Hugging Face's logo

daze-unlv
/
LennartKeller-nystromformer-gottbert-base-8192

Multiple Choice
Transformers
TensorBoard
Safetensors
nystromformer
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
daze-unlv commited on
Commit
5e8bc07
•
1 Parent(s): 8ca818d

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. config.json +32 -0
  2. log.txt +5 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. runs/Mar13_02-09-32_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710320975.cehsc-app-001.ad.unlv.edu.2792605.0 +3 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +57 -0
  9. training_args.bin +3 -0
  10. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LennartKeller/nystromformer-gottbert-base-8192",
3
+ "architectures": [
4
+ "NystromformerForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "conv_kernel_size": 65,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "inv_coeff_init_option": false,
18
+ "layer_norm_eps": 1e-05,
19
+ "max_position_embeddings": 8192,
20
+ "model_type": "nystromformer",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "num_landmarks": 64,
24
+ "pad_token_id": 1,
25
+ "position_embedding_type": "absolute",
26
+ "segment_means_seq_len": 64,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.39.0.dev0",
29
+ "type_vocab_size": 1,
30
+ "use_cache": true,
31
+ "vocab_size": 52009
32
+ }
log.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {'loss': 1.3877, 'grad_norm': 0.3732655942440033, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
2
+ {'loss': 1.3877, 'grad_norm': 0.29982370138168335, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
3
+ {'loss': 1.3869, 'grad_norm': 0.2956711947917938, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
4
+ {'loss': 1.3872, 'grad_norm': 0.2780778706073761, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
5
+ {'loss': 1.387, 'grad_norm': 0.264312207698822, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b8b9d4df7a16ee77def1cccaf341fd3cb52623277b0ce5f34d432a67d01902
3
+ size 527600452
runs/Mar13_02-09-32_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710320975.cehsc-app-001.ad.unlv.edu.2792605.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd8215782f0d0a97c3939a8000f5eaa1cc82c3c11314b9af29f0f8847b90e59
3
+ size 6294
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "52008": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2ef03073c59c4ff1e392b7d1b806e2b027cd288214569d15af9bf3c34ac696
3
+ size 4984
vocab.json ADDED
The diff for this file is too large to render. See raw diff