98166468377a0598c4
|
| 3 |
+
size 3579
|