Hugging Face's logo

nancyH
/
full_output

Model card Files
xet
 Community
nancyH commited on
Commit
f8f3a0b
·
verified ·
1 Parent(s): 8891d68

Delete human_nontata_promoters

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. human_nontata_promoters/base_3072/checkpoint-200/config.json +0 -27
  2. human_nontata_promoters/base_3072/checkpoint-200/model.safetensors +0 -3
  3. human_nontata_promoters/base_3072/checkpoint-200/optimizer.pt +0 -3
  4. human_nontata_promoters/base_3072/checkpoint-200/rng_state.pth +0 -3
  5. human_nontata_promoters/base_3072/checkpoint-200/scheduler.pt +0 -3
  6. human_nontata_promoters/base_3072/checkpoint-200/special_tokens_map.json +0 -7
  7. human_nontata_promoters/base_3072/checkpoint-200/tokenizer.json +0 -0
  8. human_nontata_promoters/base_3072/checkpoint-200/tokenizer_config.json +0 -56
  9. human_nontata_promoters/base_3072/checkpoint-200/trainer_state.json +0 -32
  10. human_nontata_promoters/base_3072/checkpoint-200/training_args.bin +0 -3
  11. human_nontata_promoters/base_3072/checkpoint-400/config.json +0 -27
  12. human_nontata_promoters/base_3072/checkpoint-400/model.safetensors +0 -3
  13. human_nontata_promoters/base_3072/checkpoint-400/optimizer.pt +0 -3
  14. human_nontata_promoters/base_3072/checkpoint-400/rng_state.pth +0 -3
  15. human_nontata_promoters/base_3072/checkpoint-400/scheduler.pt +0 -3
  16. human_nontata_promoters/base_3072/checkpoint-400/special_tokens_map.json +0 -7
  17. human_nontata_promoters/base_3072/checkpoint-400/tokenizer.json +0 -0
  18. human_nontata_promoters/base_3072/checkpoint-400/tokenizer_config.json +0 -56
  19. human_nontata_promoters/base_3072/checkpoint-400/trainer_state.json +0 -45
  20. human_nontata_promoters/base_3072/checkpoint-400/training_args.bin +0 -3
  21. human_nontata_promoters/base_3072/checkpoint-600/config.json +0 -27
  22. human_nontata_promoters/base_3072/checkpoint-600/model.safetensors +0 -3
  23. human_nontata_promoters/base_3072/checkpoint-600/optimizer.pt +0 -3
  24. human_nontata_promoters/base_3072/checkpoint-600/rng_state.pth +0 -3
  25. human_nontata_promoters/base_3072/checkpoint-600/scheduler.pt +0 -3
  26. human_nontata_promoters/base_3072/checkpoint-600/special_tokens_map.json +0 -7
  27. human_nontata_promoters/base_3072/checkpoint-600/tokenizer.json +0 -0
  28. human_nontata_promoters/base_3072/checkpoint-600/tokenizer_config.json +0 -56
  29. human_nontata_promoters/base_3072/checkpoint-600/trainer_state.json +0 -58
  30. human_nontata_promoters/base_3072/checkpoint-600/training_args.bin +0 -3
  31. human_nontata_promoters/base_3072/results/base_3072_hg38_BPE_3e-5_human_nontata_promoters_seed42/eval_results.json +0 -1
  32. human_nontata_promoters/base_4096/checkpoint-200/config.json +0 -27
  33. human_nontata_promoters/base_4096/checkpoint-200/model.safetensors +0 -3
  34. human_nontata_promoters/base_4096/checkpoint-200/optimizer.pt +0 -3
  35. human_nontata_promoters/base_4096/checkpoint-200/rng_state.pth +0 -3
  36. human_nontata_promoters/base_4096/checkpoint-200/scheduler.pt +0 -3
  37. human_nontata_promoters/base_4096/checkpoint-200/special_tokens_map.json +0 -7
  38. human_nontata_promoters/base_4096/checkpoint-200/tokenizer.json +0 -0
  39. human_nontata_promoters/base_4096/checkpoint-200/tokenizer_config.json +0 -56
  40. human_nontata_promoters/base_4096/checkpoint-200/trainer_state.json +0 -32
  41. human_nontata_promoters/base_4096/checkpoint-200/training_args.bin +0 -3
  42. human_nontata_promoters/base_4096/checkpoint-400/config.json +0 -27
  43. human_nontata_promoters/base_4096/checkpoint-400/model.safetensors +0 -3
  44. human_nontata_promoters/base_4096/checkpoint-400/optimizer.pt +0 -3
  45. human_nontata_promoters/base_4096/checkpoint-400/rng_state.pth +0 -3
  46. human_nontata_promoters/base_4096/checkpoint-400/scheduler.pt +0 -3
  47. human_nontata_promoters/base_4096/checkpoint-400/special_tokens_map.json +0 -7
  48. human_nontata_promoters/base_4096/checkpoint-400/tokenizer.json +0 -0
  49. human_nontata_promoters/base_4096/checkpoint-400/tokenizer_config.json +0 -56
  50. human_nontata_promoters/base_4096/checkpoint-400/trainer_state.json +0 -45
human_nontata_promoters/base_3072/checkpoint-200/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_3072/checkpoint-100000",
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 768,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 3072,
13
- "layer_norm_eps": 1e-12,
14
- "max_length": 512,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "position_embedding_type": "absolute",
21
- "problem_type": "single_label_classification",
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.35.2",
24
- "type_vocab_size": 2,
25
- "use_cache": true,
26
- "vocab_size": 3072
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-200/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4da584c471a33ce6afe5349a49687572834c4850de0998037d24c15208585471
3
- size 353632152
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-200/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1eb7e1f2bed484a1a6f2164b825fdc15b6c523dac9f66b0d8b49a8b72dd47da6
3
- size 707385995
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-200/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3615a64f8cf2bc9362c88bff87921fc8264d3fb7ee2703a90b3dc0f54a7c55db
3
- size 14709
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-200/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd7a706c2415bb6c236cc21c87a0c7ed17ea99d115c1adb3798d9895be0cb293
3
- size 1465
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-200/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-200/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_nontata_promoters/base_3072/checkpoint-200/tokenizer_config.json DELETED
@@ -1,56 +0,0 @@
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
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "cache_dir": null,
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "mask_token": "[MASK]",
48
- "model_max_length": 100,
49
- "pad_token": "[PAD]",
50
- "padding_side": "right",
51
- "sep_token": "[SEP]",
52
- "tokenizer_class": "PreTrainedTokenizerFast",
53
- "trust_remote_code": true,
54
- "unk_token": "[UNK]",
55
- "use_fast": true
56
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-200/trainer_state.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.8849557522123894,
5
- "eval_steps": 200,
6
- "global_step": 200,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.88,
13
- "eval_accuracy": 0.8560752836977581,
14
- "eval_f1": 0.8560728029108416,
15
- "eval_loss": 0.3306120038032532,
16
- "eval_matthews_correlation": 0.7317076841559982,
17
- "eval_precision": 0.8655274258206318,
18
- "eval_recall": 0.8661805498253218,
19
- "eval_runtime": 0.3536,
20
- "eval_samples_per_second": 10219.2,
21
- "eval_steps_per_second": 82.025,
22
- "step": 200
23
- }
24
- ],
25
- "logging_steps": 100000,
26
- "max_steps": 678,
27
- "num_train_epochs": 3,
28
- "save_steps": 200,
29
- "total_flos": 894577598791680.0,
30
- "trial_name": null,
31
- "trial_params": null
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-200/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b11e88f2e4ef6351c9e83a0034b2ed5ce634c3c3b1f3b55d329f297d3eb9e82
3
- size 5329
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-400/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_3072/checkpoint-100000",
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 768,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 3072,
13
- "layer_norm_eps": 1e-12,
14
- "max_length": 512,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "position_embedding_type": "absolute",
21
- "problem_type": "single_label_classification",
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.35.2",
24
- "type_vocab_size": 2,
25
- "use_cache": true,
26
- "vocab_size": 3072
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-400/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d4b3b568682aa5747b2d15104f5516bf182461dfc79de280058f82c9b2c8c1a
3
- size 353632152
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-400/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:763d72f7eed1ee7829f92e8bb13084c3a1330d7bd8016eca1894bbbf8df469b8
3
- size 707385995
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-400/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:98c4ff6e27039ab31f8565c0406397236e51dff4450c1b7030478f86e3c002f0
3
- size 14709
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-400/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2089997e4944f5cc2a0bcd083374dc434a2912ea0185d5b075e8268b38f5aa44
3
- size 1465
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-400/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-400/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_nontata_promoters/base_3072/checkpoint-400/tokenizer_config.json DELETED
@@ -1,56 +0,0 @@
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
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "cache_dir": null,
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "mask_token": "[MASK]",
48
- "model_max_length": 100,
49
- "pad_token": "[PAD]",
50
- "padding_side": "right",
51
- "sep_token": "[SEP]",
52
- "tokenizer_class": "PreTrainedTokenizerFast",
53
- "trust_remote_code": true,
54
- "unk_token": "[UNK]",
55
- "use_fast": true
56
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-400/trainer_state.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.7699115044247788,
5
- "eval_steps": 200,
6
- "global_step": 400,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.88,
13
- "eval_accuracy": 0.8560752836977581,
14
- "eval_f1": 0.8560728029108416,
15
- "eval_loss": 0.3306120038032532,
16
- "eval_matthews_correlation": 0.7317076841559982,
17
- "eval_precision": 0.8655274258206318,
18
- "eval_recall": 0.8661805498253218,
19
- "eval_runtime": 0.3536,
20
- "eval_samples_per_second": 10219.2,
21
- "eval_steps_per_second": 82.025,
22
- "step": 200
23
- },
24
- {
25
- "epoch": 1.77,
26
- "eval_accuracy": 0.880708552449488,
27
- "eval_f1": 0.8805239993079428,
28
- "eval_loss": 0.28219544887542725,
29
- "eval_matthews_correlation": 0.7700299247313025,
30
- "eval_precision": 0.8828539668283777,
31
- "eval_recall": 0.8871881555085832,
32
- "eval_runtime": 0.3274,
33
- "eval_samples_per_second": 11034.853,
34
- "eval_steps_per_second": 88.572,
35
- "step": 400
36
- }
37
- ],
38
- "logging_steps": 100000,
39
- "max_steps": 678,
40
- "num_train_epochs": 3,
41
- "save_steps": 200,
42
- "total_flos": 1788316538109952.0,
43
- "trial_name": null,
44
- "trial_params": null
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-400/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b11e88f2e4ef6351c9e83a0034b2ed5ce634c3c3b1f3b55d329f297d3eb9e82
3
- size 5329
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-600/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_3072/checkpoint-100000",
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 768,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 3072,
13
- "layer_norm_eps": 1e-12,
14
- "max_length": 512,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "position_embedding_type": "absolute",
21
- "problem_type": "single_label_classification",
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.35.2",
24
- "type_vocab_size": 2,
25
- "use_cache": true,
26
- "vocab_size": 3072
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-600/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3373fc9511d17faaac60e0fdad7204dd86747bf6036f55132661d0326a67e2bb
3
- size 353632152
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-600/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ae626991ec57a6b3592eddeacc9622a40e9bcc943745fb19afd50bb57bf5f93
3
- size 707385995
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-600/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:049a50c2af7bb1105baae851899ac2064be3773404dfa43297fdd152b868f6f7
3
- size 14709
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-600/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3855e6ec5cd7cab17828bc82a9698845221bc8ff444069cf522df24d43c7306
3
- size 1465
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-600/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-600/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_nontata_promoters/base_3072/checkpoint-600/tokenizer_config.json DELETED
@@ -1,56 +0,0 @@
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
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "cache_dir": null,
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "mask_token": "[MASK]",
48
- "model_max_length": 100,
49
- "pad_token": "[PAD]",
50
- "padding_side": "right",
51
- "sep_token": "[SEP]",
52
- "tokenizer_class": "PreTrainedTokenizerFast",
53
- "trust_remote_code": true,
54
- "unk_token": "[UNK]",
55
- "use_fast": true
56
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-600/trainer_state.json DELETED
@@ -1,58 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.6548672566371683,
5
- "eval_steps": 200,
6
- "global_step": 600,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.88,
13
- "eval_accuracy": 0.8560752836977581,
14
- "eval_f1": 0.8560728029108416,
15
- "eval_loss": 0.3306120038032532,
16
- "eval_matthews_correlation": 0.7317076841559982,
17
- "eval_precision": 0.8655274258206318,
18
- "eval_recall": 0.8661805498253218,
19
- "eval_runtime": 0.3536,
20
- "eval_samples_per_second": 10219.2,
21
- "eval_steps_per_second": 82.025,
22
- "step": 200
23
- },
24
- {
25
- "epoch": 1.77,
26
- "eval_accuracy": 0.880708552449488,
27
- "eval_f1": 0.8805239993079428,
28
- "eval_loss": 0.28219544887542725,
29
- "eval_matthews_correlation": 0.7700299247313025,
30
- "eval_precision": 0.8828539668283777,
31
- "eval_recall": 0.8871881555085832,
32
- "eval_runtime": 0.3274,
33
- "eval_samples_per_second": 11034.853,
34
- "eval_steps_per_second": 88.572,
35
- "step": 400
36
- },
37
- {
38
- "epoch": 2.65,
39
- "eval_accuracy": 0.8981455853861058,
40
- "eval_f1": 0.8978166185870242,
41
- "eval_loss": 0.26292458176612854,
42
- "eval_matthews_correlation": 0.8008571582942865,
43
- "eval_precision": 0.8979811620475748,
44
- "eval_recall": 0.9028910468346051,
45
- "eval_runtime": 0.3273,
46
- "eval_samples_per_second": 11039.781,
47
- "eval_steps_per_second": 88.612,
48
- "step": 600
49
- }
50
- ],
51
- "logging_steps": 100000,
52
- "max_steps": 678,
53
- "num_train_epochs": 3,
54
- "save_steps": 200,
55
- "total_flos": 2682055477428224.0,
56
- "trial_name": null,
57
- "trial_params": null
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_3072/checkpoint-600/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b11e88f2e4ef6351c9e83a0034b2ed5ce634c3c3b1f3b55d329f297d3eb9e82
3
- size 5329
 
 
 
 
human_nontata_promoters/base_3072/results/base_3072_hg38_BPE_3e-5_human_nontata_promoters_seed42/eval_results.json DELETED
@@ -1 +0,0 @@
1
- {"eval_loss": 0.24520762264728546, "eval_accuracy": 0.9070282235749861, "eval_f1": 0.9067483185110006, "eval_matthews_correlation": 0.8160075494294583, "eval_precision": 0.9063422405011909, "eval_recall": 0.9096721029449055, "eval_runtime": 0.3186, "eval_samples_per_second": 11343.923, "eval_steps_per_second": 91.028, "epoch": 3.0}
 
 
human_nontata_promoters/base_4096/checkpoint-200/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_4096/checkpoint-100000",
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 768,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 3072,
13
- "layer_norm_eps": 1e-12,
14
- "max_length": 512,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "position_embedding_type": "absolute",
21
- "problem_type": "single_label_classification",
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.35.2",
24
- "type_vocab_size": 2,
25
- "use_cache": true,
26
- "vocab_size": 4096
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-200/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaec310a6b2203bb93d7a2ab2899f52cb82f2d8b2f664789536feeac1da3f45e
3
- size 356777880
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-200/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a755afa0430aeb88f73b938fefc6887aebb7f5e05b79650a979da687080599f
3
- size 713677451
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-200/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3002a6e5523c06deb2862145d0a856e10f96d5e6d4b725c827a80bd86bca1ff5
3
- size 14709
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-200/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd7a706c2415bb6c236cc21c87a0c7ed17ea99d115c1adb3798d9895be0cb293
3
- size 1465
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-200/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-200/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_nontata_promoters/base_4096/checkpoint-200/tokenizer_config.json DELETED
@@ -1,56 +0,0 @@
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
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "cache_dir": null,
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "mask_token": "[MASK]",
48
- "model_max_length": 100,
49
- "pad_token": "[PAD]",
50
- "padding_side": "right",
51
- "sep_token": "[SEP]",
52
- "tokenizer_class": "PreTrainedTokenizerFast",
53
- "trust_remote_code": true,
54
- "unk_token": "[UNK]",
55
- "use_fast": true
56
