Hugging Face's logo

cruiser
/
distilbert_weight_decay_final

Text Classification
Transformers
PyTorch
TensorBoard
distilbert
Inference Endpoints
Model card Files Metrics Community
cruiser commited on
Commit
4e1a557
•
1 Parent(s): 92fcb9d

Training in progress, epoch 1

Browse files
Files changed (29) 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 +48 -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_05-37-38_af1ffd0a72ec/1682919463.053597/events.out.tfevents.1682919463.af1ffd0a72ec.975.3 +3 -0
  16. runs/May01_05-37-38_af1ffd0a72ec/events.out.tfevents.1682919463.af1ffd0a72ec.975.2 +3 -0
  17. runs/May01_05-37-56_af1ffd0a72ec/1682919479.1828432/events.out.tfevents.1682919479.af1ffd0a72ec.975.5 +3 -0
  18. runs/May01_05-37-56_af1ffd0a72ec/events.out.tfevents.1682919479.af1ffd0a72ec.975.4 +3 -0
  19. runs/May01_05-44-38_af1ffd0a72ec/1682919880.5800993/events.out.tfevents.1682919880.af1ffd0a72ec.975.7 +3 -0
  20. runs/May01_05-44-38_af1ffd0a72ec/events.out.tfevents.1682919880.af1ffd0a72ec.975.6 +3 -0
  21. runs/May01_05-52-46_af1ffd0a72ec/1682920369.2732103/events.out.tfevents.1682920369.af1ffd0a72ec.975.9 +3 -0
  22. runs/May01_05-52-46_af1ffd0a72ec/events.out.tfevents.1682920369.af1ffd0a72ec.975.8 +3 -0
  23. runs/May01_06-03-35_af1ffd0a72ec/1682921017.4052732/events.out.tfevents.1682921017.af1ffd0a72ec.975.11 +3 -0
  24. runs/May01_06-03-35_af1ffd0a72ec/events.out.tfevents.1682921017.af1ffd0a72ec.975.10 +3 -0
  25. special_tokens_map.json +7 -0
  26. tokenizer.json +0 -0
  27. tokenizer_config.json +13 -0
  28. training_args.bin +3 -0
  29. 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 sha256:9a177e7e58ebacb27aeeaaafa31d26179ad44cc4442bec50cd96f3a753c507af
3
+ size 535707205
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f89b283bce7d91e0a094f038f21181c4089cfb1ab3fe1fdbf36e52574105a45
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8566110134124756,
3
+ "best_model_checkpoint": "distilbert_weight_decay_final/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": 0.0382,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.58,
18
+ "learning_rate": 1.941792782305006e-05,
19
+ "loss": 0.0288,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.87,
24
+ "learning_rate": 1.9126891734575087e-05,
25
+ "loss": 0.0306,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.0,
30
+ "eval_accuracy": {
31
+ "accuracy": 0.7809847198641766
32
+ },
33
+ "eval_f1": {
34
+ "f1": 0.7844084064836702
35
+ },
36
+ "eval_loss": 1.8566110134124756,
37
+ "eval_runtime": 10.7438,
38
+ "eval_samples_per_second": 328.933,
39
+ "eval_steps_per_second": 20.57,
40
+ "step": 1718
41
+ }
42
+ ],
43
+ "max_steps": 34360,
44
+ "num_train_epochs": 20,
45
+ "total_flos": 782117510345820.0,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b5971559e4f46008c26899655526790b1f0642c2203abcf53b24a5526a8e81
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 sha256:5f89b283bce7d91e0a094f038f21181c4089cfb1ab3fe1fdbf36e52574105a45
3
+ size 267858605
runs/May01_05-37-38_af1ffd0a72ec/1682919463.053597/events.out.tfevents.1682919463.af1ffd0a72ec.975.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b3b69285940d3f059ec7efb07f96e0ab64fc7134a52e595fb125571ca8d918
3
+ size 5909
runs/May01_05-37-38_af1ffd0a72ec/events.out.tfevents.1682919463.af1ffd0a72ec.975.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9c6e0d11e6650803d64abaea07f792d69b323db605627511eb478fac55d543
3
+ size 4163
runs/May01_05-37-56_af1ffd0a72ec/1682919479.1828432/events.out.tfevents.1682919479.af1ffd0a72ec.975.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2128b5daafb795acd01eac33664e6aabae556c43f4e05d1f5f6bb4cda648d25c
3
+ size 5909
runs/May01_05-37-56_af1ffd0a72ec/events.out.tfevents.1682919479.af1ffd0a72ec.975.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64b6ed01c3bd581a42060ad05b8a9c035eb41be88a8c175deab72fe499bf51dc
3
+ size 4634
runs/May01_05-44-38_af1ffd0a72ec/1682919880.5800993/events.out.tfevents.1682919880.af1ffd0a72ec.975.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd3a8a73ce1d82c2542a605e5908fc86284f1691683d37cffdc183f7a210dc4b
3
+ size 5909
runs/May01_05-44-38_af1ffd0a72ec/events.out.tfevents.1682919880.af1ffd0a72ec.975.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ba3064d629b2822a03735ad26f934a0f19d561068ab0acc692caf45262e3a4c
3
+ size 4634
runs/May01_05-52-46_af1ffd0a72ec/1682920369.2732103/events.out.tfevents.1682920369.af1ffd0a72ec.975.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ff7e034a3153f975d6c176da8c430808dac52ce0d1cb38badae7444216cbe4
3
+ size 5909
runs/May01_05-52-46_af1ffd0a72ec/events.out.tfevents.1682920369.af1ffd0a72ec.975.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ba354bc9693e69ff1591ccb72fddd9a299a0f4a4fe61442227db8ca1ec2c93
3
+ size 4634
runs/May01_06-03-35_af1ffd0a72ec/1682921017.4052732/events.out.tfevents.1682921017.af1ffd0a72ec.975.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b7014a74d6bfa8bdb78ec9c2d6e83f30f6ec53d845a0e28be292d8534dbf111
3
+ size 5909
runs/May01_06-03-35_af1ffd0a72ec/events.out.tfevents.1682921017.af1ffd0a72ec.975.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08dcf5072db183fe3fc5f86f73a3c90d0dd9c71fb873a02e205ae51a9c6fa631
3
+ size 4905
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 sha256:04b5971559e4f46008c26899655526790b1f0642c2203abcf53b24a5526a8e81
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff