Hugging Face's logo

SjardiWillems
/
distilbert-base-uncased-finetuned-stsb

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
SjardiWillems commited on
Commit
b63fed8
·
verified ·
1 Parent(s): d9deea5

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-8/checkpoint-108/config.json +31 -0
  3. run-8/checkpoint-108/model.safetensors +3 -0
  4. run-8/checkpoint-108/optimizer.pt +3 -0
  5. run-8/checkpoint-108/rng_state.pth +3 -0
  6. run-8/checkpoint-108/scheduler.pt +3 -0
  7. run-8/checkpoint-108/special_tokens_map.json +7 -0
  8. run-8/checkpoint-108/tokenizer.json +0 -0
  9. run-8/checkpoint-108/tokenizer_config.json +55 -0
  10. run-8/checkpoint-108/trainer_state.json +56 -0
  11. run-8/checkpoint-108/training_args.bin +3 -0
  12. run-8/checkpoint-108/vocab.txt +0 -0
  13. run-8/checkpoint-72/config.json +31 -0
  14. run-8/checkpoint-72/model.safetensors +3 -0
  15. run-8/checkpoint-72/optimizer.pt +3 -0
  16. run-8/checkpoint-72/rng_state.pth +3 -0
  17. run-8/checkpoint-72/scheduler.pt +3 -0
  18. run-8/checkpoint-72/special_tokens_map.json +7 -0
  19. run-8/checkpoint-72/tokenizer.json +0 -0
  20. run-8/checkpoint-72/tokenizer_config.json +55 -0
  21. run-8/checkpoint-72/trainer_state.json +46 -0
  22. run-8/checkpoint-72/training_args.bin +3 -0
  23. run-8/checkpoint-72/vocab.txt +0 -0
  24. runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774259.6dcd98e81284.961.11 +3 -0
  25. runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774495.6dcd98e81284.961.12 +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 sha256:86f87cf2bf59060d3a0048c5a8c89d46ad6fbbda7e7277d36534ba5b40602188
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5fc3b8d4422a6943c82d56761559ef083a87dc77f4b3339f6d3b173f2b59b58
3
  size 267829484
run-8/checkpoint-108/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "vocab_size": 30522
31
+ }
run-8/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7b41b1162886e7f19d52475bd8cd532d0b64f3d58274232dce5e25cceb78584
3
+ size 267829484
run-8/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11132f9ffeb58d9f7e5269a62529c89628ccb6476c8ef7f6fa39c73e08764b5c
3
+ size 535721146
run-8/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2425f522d9457ef7c0fce08992204899d0f83ea37673b7c1f758d4de8167ecd5
3
+ size 14308
run-8/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4c90472c10abdca8a57dbb278bf31a2d810165632447ed5a08b52fa37b73259
3
+ size 1064
run-8/checkpoint-108/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-8/checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-108/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-8/checkpoint-108/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.824136706588593,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-8/checkpoint-108",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 108,
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_loss": 1.3752338886260986,
14
+ "eval_pearson": 0.7318354585295763,
15
+ "eval_runtime": 0.8667,
16
+ "eval_samples_per_second": 1730.617,
17
+ "eval_spearmanr": 0.7352649171390578,
18
+ "eval_steps_per_second": 108.452,
19
+ "step": 36
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 1.0067311525344849,
24
+ "eval_pearson": 0.8140212325971369,
25
+ "eval_runtime": 0.8653,
26
+ "eval_samples_per_second": 1733.449,
27
+ "eval_spearmanr": 0.8112995192982398,
28
+ "eval_steps_per_second": 108.629,
29
+ "step": 72
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_loss": 0.75139981508255,
34
+ "eval_pearson": 0.824136706588593,
35
+ "eval_runtime": 0.8903,
36
+ "eval_samples_per_second": 1684.846,
37
+ "eval_spearmanr": 0.8206768378703474,
38
+ "eval_steps_per_second": 105.584,
39
+ "step": 108
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 108,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
+ "save_steps": 500,
47
+ "total_flos": 0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 8.023427611654661e-05,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 32
55
+ }
56
+ }
run-8/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc9ff8b6111b24f8c33c7c89aa6bd61df59ec50315b654becfc206c361b6086
3
+ size 4920
run-8/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-72/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "vocab_size": 30522
31
+ }
run-8/checkpoint-72/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c71349818ee6bf6dc9a93e0b0b0fc26677276ae667a676db0ac5e6606a118626
3
+ size 267829484
run-8/checkpoint-72/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50618f45f0897ac214acd11e8c08ce4c34c2917519e5c427220f75af6349ab8c
3
+ size 535721146
run-8/checkpoint-72/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc1e1afdbce1c1659090549a679e121a3e13c17ac36832ffad5e1eff7ea7095
3
+ size 14308
run-8/checkpoint-72/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1ccd0876921ecd1ee9956c58ccc68191e79d3236c73ee06af83a4915cbe987
3
+ size 1064
run-8/checkpoint-72/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-8/checkpoint-72/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-72/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-8/checkpoint-72/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8140212325971369,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-8/checkpoint-72",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 72,
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_loss": 1.3752338886260986,
14
+ "eval_pearson": 0.7318354585295763,
15
+ "eval_runtime": 0.8667,
16
+ "eval_samples_per_second": 1730.617,
17
+ "eval_spearmanr": 0.7352649171390578,
18
+ "eval_steps_per_second": 108.452,
19
+ "step": 36
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 1.0067311525344849,
24
+ "eval_pearson": 0.8140212325971369,
25
+ "eval_runtime": 0.8653,
26
+ "eval_samples_per_second": 1733.449,
27
+ "eval_spearmanr": 0.8112995192982398,
28
+ "eval_steps_per_second": 108.629,
29
+ "step": 72
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 108,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 3,
36
+ "save_steps": 500,
37
+ "total_flos": 0,
38
+ "train_batch_size": 16,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "learning_rate": 8.023427611654661e-05,
42
+ "num_train_epochs": 3,
43
+ "per_device_train_batch_size": 16,
44
+ "seed": 32
45
+ }
46
+ }
run-8/checkpoint-72/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc9ff8b6111b24f8c33c7c89aa6bd61df59ec50315b654becfc206c361b6086
3
+ size 4920
run-8/checkpoint-72/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774259.6dcd98e81284.961.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499fa97f8b8dc22c74d024145de2ef1caf5d03a2b3087ecd4fa589974f3598fe
3
+ size 4982
runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774495.6dcd98e81284.961.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55091336adf2c09cc97567b5f9970cb7aab10f7b74413b73c7b874f8cfb18c07
3
+ size 6882
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbc9ff8b6111b24f8c33c7c89aa6bd61df59ec50315b654becfc206c361b6086
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34840284466eb2205f9f10ed091682dc9319569f75d63faf8795d5f603abf328
3
  size 4920