Hugging Face's logo

cruiser
/
distilbert_final_tweet_dataset_200_epoch

Text Classification
Transformers
TensorBoard
distilbert
Inference Endpoints
Model card Files Metrics Community
cruiser commited on
Commit
777ac7a
·
1 Parent(s): 3522448

Training in progress, epoch 1

Browse files
Files changed (21) hide show
  1. .gitignore +1 -0
  2. config.json +34 -0
  3. last-checkpoint/config.json +34 -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 +26 -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_10-03-26_b04f269e142e/1682935412.0058336/events.out.tfevents.1682935412.b04f269e142e.1987.3 +3 -0
  16. runs/May01_10-03-26_b04f269e142e/events.out.tfevents.1682935412.b04f269e142e.1987.2 +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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.28.1",
33
+ "vocab_size": 30522
34
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.28.1",
33
+ "vocab_size": 30522
34
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04914b04f278a74893a34042e556db9b68002678574bfd72a636655782b70f5
3
+ size 535707077
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50689028b8d69446708619e444b5ef6df34c1cd79f08e2166b53ace0bc4e2e4d
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:e346e6688c1eadb672218a4848843cc41a81cf3151a0155342c1d6a279ce7a84
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3667512d48e7f74e55ec7e7186b9d651968c529cd3dfd50d119b07cd9465b07
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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.3408091068267822,
3
+ "best_model_checkpoint": "distilbert_final_tweet_dataset_200_epoch/checkpoint-115",
4
+ "epoch": 1.0,
5
+ "global_step": 115,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.6327160493827161,
13
+ "eval_f1": 0.6368645566163996,
14
+ "eval_loss": 2.3408091068267822,
15
+ "eval_runtime": 0.7378,
16
+ "eval_samples_per_second": 439.117,
17
+ "eval_steps_per_second": 55.567,
18
+ "step": 115
19
+ }
20
+ ],
21
+ "max_steps": 23000,
22
+ "num_train_epochs": 200,
23
+ "total_flos": 37112748946884.0,
24
+ "trial_name": null,
25
+ "trial_params": null
26
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2df7be961dfb9faf160ad0cc8ff5bd3a80c108e2698165585f80de00d1341eb
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 sha256:50689028b8d69446708619e444b5ef6df34c1cd79f08e2166b53ace0bc4e2e4d
3
+ size 267858605
runs/May01_10-03-26_b04f269e142e/1682935412.0058336/events.out.tfevents.1682935412.b04f269e142e.1987.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406feef4dbd1aa5068f12b46feee4eb6468e672a94a2f4741e636696a91d4b87
3
+ size 5942
runs/May01_10-03-26_b04f269e142e/events.out.tfevents.1682935412.b04f269e142e.1987.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3797c0ebe96042ce1a2f7f944bf9cc6aea3cad1c5913a5e2589fb6caff614520
3
+ size 4532
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:b2df7be961dfb9faf160ad0cc8ff5bd3a80c108e2698165585f80de00d1341eb
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff