Hugging Face's logo

slevis
/
bert-finetuned-das

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
text-embeddings-inference
Model card Files
xet
 Metrics Community
slevis commited on
Commit
d348bd2
·
verified ·
1 Parent(s): d2ebe37

Training in progress, epoch 1

Browse files
Files changed (19) hide show
  1. config.json +35 -0
  2. model.safetensors +3 -0
  3. run-0/checkpoint-820/config.json +35 -0
  4. run-0/checkpoint-820/model.safetensors +3 -0
  5. run-0/checkpoint-820/optimizer.pt +3 -0
  6. run-0/checkpoint-820/rng_state.pth +3 -0
  7. run-0/checkpoint-820/scheduler.pt +3 -0
  8. run-0/checkpoint-820/special_tokens_map.json +7 -0
  9. run-0/checkpoint-820/tokenizer.json +0 -0
  10. run-0/checkpoint-820/tokenizer_config.json +55 -0
  11. run-0/checkpoint-820/trainer_state.json +54 -0
  12. run-0/checkpoint-820/training_args.bin +3 -0
  13. run-0/checkpoint-820/vocab.txt +0 -0
  14. runs/Jul17_22-58-25_10dbc3c42dd8/events.out.tfevents.1721257299.10dbc3c42dd8.34.3 +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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Not-Applicable",
13
+ "1": "Closed",
14
+ "2": "Open"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "Closed": 1,
19
+ "Not-Applicable": 0,
20
+ "Open": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.41.2",
34
+ "vocab_size": 30522
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be3d9f270ed98c53255781454631f8140be091dcbbc82d42aabd274b1764441
3
+ size 267835644
run-0/checkpoint-820/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Not-Applicable",
13
+ "1": "Closed",
14
+ "2": "Open"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "Closed": 1,
19
+ "Not-Applicable": 0,
20
+ "Open": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.41.2",
34
+ "vocab_size": 30522
35
+ }
run-0/checkpoint-820/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be3d9f270ed98c53255781454631f8140be091dcbbc82d42aabd274b1764441
3
+ size 267835644
run-0/checkpoint-820/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817e0f292650f9cfc33206a0285d97617f1f7ce76d39552c387d22bf379a643e
3
+ size 535733434
run-0/checkpoint-820/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c5609abf7e1426dcd5ca0d52e7a2eb41ee5de293c1214281185857fa19e6a0
3
+ size 14308
run-0/checkpoint-820/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b06be0364efbaa6689f10c239ffc7074277f19bc7456d08e2a8637501475fc
3
+ size 1064
run-0/checkpoint-820/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-820/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-820/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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-820/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.32205894589424133,
3
+ "best_model_checkpoint": "bert-finetuned-das/run-0/checkpoint-820",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 820,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6097560975609756,
13
+ "grad_norm": 6.909906387329102,
14
+ "learning_rate": 1.2707321441211695e-05,
15
+ "loss": 0.482,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8989037758830695,
21
+ "eval_loss": 0.32205894589424133,
22
+ "eval_runtime": 2.1237,
23
+ "eval_samples_per_second": 386.598,
24
+ "eval_steps_per_second": 24.486,
25
+ "step": 820
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 3280,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 4,
32
+ "save_steps": 500,
33
+ "stateful_callbacks": {
34
+ "TrainerControl": {
35
+ "args": {
36
+ "should_epoch_stop": false,
37
+ "should_evaluate": false,
38
+ "should_log": false,
39
+ "should_save": true,
40
+ "should_training_stop": false
41
+ },
42
+ "attributes": {}
43
+ }
44
+ },
45
+ "total_flos": 41842850843448.0,
46
+ "train_batch_size": 4,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "learning_rate": 1.4992810909055526e-05,
50
+ "num_train_epochs": 4,
51
+ "per_device_train_batch_size": 4,
52
+ "seed": 20
53
+ }
54
+ }
run-0/checkpoint-820/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0f5d683ba7842a9befa31fbd56c9c9d4eb9148c126c4076136fed0b561b05d
3
+ size 5112
run-0/checkpoint-820/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jul17_22-58-25_10dbc3c42dd8/events.out.tfevents.1721257299.10dbc3c42dd8.34.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f06390e4b804b0194e5ab8ee8b2949f75508d53f458bf1d625519f25a85284
3
+ size 5431
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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0f5d683ba7842a9befa31fbd56c9c9d4eb9148c126c4076136fed0b561b05d
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff