kubalewcz commited on
Commit
a622549
·
verified ·
1 Parent(s): 66d3232

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allegro/herbert-base-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "tokenizer_class": "HerbertTokenizerFast",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.47.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 50000
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38158a5b07db8b8f7b2dde4a357ce0712e99a1e3894c552285c248adc91b6327
3
+ size 497807368
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771dad8659d1bde2cb46b440fe760808d3c35ca988cbaf9080e90928b66afd5b
3
+ size 995735738
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0686af21959b6ddd3351441a7dbb01030f43297a3857377c038b81c8a640167
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ed989fd77dd82eb3c4b4285da30c835ab11516e66fceb28613a1638eebe7c5d
3
+ size 1064
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a11b3b0a7b08d6f20d0cf01af2177a810987ad51b165feb6944443694c0f5fe
3
+ size 5240