Hugging Face's logo

datht
/
distilbert-base-uncased-finetuned-SA

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
datht commited on
Commit
c517fe0
•
1 Parent(s): 7ede6ed

Training in progress, epoch 4

Browse files
Files changed (24) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-441/config.json +35 -0
  3. run-2/checkpoint-441/model.safetensors +3 -0
  4. run-2/checkpoint-441/optimizer.pt +3 -0
  5. run-2/checkpoint-441/rng_state.pth +3 -0
  6. run-2/checkpoint-441/scheduler.pt +3 -0
  7. run-2/checkpoint-441/special_tokens_map.json +7 -0
  8. run-2/checkpoint-441/tokenizer.json +0 -0
  9. run-2/checkpoint-441/tokenizer_config.json +55 -0
  10. run-2/checkpoint-441/trainer_state.json +53 -0
  11. run-2/checkpoint-441/training_args.bin +3 -0
  12. run-2/checkpoint-441/vocab.txt +0 -0
  13. run-2/checkpoint-588/config.json +35 -0
  14. run-2/checkpoint-588/model.safetensors +3 -0
  15. run-2/checkpoint-588/optimizer.pt +3 -0
  16. run-2/checkpoint-588/rng_state.pth +3 -0
  17. run-2/checkpoint-588/scheduler.pt +3 -0
  18. run-2/checkpoint-588/special_tokens_map.json +7 -0
  19. run-2/checkpoint-588/tokenizer.json +0 -0
  20. run-2/checkpoint-588/tokenizer_config.json +55 -0
  21. run-2/checkpoint-588/trainer_state.json +69 -0
  22. run-2/checkpoint-588/training_args.bin +3 -0
  23. run-2/checkpoint-588/vocab.txt +0 -0
  24. runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711979017.c7a746a4e968.35.5 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:660adf2801f75a7d2e7d30bbf079280332a902672f373039e475628ce4bbc370
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf9c5a016dd02e0ede25ea96e58f95cdd431dc85a344c97f37ce4b51f79aef1
3
  size 267835644
run-2/checkpoint-441/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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 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": "4.38.1",
34
+ "vocab_size": 30522
35
+ }
run-2/checkpoint-441/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae32b0f7b61c9855b9c0ed063172727d465d9da40ec4f714f7f182c10ac73ab6
3
+ size 267835644
run-2/checkpoint-441/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b87f2f5c6bb4bf0a95626ed25b62c32a661262f174a6d974591c90d87aa4d6
3
+ size 535733434
run-2/checkpoint-441/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a572c6bcdaf172bf4c9de22389f6a94b792de7ca465701bb9ddcdbf251a9b316
3
+ size 14308
run-2/checkpoint-441/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4de6caeafd8eef8f488e3ae14ca033fb16746ff8c195e88ef046b36bc32aa2
3
+ size 1064
run-2/checkpoint-441/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-2/checkpoint-441/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-441/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-2/checkpoint-441/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7722602739726028,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-2/checkpoint-294",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 441,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.6643835616438356,
14
+ "eval_loss": 0.7592821717262268,
15
+ "eval_runtime": 3.589,
16
+ "eval_samples_per_second": 162.72,
17
+ "eval_steps_per_second": 10.309,
18
+ "step": 147
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7722602739726028,
23
+ "eval_loss": 0.5706833004951477,
24
+ "eval_runtime": 3.5712,
25
+ "eval_samples_per_second": 163.531,
26
+ "eval_steps_per_second": 10.361,
27
+ "step": 294
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.7671232876712328,
32
+ "eval_loss": 0.5250597596168518,
33
+ "eval_runtime": 3.5872,
34
+ "eval_samples_per_second": 162.802,
35
+ "eval_steps_per_second": 10.314,
36
+ "step": 441
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 735,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 32,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 6.031594833830981e-06,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 20
52
+ }
53
+ }
run-2/checkpoint-441/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36120bb4b2d0b720eac4a646b1e2a8af896ce0926f8d47d5e1fdf1d13dfce58c
3
+ size 4984
run-2/checkpoint-441/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-588/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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 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": "4.38.1",
34
+ "vocab_size": 30522
35
+ }
run-2/checkpoint-588/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf9c5a016dd02e0ede25ea96e58f95cdd431dc85a344c97f37ce4b51f79aef1
3
+ size 267835644
run-2/checkpoint-588/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:565e606951663089102361101050cf92f2f32cfc1ccd0c811504d160477bd47e
3
+ size 535733434
run-2/checkpoint-588/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbdb20f78d1306c76f0f0b0d864f690829f5d5adb2cee92b16e7392673486e9
3
+ size 14308
run-2/checkpoint-588/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23cf2d54b6f4a35a627185554d7dc5326072e6a36b491a6bf2d369c0481ccdc
3
+ size 1064
run-2/checkpoint-588/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-2/checkpoint-588/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-588/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-2/checkpoint-588/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.785958904109589,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-2/checkpoint-588",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 588,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.6643835616438356,
14
+ "eval_loss": 0.7592821717262268,
15
+ "eval_runtime": 3.589,
16
+ "eval_samples_per_second": 162.72,
17
+ "eval_steps_per_second": 10.309,
18
+ "step": 147
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7722602739726028,
23
+ "eval_loss": 0.5706833004951477,
24
+ "eval_runtime": 3.5712,
25
+ "eval_samples_per_second": 163.531,
26
+ "eval_steps_per_second": 10.361,
27
+ "step": 294
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.7671232876712328,
32
+ "eval_loss": 0.5250597596168518,
33
+ "eval_runtime": 3.5872,
34
+ "eval_samples_per_second": 162.802,
35
+ "eval_steps_per_second": 10.314,
36
+ "step": 441
37
+ },
38
+ {
39
+ "epoch": 3.4,
40
+ "grad_norm": 3.6389541625976562,
41
+ "learning_rate": 1.928469096530994e-06,
42
+ "loss": 0.6489,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.785958904109589,
48
+ "eval_loss": 0.5115081071853638,
49
+ "eval_runtime": 3.573,
50
+ "eval_samples_per_second": 163.447,
51
+ "eval_steps_per_second": 10.355,
52
+ "step": 588
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 735,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 5,
59
+ "save_steps": 500,
60
+ "total_flos": 1296419714671410.0,
61
+ "train_batch_size": 32,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 6.031594833830981e-06,
65
+ "num_train_epochs": 5,
66
+ "per_device_train_batch_size": 32,
67
+ "seed": 20
68
+ }
69
+ }
run-2/checkpoint-588/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36120bb4b2d0b720eac4a646b1e2a8af896ce0926f8d47d5e1fdf1d13dfce58c
3
+ size 4984
run-2/checkpoint-588/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711979017.c7a746a4e968.35.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64c1dd1694ecf7707c5278fa03b95e84e738bbffaad82cd80f39fd0ac5b879eb
3
- size 5303
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b0d2a1d3f2e25a782bd387e1b6e848827d9c900231459c8459fedb2255b71fe
3
+ size 6160