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-200/trainer_state.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.8849557522123894,
5
- "eval_steps": 200,
6
- "global_step": 200,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.88,
13
- "eval_accuracy": 0.8505397176861335,
14
- "eval_f1": 0.8505272480440798,
15
- "eval_loss": 0.33328473567962646,
16
- "eval_matthews_correlation": 0.7186942170904793,
17
- "eval_precision": 0.8586758124930464,
18
- "eval_recall": 0.8600196609921325,
19
- "eval_runtime": 0.3164,
20
- "eval_samples_per_second": 11418.253,
21
- "eval_steps_per_second": 91.649,
22
- "step": 200
23
- }
24
- ],
25
- "logging_steps": 100000,
26
- "max_steps": 678,
27
- "num_train_epochs": 3,
28
- "save_steps": 200,
29
- "total_flos": 855110942982144.0,
30
- "trial_name": null,
31
- "trial_params": null
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-200/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b657b1f3091236cc245ae34faba2113502cf14a9a0ee2f66a0fec55188e991f9
3
- size 5329
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-400/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_4096/checkpoint-100000",
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 768,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 3072,
13
- "layer_norm_eps": 1e-12,
14
- "max_length": 512,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "position_embedding_type": "absolute",
21
- "problem_type": "single_label_classification",
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.35.2",
24
- "type_vocab_size": 2,
25
- "use_cache": true,
26
- "vocab_size": 4096
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-400/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c21b27cb5e7b287e34b7d9972818dc794d335e4648fe6af399782769d4c50694
3
- size 356777880
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-400/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d3c83c6a7b44fb39b83c62f8d116a0be0a2390a8a0a56985a26067f71fdc56f
3
- size 713677451
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-400/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:304b431b588a76d574eafcb6d625f54136161dd085285400b2e3b1218faa63b8
3
- size 14709
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-400/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2089997e4944f5cc2a0bcd083374dc434a2912ea0185d5b075e8268b38f5aa44
3
- size 1465
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-400/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-400/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_nontata_promoters/base_4096/checkpoint-400/tokenizer_config.json DELETED
@@ -1,56 +0,0 @@
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
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "cache_dir": null,
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "mask_token": "[MASK]",
48
- "model_max_length": 100,
49
- "pad_token": "[PAD]",
50
- "padding_side": "right",
51
- "sep_token": "[SEP]",
52
- "tokenizer_class": "PreTrainedTokenizerFast",
53
- "trust_remote_code": true,
54
- "unk_token": "[UNK]",
55
- "use_fast": true
56
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_nontata_promoters/base_4096/checkpoint-400/trainer_state.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.7699115044247788,
5
- "eval_steps": 200,
6
- "global_step": 400,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.88,
13
- "eval_accuracy": 0.8505397176861335,
14
- "eval_f1": 0.8505272480440798,
15
- "eval_loss": 0.33328473567962646,
16
- "eval_matthews_correlation": 0.7186942170904793,
17
- "eval_precision": 0.8586758124930464,
18
- "eval_recall": 0.8600196609921325,
19
- "eval_runtime": 0.3164,
20
- "eval_samples_per_second": 11418.253,
21
- "eval_steps_per_second": 91.649,
22
- "step": 200
23
- },
24
- {
25
- "epoch": 1.77,
26
- "eval_accuracy": 0.8831995571547191,
27
- "eval_f1": 0.8826055689528263,
28
- "eval_loss": 0.2829147279262543,
29
- "eval_matthews_correlation": 0.7679681311666743,
30
- "eval_precision": 0.8818288562194951,
31
- "eval_recall": 0.8861514398931395,
32
- "eval_runtime": 0.2891,
33
- "eval_samples_per_second": 12495.348,
34
- "eval_steps_per_second": 100.295,
35
- "step": 400
36
- }
37
- ],
38
- "logging_steps": 100000,
39
- "max_steps": 678,
40
- "num_train_epochs": 3,
41
- "save_steps": 200,
42
- "total_flos": 1709420203474944.0,
43
- "trial_name": null,
44
- "trial_params": null
45
- }