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
b9a68b0
•
1 Parent(s): c517fe0

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-735/config.json +35 -0
  3. run-2/checkpoint-735/model.safetensors +3 -0
  4. run-2/checkpoint-735/optimizer.pt +3 -0
  5. run-2/checkpoint-735/rng_state.pth +3 -0
  6. run-2/checkpoint-735/scheduler.pt +3 -0
  7. run-2/checkpoint-735/special_tokens_map.json +7 -0
  8. run-2/checkpoint-735/tokenizer.json +0 -0
  9. run-2/checkpoint-735/tokenizer_config.json +55 -0
  10. run-2/checkpoint-735/trainer_state.json +78 -0
  11. run-2/checkpoint-735/training_args.bin +3 -0
  12. run-2/checkpoint-735/vocab.txt +0 -0
  13. run-3/checkpoint-585/config.json +35 -0
  14. run-3/checkpoint-585/model.safetensors +3 -0
  15. run-3/checkpoint-585/optimizer.pt +3 -0
  16. run-3/checkpoint-585/rng_state.pth +3 -0
  17. run-3/checkpoint-585/scheduler.pt +3 -0
  18. run-3/checkpoint-585/special_tokens_map.json +7 -0
  19. run-3/checkpoint-585/tokenizer.json +0 -0
  20. run-3/checkpoint-585/tokenizer_config.json +55 -0
  21. run-3/checkpoint-585/trainer_state.json +42 -0
  22. run-3/checkpoint-585/training_args.bin +3 -0
  23. run-3/checkpoint-585/vocab.txt +0 -0
  24. runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711979017.c7a746a4e968.35.5 +2 -2
  25. runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711979478.c7a746a4e968.35.6 +3 -0
  26. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abf9c5a016dd02e0ede25ea96e58f95cdd431dc85a344c97f37ce4b51f79aef1
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528bbd4ff8503347d78863ae6811fea9d1e18942659e73f7a4b88201932cb63d
3
  size 267835644
run-2/checkpoint-735/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-735/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ae8184b87ae7c2e84c6c5484b4f56c801e5d4976512044294d355ee890ae31
3
+ size 267835644
run-2/checkpoint-735/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3928402cc5fbc9751ec986cf172568f65904240c7f027e4fb4592d02300be685
3
+ size 535733434
run-2/checkpoint-735/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3f3493c0c37d5ee8ce510598767b20b24dd0d116164e1560b431a47921ef98
3
+ size 14308
run-2/checkpoint-735/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5964e81533dfb448787b1945d14230887fa7de27f517dca776970e0c4adf8cb2
3
+ size 1064
run-2/checkpoint-735/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-735/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-735/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-735/trainer_state.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7876712328767124,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-2/checkpoint-735",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 735,
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
+ "epoch": 5.0,
56
+ "eval_accuracy": 0.7876712328767124,
57
+ "eval_loss": 0.5062544345855713,
58
+ "eval_runtime": 3.5999,
59
+ "eval_samples_per_second": 162.226,
60
+ "eval_steps_per_second": 10.278,
61
+ "step": 735
62
+ }
63
+ ],
64
+ "logging_steps": 500,
65
+ "max_steps": 735,
66
+ "num_input_tokens_seen": 0,
67
+ "num_train_epochs": 5,
68
+ "save_steps": 500,
69
+ "total_flos": 1296419714671410.0,
70
+ "train_batch_size": 32,
71
+ "trial_name": null,
72
+ "trial_params": {
73
+ "learning_rate": 6.031594833830981e-06,
74
+ "num_train_epochs": 5,
75
+ "per_device_train_batch_size": 32,
76
+ "seed": 20
77
+ }
78
+ }
run-2/checkpoint-735/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-735/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-585/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-3/checkpoint-585/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528bbd4ff8503347d78863ae6811fea9d1e18942659e73f7a4b88201932cb63d
3
+ size 267835644
run-3/checkpoint-585/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9a6211fb2f16ef516be683e58db707208d624235d33684e2a13db467cfd60c
3
+ size 535733434
run-3/checkpoint-585/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06fb30c761257a0477ac26e6c115362de15b75c2eec808c72fc76e4e2e6b9a07
3
+ size 14244
run-3/checkpoint-585/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5384b2ec2eae5df030729ac6f2c113b97d3ceb6c50179d6e261eab9c8244b783
3
+ size 1064
run-3/checkpoint-585/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-3/checkpoint-585/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-585/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-3/checkpoint-585/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5171232876712328,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-3/checkpoint-585",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 585,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.85,
13
+ "grad_norm": 2.2346689701080322,
14
+ "learning_rate": 1.7036613585538902e-07,
15
+ "loss": 1.0151,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5171232876712328,
21
+ "eval_loss": 0.9680984616279602,
22
+ "eval_runtime": 3.5917,
23
+ "eval_samples_per_second": 162.596,
24
+ "eval_steps_per_second": 10.301,
25
+ "step": 585
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 585,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 1,
32
+ "save_steps": 500,
33
+ "total_flos": 325999802520000.0,
34
+ "train_batch_size": 8,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 1.1725198761812067e-06,
38
+ "num_train_epochs": 1,
39
+ "per_device_train_batch_size": 8,
40
+ "seed": 16
41
+ }
42
+ }
run-3/checkpoint-585/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f8db343f5b9a4d7258a51829ca45cfb2fc87f12b6788f3e856db73d5ce91c3
3
+ size 4984
run-3/checkpoint-585/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 sha256:3b0d2a1d3f2e25a782bd387e1b6e848827d9c900231459c8459fedb2255b71fe
3
- size 6160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aece4709c149ada03298ef54a49ef01e81d5dcf724b866708a52d3b29bfe035a
3
+ size 6837
runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711979478.c7a746a4e968.35.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdb2c92a0ceef3845f877f22f7dc6affe7453730f28acb7315fe815c11330fae
3
+ size 5545
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36120bb4b2d0b720eac4a646b1e2a8af896ce0926f8d47d5e1fdf1d13dfce58c
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f8db343f5b9a4d7258a51829ca45cfb2fc87f12b6788f3e856db73d5ce91c3
3
  size 4984