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
b157447
·
verified ·
1 Parent(s): 9b1c9f6

Training in progress, epoch 1

Browse files
Files changed (49) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-108/config.json +31 -0
  3. run-4/checkpoint-108/model.safetensors +3 -0
  4. run-4/checkpoint-108/optimizer.pt +3 -0
  5. run-4/checkpoint-108/rng_state.pth +3 -0
  6. run-4/checkpoint-108/scheduler.pt +3 -0
  7. run-4/checkpoint-108/special_tokens_map.json +7 -0
  8. run-4/checkpoint-108/tokenizer.json +0 -0
  9. run-4/checkpoint-108/tokenizer_config.json +55 -0
  10. run-4/checkpoint-108/trainer_state.json +56 -0
  11. run-4/checkpoint-108/training_args.bin +3 -0
  12. run-4/checkpoint-108/vocab.txt +0 -0
  13. run-4/checkpoint-144/config.json +31 -0
  14. run-4/checkpoint-144/model.safetensors +3 -0
  15. run-4/checkpoint-144/optimizer.pt +3 -0
  16. run-4/checkpoint-144/rng_state.pth +3 -0
  17. run-4/checkpoint-144/scheduler.pt +3 -0
  18. run-4/checkpoint-144/special_tokens_map.json +7 -0
  19. run-4/checkpoint-144/tokenizer.json +0 -0
  20. run-4/checkpoint-144/tokenizer_config.json +55 -0
  21. run-4/checkpoint-144/trainer_state.json +66 -0
  22. run-4/checkpoint-144/training_args.bin +3 -0
  23. run-4/checkpoint-144/vocab.txt +0 -0
  24. run-4/checkpoint-72/config.json +31 -0
  25. run-4/checkpoint-72/model.safetensors +3 -0
  26. run-4/checkpoint-72/optimizer.pt +3 -0
  27. run-4/checkpoint-72/rng_state.pth +3 -0
  28. run-4/checkpoint-72/scheduler.pt +3 -0
  29. run-4/checkpoint-72/special_tokens_map.json +7 -0
  30. run-4/checkpoint-72/tokenizer.json +0 -0
  31. run-4/checkpoint-72/tokenizer_config.json +55 -0
  32. run-4/checkpoint-72/trainer_state.json +46 -0
  33. run-4/checkpoint-72/training_args.bin +3 -0
  34. run-4/checkpoint-72/vocab.txt +0 -0
  35. run-7/checkpoint-36/config.json +31 -0
  36. run-7/checkpoint-36/model.safetensors +3 -0
  37. run-7/checkpoint-36/optimizer.pt +3 -0
  38. run-7/checkpoint-36/rng_state.pth +3 -0
  39. run-7/checkpoint-36/scheduler.pt +3 -0
  40. run-7/checkpoint-36/special_tokens_map.json +7 -0
  41. run-7/checkpoint-36/tokenizer.json +0 -0
  42. run-7/checkpoint-36/tokenizer_config.json +55 -0
  43. run-7/checkpoint-36/trainer_state.json +36 -0
  44. run-7/checkpoint-36/training_args.bin +3 -0
  45. run-7/checkpoint-36/vocab.txt +0 -0
  46. runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676366.fe13c9557656.828.7 +3 -0
  47. runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676370.fe13c9557656.828.8 +3 -0
  48. runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676372.fe13c9557656.828.9 +3 -0
  49. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7415615791e29904ce088212da37b0c3848feffe108ed1ca7a498483bbfd324d
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bbcd860dbea13c10b095de95e6b8c87bc449be27e38f724926dcd578a08821
3
  size 267829484
run-4/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-4/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:171f4c90c6e8039e2c7d62ac8854e8d9cb7a7794d0d7417429ec478d29a2815f
3
+ size 267829484
run-4/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5405e7b0692e34255e751a94275c0d34f1e906ca633240844b7a7dda6412dc31
3
+ size 535721146
run-4/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20160c8454a4a044460dce583959a38cc238deeea32b32ee8bf7fbbaa7a9918e
3
+ size 14244
run-4/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:133334039d3706261055b013fe4eb74acca1dfa02b3cb11dcc48548288f48f07
3
+ size 1064
run-4/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-4/checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-108/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.44427892419195647,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/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": 3.607897996902466,
14
+ "eval_pearson": 0.20189901594611118,
15
+ "eval_runtime": 0.9286,
16
+ "eval_samples_per_second": 1615.373,
17
+ "eval_spearmanr": 0.19575057246397828,
18
+ "eval_steps_per_second": 101.23,
19
+ "step": 36
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 2.214840888977051,
24
+ "eval_pearson": 0.22452541125699038,
25
+ "eval_runtime": 0.9301,
26
+ "eval_samples_per_second": 1612.779,
27
+ "eval_spearmanr": 0.24754498733937647,
28
+ "eval_steps_per_second": 101.067,
29
+ "step": 72
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_loss": 2.1850011348724365,
34
+ "eval_pearson": 0.44427892419195647,
35
+ "eval_runtime": 0.9423,
36
+ "eval_samples_per_second": 1591.797,
37
+ "eval_spearmanr": 0.4862668413482525,
38
+ "eval_steps_per_second": 99.753,
39
+ "step": 108
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 144,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 4,
46
+ "save_steps": 500,
47
+ "total_flos": 0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 6.104946209890916e-06,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 9
55
+ }
56
+ }
run-4/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91a99dd245b7ad0b44d46d2003409907fbff02d5cbdc46820df8e68c16a2dbf
3
+ size 4920
run-4/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-144/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-4/checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e62ba66a89926e77077e6643bf2908a9a0bfc9b6548d3f16923c4d229e189272
3
+ size 267829484
run-4/checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48acbba456f3eac77a3b888b44b914aa7af737743f83dfc1e9593d2d071663a1
3
+ size 535721146
run-4/checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab93f76e719fdcd90ef1bc59d1f118a003512417a83f1cb95fcf287d4ab5ea6
3
+ size 14244
run-4/checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8fe60709b17fdd284b4ee879ece7df87e285ef6401bd27d6fc1fa16511dc539
3
+ size 1064
run-4/checkpoint-144/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-4/checkpoint-144/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-144/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-4/checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5270714523203409,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-144",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 144,
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": 3.607897996902466,
14
+ "eval_pearson": 0.20189901594611118,
15
+ "eval_runtime": 0.9286,
16
+ "eval_samples_per_second": 1615.373,
17
+ "eval_spearmanr": 0.19575057246397828,
18
+ "eval_steps_per_second": 101.23,
19
+ "step": 36
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 2.214840888977051,
24
+ "eval_pearson": 0.22452541125699038,
25
+ "eval_runtime": 0.9301,
26
+ "eval_samples_per_second": 1612.779,
27
+ "eval_spearmanr": 0.24754498733937647,
28
+ "eval_steps_per_second": 101.067,
29
+ "step": 72
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_loss": 2.1850011348724365,
34
+ "eval_pearson": 0.44427892419195647,
35
+ "eval_runtime": 0.9423,
36
+ "eval_samples_per_second": 1591.797,
37
+ "eval_spearmanr": 0.4862668413482525,
38
+ "eval_steps_per_second": 99.753,
39
+ "step": 108
40
+ },
41
+ {
42
+ "epoch": 4.0,
43
+ "eval_loss": 2.1628456115722656,
44
+ "eval_pearson": 0.5270714523203409,
45
+ "eval_runtime": 0.9378,
46
+ "eval_samples_per_second": 1599.452,
47
+ "eval_spearmanr": 0.5570093927998047,
48
+ "eval_steps_per_second": 100.232,
49
+ "step": 144
50
+ }
51
+ ],
52
+ "logging_steps": 500,
53
+ "max_steps": 144,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 4,
56
+ "save_steps": 500,
57
+ "total_flos": 0,
58
+ "train_batch_size": 16,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "learning_rate": 6.104946209890916e-06,
62
+ "num_train_epochs": 4,
63
+ "per_device_train_batch_size": 16,
64
+ "seed": 9
65
+ }
66
+ }
run-4/checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91a99dd245b7ad0b44d46d2003409907fbff02d5cbdc46820df8e68c16a2dbf
3
+ size 4920
run-4/checkpoint-144/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-72/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67b2e3d0a525135bd49569a8d64725ba116a2c1b8fd11bb3acfd5821409bf78a
3
+ size 267829484
run-4/checkpoint-72/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a133f68e737fbf59ebad435b5eb189eb9bbb79881de220fe5850a71c95fccf
3
+ size 535721146
run-4/checkpoint-72/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86fd676f2765f76ae40e8279a83aad1f3f514402e7dd2ef3841c0eb67d7dcd5b
3
+ size 14244
run-4/checkpoint-72/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9a3508d8a761e914163950bd782ee13212d965a0ecd807e8d58838a564272d
3
+ size 1064
run-4/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-4/checkpoint-72/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-72/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.22452541125699038,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/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": 3.607897996902466,
14
+ "eval_pearson": 0.20189901594611118,
15
+ "eval_runtime": 0.9286,
16
+ "eval_samples_per_second": 1615.373,
17
+ "eval_spearmanr": 0.19575057246397828,
18
+ "eval_steps_per_second": 101.23,
19
+ "step": 36
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 2.214840888977051,
24
+ "eval_pearson": 0.22452541125699038,
25
+ "eval_runtime": 0.9301,
26
+ "eval_samples_per_second": 1612.779,
27
+ "eval_spearmanr": 0.24754498733937647,
28
+ "eval_steps_per_second": 101.067,
29
+ "step": 72
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 144,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 4,
36
+ "save_steps": 500,
37
+ "total_flos": 0,
38
+ "train_batch_size": 16,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "learning_rate": 6.104946209890916e-06,
42
+ "num_train_epochs": 4,
43
+ "per_device_train_batch_size": 16,
44
+ "seed": 9
45
+ }
46
+ }
run-4/checkpoint-72/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91a99dd245b7ad0b44d46d2003409907fbff02d5cbdc46820df8e68c16a2dbf
3
+ size 4920
run-4/checkpoint-72/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-36/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-7/checkpoint-36/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bbcd860dbea13c10b095de95e6b8c87bc449be27e38f724926dcd578a08821
3
+ size 267829484
run-7/checkpoint-36/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08d74bbdc641f5230795695e6c6137d41951715d5c2208c2de0f933bcdcaec97
3
+ size 535721146
run-7/checkpoint-36/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1836ab2b89e0f3909a1d9bd7f271b58811660577d8389a1c49aeb75995f149
3
+ size 14244
run-7/checkpoint-36/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f4c45031cea00d881324c073c2a2e5199ef8c2209d707b198b3a95f2cf22d5
3
+ size 1064
run-7/checkpoint-36/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-7/checkpoint-36/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-36/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-7/checkpoint-36/trainer_state.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.457192832227161,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-7/checkpoint-36",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 36,
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": 2.1181581020355225,
14
+ "eval_pearson": 0.457192832227161,
15
+ "eval_runtime": 0.8791,
16
+ "eval_samples_per_second": 1706.218,
17
+ "eval_spearmanr": 0.44927428651795276,
18
+ "eval_steps_per_second": 106.923,
19
+ "step": 36
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 144,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 4,
26
+ "save_steps": 500,
27
+ "total_flos": 0,
28
+ "train_batch_size": 16,
29
+ "trial_name": null,
30
+ "trial_params": {
31
+ "learning_rate": 2.2613535003508284e-05,
32
+ "num_train_epochs": 4,
33
+ "per_device_train_batch_size": 16,
34
+ "seed": 19
35
+ }
36
+ }
run-7/checkpoint-36/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d651dfeb39fbfdee53e1bd84f374650de80a6c4a3ae4617d7d4651e3cf08bd
3
+ size 4920
run-7/checkpoint-36/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676366.fe13c9557656.828.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3566c234da6c4f8b1fc2e8804f4a69b884d6b57b5ef51ea5b64faac7263bb40
3
+ size 4975
runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676370.fe13c9557656.828.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:756dc00c841b49bd1d864383987f5c001c0f56d27f40ba7cdd09d145ce47ae06
3
+ size 4974
runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676372.fe13c9557656.828.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111de97f1b151209882419364b2e4256d8f167766a7798e95fd38c9f505b67e0
3
+ size 6441
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a91a99dd245b7ad0b44d46d2003409907fbff02d5cbdc46820df8e68c16a2dbf
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d651dfeb39fbfdee53e1bd84f374650de80a6c4a3ae4617d7d4651e3cf08bd
3
  size 4920