Hugging Face's logo

cruiser
/
distilbert_weight_decay_final_metrics

Text Classification
Transformers
PyTorch
TensorBoard
distilbert
Inference Endpoints
Model card Files Metrics Community
cruiser commited on
Commit
895c12e
•
1 Parent(s): c1ec0b6

Training in progress, epoch 1

Browse files
Files changed (21) hide show
  1. .gitignore +1 -0
  2. config.json +35 -0
  3. last-checkpoint/config.json +35 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scheduler.pt +3 -0
  8. last-checkpoint/special_tokens_map.json +7 -0
  9. last-checkpoint/tokenizer.json +0 -0
  10. last-checkpoint/tokenizer_config.json +13 -0
  11. last-checkpoint/trainer_state.json +44 -0
  12. last-checkpoint/training_args.bin +3 -0
  13. last-checkpoint/vocab.txt +0 -0
  14. pytorch_model.bin +3 -0
  15. runs/May01_06-16-39_af1ffd0a72ec/1682921804.7410483/events.out.tfevents.1682921804.af1ffd0a72ec.975.13 +3 -0
  16. runs/May01_06-16-39_af1ffd0a72ec/events.out.tfevents.1682921804.af1ffd0a72ec.975.12 +3 -0
  17. special_tokens_map.json +7 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +13 -0
  20. training_args.bin +3 -0
  21. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "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": "Negative",
13
+ "1": "Neutral",
14
+ "2": "Positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "Negative": 0,
19
+ "Neutral": 1,
20
+ "Positive": 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": "4.28.1",
34
+ "vocab_size": 30522
35
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "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": "Negative",
13
+ "1": "Neutral",
14
+ "2": "Positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "Negative": 0,
19
+ "Neutral": 1,
20
+ "Positive": 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": "4.28.1",
34
+ "vocab_size": 30522
35
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:558fc6c74444158434ea7e5a2abbd7e4bfc87c1409f9ad5653126032a8ce79a6
3
+ size 535707205
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87175da7d5baa1888c80066cbd1b9d34c063f51f5205572230cbfdac03bb57f6
3
+ size 267858605
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1afa4fb390fed62209a33ec31502a83421450b5e725ed87b9f6a0e5a6fe43e4a
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8887e02a63197212eb08e6268a00af8c32453672a22c577dcf1de8bc5e2b976a
3
+ size 627
last-checkpoint/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
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8788982629776,
3
+ "best_model_checkpoint": "distilbert_weight_decay_final_metrics/checkpoint-1718",
4
+ "epoch": 1.0,
5
+ "global_step": 1718,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.29,
12
+ "learning_rate": 1.970896391152503e-05,
13
+ "loss": 0.0266,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.58,
18
+ "learning_rate": 1.941792782305006e-05,
19
+ "loss": 0.0377,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.87,
24
+ "learning_rate": 1.9126891734575087e-05,
25
+ "loss": 0.0319,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.0,
30
+ "eval_accuracy": 0.7770232031692134,
31
+ "eval_f1": 0.781143699897714,
32
+ "eval_loss": 1.8788982629776,
33
+ "eval_runtime": 8.0848,
34
+ "eval_samples_per_second": 437.119,
35
+ "eval_steps_per_second": 27.335,
36
+ "step": 1718
37
+ }
38
+ ],
39
+ "max_steps": 34360,
40
+ "num_train_epochs": 20,
41
+ "total_flos": 782117510345820.0,
42
+ "trial_name": null,
43
+ "trial_params": null
44
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af32211f4867f7295b386765bbaac8a9dab0c555f1b63eb2d3aaf649924c02d6
3
+ size 3643
last-checkpoint/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87175da7d5baa1888c80066cbd1b9d34c063f51f5205572230cbfdac03bb57f6
3
+ size 267858605
runs/May01_06-16-39_af1ffd0a72ec/1682921804.7410483/events.out.tfevents.1682921804.af1ffd0a72ec.975.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4739bc7e53077028dc2d1dd37fd197bb254a863a29d6e9fa08865ae29962e115
3
+ size 5933
runs/May01_06-16-39_af1ffd0a72ec/events.out.tfevents.1682921804.af1ffd0a72ec.975.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b858d16e7e1ee6f802bbf7937d9ef1d6f8a782d4582bb785862815821d379c
3
+ size 5027
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af32211f4867f7295b386765bbaac8a9dab0c555f1b63eb2d3aaf649924c02d6
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff