AllanK24 commited on
Commit
ce36c23
·
verified ·
1 Parent(s): 15b32c5

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. config.json +65 -0
  2. model.safetensors +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": 50282,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 160000.0,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "LABEL_0",
24
+ "1": "LABEL_1",
25
+ "2": "LABEL_2",
26
+ "3": "LABEL_3",
27
+ "4": "LABEL_4",
28
+ "5": "LABEL_5",
29
+ "6": "LABEL_6",
30
+ "7": "LABEL_7"
31
+ },
32
+ "initializer_cutoff_factor": 2.0,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 1152,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_2": 2,
39
+ "LABEL_3": 3,
40
+ "LABEL_4": 4,
41
+ "LABEL_5": 5,
42
+ "LABEL_6": 6,
43
+ "LABEL_7": 7
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "local_attention": 128,
47
+ "local_rope_theta": 10000.0,
48
+ "max_position_embeddings": 8192,
49
+ "mlp_bias": false,
50
+ "mlp_dropout": 0.0,
51
+ "model_type": "modernbert",
52
+ "norm_bias": false,
53
+ "norm_eps": 1e-05,
54
+ "num_attention_heads": 12,
55
+ "num_hidden_layers": 22,
56
+ "pad_token_id": 50283,
57
+ "position_embedding_type": "absolute",
58
+ "repad_logits_with_grad": false,
59
+ "sep_token_id": 50282,
60
+ "sparse_pred_ignore_index": -100,
61
+ "sparse_prediction": false,
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.51.1",
64
+ "vocab_size": 50368
65
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7437361ed226023e48f395daa35645ece06e0bf911e3d130ade5492047a1285d
3
+ size 598458240
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ea7ac04d237d6b145c9dc9e4eba34df5774a11d6149f077f6d3cfd1a97e775
3
+ size 5368