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
f71e060
·
verified ·
1 Parent(s): d29d117

Training in progress, epoch 1

Browse files
Files changed (29) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-288/config.json +31 -0
  3. run-5/checkpoint-288/model.safetensors +3 -0
  4. run-5/checkpoint-288/optimizer.pt +3 -0
  5. run-5/checkpoint-288/rng_state.pth +3 -0
  6. run-5/checkpoint-288/scheduler.pt +3 -0
  7. run-5/checkpoint-288/special_tokens_map.json +7 -0
  8. run-5/checkpoint-288/tokenizer.json +0 -0
  9. run-5/checkpoint-288/tokenizer_config.json +55 -0
  10. run-5/checkpoint-288/trainer_state.json +46 -0
  11. run-5/checkpoint-288/training_args.bin +3 -0
  12. run-5/checkpoint-288/vocab.txt +0 -0
  13. run-5/checkpoint-432/config.json +31 -0
  14. run-5/checkpoint-432/model.safetensors +3 -0
  15. run-5/checkpoint-432/optimizer.pt +3 -0
  16. run-5/checkpoint-432/rng_state.pth +3 -0
  17. run-5/checkpoint-432/scheduler.pt +3 -0
  18. run-5/checkpoint-432/special_tokens_map.json +7 -0
  19. run-5/checkpoint-432/tokenizer.json +0 -0
  20. run-5/checkpoint-432/tokenizer_config.json +55 -0
  21. run-5/checkpoint-432/trainer_state.json +56 -0
  22. run-5/checkpoint-432/training_args.bin +3 -0
  23. run-5/checkpoint-432/vocab.txt +0 -0
  24. runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110686.0f0a24039c15.273.8 +3 -0
  25. runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110688.0f0a24039c15.273.9 +3 -0
  26. runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110691.0f0a24039c15.273.10 +3 -0
  27. runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110693.0f0a24039c15.273.11 +3 -0
  28. runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110699.0f0a24039c15.273.12 +3 -0
  29. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81b8c78fe5026c94af7a8215ef418f077d1b268ab1a05d9f5b3ae585fa964aa3
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da441763cabae0320f06ae00d4bab624b4304c700c2711581a1ceb32363235b2
3
  size 267829484
run-5/checkpoint-288/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
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-5/checkpoint-288/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e27c1af20df3e11eb6e302b6d47ad94d291cfb9cc38222f38dad326ed6af2db1
3
+ size 267829484
run-5/checkpoint-288/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f12ef61ce9902581ca871029c692cc32f5944003cab46e961c02c286ac806e4
3
+ size 535721146
run-5/checkpoint-288/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2826085d3a8ff98aba23d7ce9076de8052525af90c5fa53695c34c6987197caa
3
+ size 14308
run-5/checkpoint-288/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d50bce45bea72d615163622f34177f192d9e848246ac5b806cf465d7defe16
3
+ size 1064
run-5/checkpoint-288/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-5/checkpoint-288/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-288/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-5/checkpoint-288/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8704690745503131,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-5/checkpoint-288",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 288,
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": 0.5534277558326721,
14
+ "eval_pearson": 0.8704356686123957,
15
+ "eval_runtime": 0.7898,
16
+ "eval_samples_per_second": 1899.33,
17
+ "eval_spearmanr": 0.8659393895289175,
18
+ "eval_steps_per_second": 119.025,
19
+ "step": 144
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 0.5520570278167725,
24
+ "eval_pearson": 0.8704690745503131,
25
+ "eval_runtime": 0.8117,
26
+ "eval_samples_per_second": 1847.922,
27
+ "eval_spearmanr": 0.8662993614269031,
28
+ "eval_steps_per_second": 115.803,
29
+ "step": 288
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 432,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 3,
36
+ "save_steps": 500,
37
+ "total_flos": 0,
38
+ "train_batch_size": 4,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "learning_rate": 2.532250940931899e-06,
42
+ "num_train_epochs": 3,
43
+ "per_device_train_batch_size": 4,
44
+ "seed": 33
45
+ }
46
+ }
run-5/checkpoint-288/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d063450f94a7ab133a59ea26cf4a1835754e836fb09e39b3319de7656bcf4f60
3
+ size 4920
run-5/checkpoint-288/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-432/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
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-5/checkpoint-432/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad069ef38d70a533221f8e1ad48f448d8095c0fa43fc1551872c61b162fdff28
3
+ size 267829484
run-5/checkpoint-432/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e49bf8bd4bf7f9cfaaf5bd2f1f78892ca7015e7bc21c6f26969e2b5268d477
3
+ size 535721146
run-5/checkpoint-432/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e027600cf7419dd518dec0e144fef1be76e32040d616c39bf661744360992e0
3
+ size 14308
run-5/checkpoint-432/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e06f8b57943e092b3c995b1948e149b61da7337e792e5db52663190ac73d6f
3
+ size 1064
run-5/checkpoint-432/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-5/checkpoint-432/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-432/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-5/checkpoint-432/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8705463356456306,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-5/checkpoint-432",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 432,
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": 0.5534277558326721,
14
+ "eval_pearson": 0.8704356686123957,
15
+ "eval_runtime": 0.7898,
16
+ "eval_samples_per_second": 1899.33,
17
+ "eval_spearmanr": 0.8659393895289175,
18
+ "eval_steps_per_second": 119.025,
19
+ "step": 144
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 0.5520570278167725,
24
+ "eval_pearson": 0.8704690745503131,
25
+ "eval_runtime": 0.8117,
26
+ "eval_samples_per_second": 1847.922,
27
+ "eval_spearmanr": 0.8662993614269031,
28
+ "eval_steps_per_second": 115.803,
29
+ "step": 288
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_loss": 0.5485523343086243,
34
+ "eval_pearson": 0.8705463356456306,
35
+ "eval_runtime": 0.7981,
36
+ "eval_samples_per_second": 1879.36,
37
+ "eval_spearmanr": 0.8663371896251539,
38
+ "eval_steps_per_second": 117.773,
39
+ "step": 432
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 432,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
+ "save_steps": 500,
47
+ "total_flos": 0,
48
+ "train_batch_size": 4,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 2.532250940931899e-06,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 4,
54
+ "seed": 33
55
+ }
56
+ }
run-5/checkpoint-432/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d063450f94a7ab133a59ea26cf4a1835754e836fb09e39b3319de7656bcf4f60
3
+ size 4920
run-5/checkpoint-432/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110686.0f0a24039c15.273.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0dff1e1c7299c41befd784d295f1e6483fe66e11246babdc2edb451d2b5ecb9
3
+ size 5078
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110688.0f0a24039c15.273.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5feec0028bfa856401e9a0dfda3f0a5638cae452574f6a2ea2dc0a38500b07fa
3
+ size 5077
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110691.0f0a24039c15.273.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadd636055bbe9ec771267d28f1011896f79111adb1936056676470348be8d65
3
+ size 5077
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110693.0f0a24039c15.273.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620ac3be608728729b7262225d5e6329cd9b1deb543ea9fb6ea665ed14e3b666
3
+ size 5083
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110699.0f0a24039c15.273.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d653c9701d53a163ecda7c328bb099eb82737e257d98ea47e0e1fae331bf10
3
+ size 6865
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d063450f94a7ab133a59ea26cf4a1835754e836fb09e39b3319de7656bcf4f60
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f60e6fcaaa02ec39d4a651a97e61c3bf1d26dfb974d7e291de6d7d5b31621d03
3
  size 4920