MamiVenkat commited on
Commit
c42cf5b
·
verified ·
1 Parent(s): 0b1a384

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "English",
25
+ "1": "Hinglish",
26
+ "2": "Others"
27
+ },
28
+ "initializer_cutoff_factor": 2.0,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 1152,
31
+ "label2id": {
32
+ "English": "0",
33
+ "Hinglish": "1",
34
+ "Others": "2"
35
+ },
36
+ "layer_norm_eps": 1e-05,
37
+ "local_attention": 128,
38
+ "local_rope_theta": 10000.0,
39
+ "max_position_embeddings": 8192,
40
+ "mlp_bias": false,
41
+ "mlp_dropout": 0.0,
42
+ "model_type": "modernbert",
43
+ "norm_bias": false,
44
+ "norm_eps": 1e-05,
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 22,
47
+ "pad_token_id": 50283,
48
+ "position_embedding_type": "absolute",
49
+ "problem_type": "single_label_classification",
50
+ "reference_compile": true,
51
+ "sep_token_id": 50282,
52
+ "sparse_pred_ignore_index": -100,
53
+ "sparse_prediction": false,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.48.0.dev0",
56
+ "vocab_size": 50368
57
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e457d362195d0ee3eddfe147a2707b5eaa0c13cab6894b2a5764b3142e45984
3
+ size 598442860
runs/Aug12_15-15-28_19fac5b1f42e/events.out.tfevents.1755011757.19fac5b1f42e.4502.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb35984a158366ec20bb46617ce52eaccf65f06b0be513e6afec37393ee2beb
3
+ size 6045
runs/Aug12_15-21-06_19fac5b1f42e/events.out.tfevents.1755012071.19fac5b1f42e.4502.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfd6c860e38e0a281866c05f87fe1ff92cb83101897db002fb97ced960c7b5f
3
+ size 6833
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e4333a4d16c5e7fec024e1afc918008b2ab8c16e3c492ac0226b9b77ce7308
3
+ size 5368