andsam commited on
Commit
3480370
·
verified ·
1 Parent(s): 57bb7c4

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. config.json +62 -0
  2. model.safetensors +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "answerdotai/ModernBERT-base",
3
+ "architectures": [
4
+ "ModernBertForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1",
26
+ "2": "LABEL_2",
27
+ "3": "LABEL_3",
28
+ "4": "LABEL_4"
29
+ },
30
+ "initializer_cutoff_factor": 2.0,
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 1152,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1,
36
+ "LABEL_2": 2,
37
+ "LABEL_3": 3,
38
+ "LABEL_4": 4
39
+ },
40
+ "layer_norm_eps": 1e-05,
41
+ "local_attention": 128,
42
+ "local_rope_theta": 10000.0,
43
+ "max_position_embeddings": 8192,
44
+ "mlp_bias": false,
45
+ "mlp_dropout": 0.0,
46
+ "model_type": "modernbert",
47
+ "norm_bias": false,
48
+ "norm_eps": 1e-05,
49
+ "num_attention_heads": 12,
50
+ "num_hidden_layers": 22,
51
+ "pad_token_id": 50283,
52
+ "position_embedding_type": "absolute",
53
+ "problem_type": "single_label_classification",
54
+ "reference_compile": true,
55
+ "repad_logits_with_grad": false,
56
+ "sep_token_id": 50282,
57
+ "sparse_pred_ignore_index": -100,
58
+ "sparse_prediction": false,
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.48.3",
61
+ "vocab_size": 50368
62
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0082ff900f64743ee7d99d92e04c5d3b8e49f5297901e67b2675b36cbff61a65
3
+ size 598449012
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123284f72cda15632af1f7e00c0def8ad14dc1fab976c41e43ed068a02eb5979
3
+ size 5368