Hugging Face's logo

ana-grassmann
/
bert-base-uncased-finetuned-spam

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ana-grassmann commited on
Commit
d58a62e
•
1 Parent(s): 836b0e6

Training in progress, epoch 1

Browse files
Files changed (19) hide show
  1. config.json +27 -0
  2. model.safetensors +3 -0
  3. run-0/checkpoint-835/config.json +27 -0
  4. run-0/checkpoint-835/model.safetensors +3 -0
  5. run-0/checkpoint-835/optimizer.pt +3 -0
  6. run-0/checkpoint-835/rng_state.pth +3 -0
  7. run-0/checkpoint-835/scheduler.pt +3 -0
  8. run-0/checkpoint-835/special_tokens_map.json +7 -0
  9. run-0/checkpoint-835/tokenizer.json +0 -0
  10. run-0/checkpoint-835/tokenizer_config.json +55 -0
  11. run-0/checkpoint-835/trainer_state.json +42 -0
  12. run-0/checkpoint-835/training_args.bin +3 -0
  13. run-0/checkpoint-835/vocab.txt +0 -0
  14. runs/Mar21_16-50-03_43ee8d6b3d53/events.out.tfevents.1711039811.43ee8d6b3d53.2090.0 +3 -0
  15. special_tokens_map.json +7 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +55 -0
  18. training_args.bin +3 -0
  19. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4152800bb4aaef11f14fd137a5fdba6bb42021a7e4d7612c8e07e7c6811a353
3
+ size 437958648
run-0/checkpoint-835/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-0/checkpoint-835/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4152800bb4aaef11f14fd137a5fdba6bb42021a7e4d7612c8e07e7c6811a353
3
+ size 437958648
run-0/checkpoint-835/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d865ff1971afe67c51744878d5c98d5fef63b88466921ba7caca5e3744ab30
3
+ size 876038394
run-0/checkpoint-835/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574cbd875350bbca156753e0947d35731ac9225d768aa8f37d27744f979fe288
3
+ size 14244
run-0/checkpoint-835/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45a0936aeb35c45eea180bfb2000960d839d10a893285a58ae71001be0398b80
3
+ size 1064
run-0/checkpoint-835/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-0/checkpoint-835/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-835/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-835/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9701617735170761,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-0/checkpoint-835",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 835,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6,
13
+ "grad_norm": 9.867770195007324,
14
+ "learning_rate": 3.6170648435377026e-06,
15
+ "loss": 0.1925,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.9701617735170761,
21
+ "eval_loss": 0.11657896637916565,
22
+ "eval_runtime": 598.01,
23
+ "eval_samples_per_second": 27.909,
24
+ "eval_steps_per_second": 1.746,
25
+ "step": 835
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 835,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 1,
32
+ "save_steps": 500,
33
+ "total_flos": 1000081010313120.0,
34
+ "train_batch_size": 8,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 9.015669087623826e-06,
38
+ "num_train_epochs": 1,
39
+ "per_device_train_batch_size": 8,
40
+ "seed": 38
41
+ }
42
+ }
run-0/checkpoint-835/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072029afd86e7438600bb513bc90a4834b49d28148eb576b7ed3be679cde4f5f
3
+ size 4920
run-0/checkpoint-835/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar21_16-50-03_43ee8d6b3d53/events.out.tfevents.1711039811.43ee8d6b3d53.2090.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e175fca637de50c55c7a3c50ec699399338b669acbe6849ef8def27a5ed08b9c
3
+ size 5526
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072029afd86e7438600bb513bc90a4834b49d28148eb576b7ed3be679cde4f5f
3
+ size 4920
vocab.txt ADDED
The diff for this file is too large to render. See raw diff