Hugging Face's logo

Afaf
/
minabert

TensorBoard
Safetensors
modernbert
Model card Files Metrics Community
Afaf commited on
Commit
368cc17
·
verified ·
1 Parent(s): c5df02e

Training in progress, step 10

Browse files
Files changed (11) hide show
  1. config.json +47 -0
  2. model.safetensors +3 -0
  3. runs/Jan11_22-33-54_492dae7079f7/events.out.tfevents.1736634902.492dae7079f7.9961.0 +3 -0
  4. runs/Jan11_22-33-54_492dae7079f7/events.out.tfevents.1736635242.492dae7079f7.9961.1 +3 -0
  5. runs/Jan11_22-42-43_492dae7079f7/events.out.tfevents.1736635368.492dae7079f7.9961.2 +3 -0
  6. runs/Jan11_22-42-55_492dae7079f7/events.out.tfevents.1736635379.492dae7079f7.9961.3 +3 -0
  7. runs/Jan11_22-45-17_492dae7079f7/events.out.tfevents.1736635517.492dae7079f7.9961.4 +3 -0
  8. runs/Jan11_22-53-44_492dae7079f7/events.out.tfevents.1736636025.492dae7079f7.9961.5 +3 -0
  9. runs/Jan11_22-56-38_492dae7079f7/events.out.tfevents.1736636199.492dae7079f7.9961.6 +3 -0
  10. runs/Jan11_22-57-36_492dae7079f7/events.out.tfevents.1736636257.492dae7079f7.9961.7 +3 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "answerdotai/ModernBERT-base",
3
+ "architectures": [
4
+ "ModernBertForMaskedLM"
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
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1152,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 22,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": false,
40
+ "repad_logits_with_grad": false,
41
+ "sep_token_id": 50282,
42
+ "sparse_pred_ignore_index": -100,
43
+ "sparse_prediction": false,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.48.0",
46
+ "vocab_size": 50368
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd4a49fc5d4bc0a569d00515270013bfa4627717cec0b831e42159c23994f46
3
+ size 598635032
runs/Jan11_22-33-54_492dae7079f7/events.out.tfevents.1736634902.492dae7079f7.9961.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b89bf25d3c4f4720f1390ff0b85ff6628f299dae9b635fd2d1bbe269c8e9c8
3
+ size 11302
runs/Jan11_22-33-54_492dae7079f7/events.out.tfevents.1736635242.492dae7079f7.9961.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcbeaf39ac8f5e5667f08461b503ee2ac608f91a75c8d01bd539c8ac43851df7
3
+ size 5695
runs/Jan11_22-42-43_492dae7079f7/events.out.tfevents.1736635368.492dae7079f7.9961.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23fbcab58eb0bec177189cffbe71eb3d8ff620954d1ff71391e2e67f04c3f5a5
3
+ size 5695
runs/Jan11_22-42-55_492dae7079f7/events.out.tfevents.1736635379.492dae7079f7.9961.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8745f1a084a5656866dc97e089d43e83086390d1226c0e32dbdf4e05e3946a8e
3
+ size 5695
runs/Jan11_22-45-17_492dae7079f7/events.out.tfevents.1736635517.492dae7079f7.9961.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7fb2e8405b6be19b84a738ca4fa761dfcf6d7e6349907d879b27216a70867f0
3
+ size 5696
runs/Jan11_22-53-44_492dae7079f7/events.out.tfevents.1736636025.492dae7079f7.9961.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa71c26e13688221074f8ccd21cbd8f70238d958073998d32a35a4d886bbe4db
3
+ size 5706
runs/Jan11_22-56-38_492dae7079f7/events.out.tfevents.1736636199.492dae7079f7.9961.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d0e4117624dc98ce00a2d3228d17fc9ab567681d77e5ea6734ed26e0ed3e33e
3
+ size 4184
runs/Jan11_22-57-36_492dae7079f7/events.out.tfevents.1736636257.492dae7079f7.9961.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768f7f4b30cc2bce5a5b90a1e5cd7aeef916f65287ce63c486527ca41bc9bd78
3
+ size 4184
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d44d9c8ccb44e4a60b41d6fe79150d61b90ae4b4c75e3fa252be0c573247d9
3
+ size 5368