Hugging Face's logo

traromal
/
modernbert-llm-router

Text Classification
Transformers
TensorBoard
Safetensors
modernbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
traromal commited on
Commit
3a10ed3
·
verified ·
1 Parent(s): c77721e

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. config.json +54 -0
  2. model.safetensors +3 -0
  3. runs/Jul10_12-15-04_dd83ea197c93/events.out.tfevents.1752149706.dd83ea197c93.489.0 +3 -0
  4. runs/Jul10_12-15-41_dd83ea197c93/events.out.tfevents.1752149742.dd83ea197c93.489.1 +3 -0
  5. runs/Jul10_12-15-43_dd83ea197c93/events.out.tfevents.1752149745.dd83ea197c93.489.2 +3 -0
  6. runs/Jul10_12-15-47_dd83ea197c93/events.out.tfevents.1752149748.dd83ea197c93.489.3 +3 -0
  7. runs/Jul10_12-18-02_dd83ea197c93/events.out.tfevents.1752149886.dd83ea197c93.2839.0 +3 -0
  8. runs/Jul10_12-20-52_dd83ea197c93/events.out.tfevents.1752150053.dd83ea197c93.2839.1 +3 -0
  9. runs/Jul10_12-22-34_dd83ea197c93/events.out.tfevents.1752150155.dd83ea197c93.2839.2 +3 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "False",
24
+ "1": "True"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "False": "0",
31
+ "True": "1"
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "local_attention": 128,
35
+ "local_rope_theta": 10000.0,
36
+ "max_position_embeddings": 8192,
37
+ "mlp_bias": false,
38
+ "mlp_dropout": 0.0,
39
+ "model_type": "modernbert",
40
+ "norm_bias": false,
41
+ "norm_eps": 1e-05,
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 22,
44
+ "pad_token_id": 50283,
45
+ "position_embedding_type": "absolute",
46
+ "problem_type": "single_label_classification",
47
+ "repad_logits_with_grad": false,
48
+ "sep_token_id": 50282,
49
+ "sparse_pred_ignore_index": -100,
50
+ "sparse_prediction": false,
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.53.1",
53
+ "vocab_size": 50368
54
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e41bd6b87d7578371a857fb05f5e9c9144551910ab5d4fd8d48786f90c56d947
3
+ size 598439784
runs/Jul10_12-15-04_dd83ea197c93/events.out.tfevents.1752149706.dd83ea197c93.489.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99997c89a56fcb8070e7c4c04e47f2bee7a7d5b694e9ce19f0a300b1c08386f2
3
+ size 4184
runs/Jul10_12-15-41_dd83ea197c93/events.out.tfevents.1752149742.dd83ea197c93.489.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67b3c16394ff072da03b73992e5e0b0b7eb58872f24668c8478129df04e45f0c
3
+ size 4184
runs/Jul10_12-15-43_dd83ea197c93/events.out.tfevents.1752149745.dd83ea197c93.489.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3835decb45714e48c9c253320078fd55ef9ea371e67c5a01a0391de90983db
3
+ size 4184
runs/Jul10_12-15-47_dd83ea197c93/events.out.tfevents.1752149748.dd83ea197c93.489.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acdeaa848e6cfc67487c8b94d582d3d907c72f814cfddf2f482129feb7e682da
3
+ size 4184
runs/Jul10_12-18-02_dd83ea197c93/events.out.tfevents.1752149886.dd83ea197c93.2839.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c46eb343b49606655d0147b77f62f9c747819fc6823fb8483101d21292aa064
3
+ size 5666
runs/Jul10_12-20-52_dd83ea197c93/events.out.tfevents.1752150053.dd83ea197c93.2839.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4aa4e7c899664f1d6ffc262a078370801f831b01b5035c1b69ff9d317ccbb9b
3
+ size 5666
runs/Jul10_12-22-34_dd83ea197c93/events.out.tfevents.1752150155.dd83ea197c93.2839.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35cfdc5b9182145aeefd8cd9f0d2e7051645698f117bbb1ccfbe0bb9fb07ff50
3
+ size 6190
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f155fe80fb0413048067360eeae189b5e490c4d6ad081735c70ce8eb43faa65
3
+ size 5368