Hugging Face's logo

nancyH
/
full_output

Model card Files
xet
 Community
nancyH commited on
Commit
2bce03c
·
verified ·
1 Parent(s): 0d755a6

Delete human_enhancers_cohn

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_enhancers_cohn/base_3072/checkpoint-200/config.json +0 -27
  2. human_enhancers_cohn/base_3072/checkpoint-200/model.safetensors +0 -3
  3. human_enhancers_cohn/base_3072/checkpoint-200/optimizer.pt +0 -3
  4. human_enhancers_cohn/base_3072/checkpoint-200/rng_state.pth +0 -3
  5. human_enhancers_cohn/base_3072/checkpoint-200/scheduler.pt +0 -3
  6. human_enhancers_cohn/base_3072/checkpoint-200/special_tokens_map.json +0 -7
  7. human_enhancers_cohn/base_3072/checkpoint-200/tokenizer.json +0 -0
  8. human_enhancers_cohn/base_3072/checkpoint-200/tokenizer_config.json +0 -56
  9. human_enhancers_cohn/base_3072/checkpoint-200/trainer_state.json +0 -32
  10. human_enhancers_cohn/base_3072/checkpoint-200/training_args.bin +0 -3
  11. human_enhancers_cohn/base_3072/checkpoint-400/config.json +0 -27
  12. human_enhancers_cohn/base_3072/checkpoint-400/model.safetensors +0 -3
  13. human_enhancers_cohn/base_3072/checkpoint-400/optimizer.pt +0 -3
  14. human_enhancers_cohn/base_3072/checkpoint-400/rng_state.pth +0 -3
  15. human_enhancers_cohn/base_3072/checkpoint-400/scheduler.pt +0 -3
  16. human_enhancers_cohn/base_3072/checkpoint-400/special_tokens_map.json +0 -7
  17. human_enhancers_cohn/base_3072/checkpoint-400/tokenizer.json +0 -0
  18. human_enhancers_cohn/base_3072/checkpoint-400/tokenizer_config.json +0 -56
  19. human_enhancers_cohn/base_3072/checkpoint-400/trainer_state.json +0 -45
  20. human_enhancers_cohn/base_3072/checkpoint-400/training_args.bin +0 -3
  21. human_enhancers_cohn/base_3072/results/base_3072_hg38_BPE_3e-5_human_enhancers_cohn_seed42/eval_results.json +0 -1
  22. human_enhancers_cohn/base_4096/checkpoint-200/config.json +0 -27
  23. human_enhancers_cohn/base_4096/checkpoint-200/model.safetensors +0 -3
  24. human_enhancers_cohn/base_4096/checkpoint-200/optimizer.pt +0 -3
  25. human_enhancers_cohn/base_4096/checkpoint-200/rng_state.pth +0 -3
  26. human_enhancers_cohn/base_4096/checkpoint-200/scheduler.pt +0 -3
  27. human_enhancers_cohn/base_4096/checkpoint-200/special_tokens_map.json +0 -7
  28. human_enhancers_cohn/base_4096/checkpoint-200/tokenizer.json +0 -0
  29. human_enhancers_cohn/base_4096/checkpoint-200/tokenizer_config.json +0 -56
  30. human_enhancers_cohn/base_4096/checkpoint-200/trainer_state.json +0 -32
  31. human_enhancers_cohn/base_4096/checkpoint-200/training_args.bin +0 -3
  32. human_enhancers_cohn/base_4096/checkpoint-400/config.json +0 -27
  33. human_enhancers_cohn/base_4096/checkpoint-400/model.safetensors +0 -3
  34. human_enhancers_cohn/base_4096/checkpoint-400/optimizer.pt +0 -3
  35. human_enhancers_cohn/base_4096/checkpoint-400/rng_state.pth +0 -3
  36. human_enhancers_cohn/base_4096/checkpoint-400/scheduler.pt +0 -3
  37. human_enhancers_cohn/base_4096/checkpoint-400/special_tokens_map.json +0 -7
  38. human_enhancers_cohn/base_4096/checkpoint-400/tokenizer.json +0 -0
  39. human_enhancers_cohn/base_4096/checkpoint-400/tokenizer_config.json +0 -56
  40. human_enhancers_cohn/base_4096/checkpoint-400/trainer_state.json +0 -45
  41. human_enhancers_cohn/base_4096/checkpoint-400/training_args.bin +0 -3
  42. human_enhancers_cohn/base_4096/results/base_4096_hg38_BPE_3e-5_human_enhancers_cohn_seed42/eval_results.json +0 -1
  43. human_enhancers_cohn/len2_4096/checkpoint-200/config.json +0 -27
  44. human_enhancers_cohn/len2_4096/checkpoint-200/model.safetensors +0 -3
  45. human_enhancers_cohn/len2_4096/checkpoint-200/optimizer.pt +0 -3
  46. human_enhancers_cohn/len2_4096/checkpoint-200/rng_state.pth +0 -3
  47. human_enhancers_cohn/len2_4096/checkpoint-200/scheduler.pt +0 -3
  48. human_enhancers_cohn/len2_4096/checkpoint-200/special_tokens_map.json +0 -7
  49. human_enhancers_cohn/len2_4096/checkpoint-200/tokenizer.json +0 -0
  50. human_enhancers_cohn/len2_4096/checkpoint-200/tokenizer_config.json +0 -15
human_enhancers_cohn/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_enhancers_cohn/base_3072/checkpoint-200/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1c3c78c0f76fa53a518fa1d22f9df99ff736b2ca3a8908cfd0e549b6a22879d
3
- size 353632152
 
 
 
 
human_enhancers_cohn/base_3072/checkpoint-200/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a628ae7eab4421da983805cf7f5e6eb448bba273fe46601328c7955019c2d0e
3
- size 707385995
 
 
 
 
human_enhancers_cohn/base_3072/checkpoint-200/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e42ae1e4d1487d5e895b4aedb9ab73c4b5e5e7cb820f8e2c7209169be990d46
3
- size 14709
 
 
 
 
human_enhancers_cohn/base_3072/checkpoint-200/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb8396a28d05435f8711ed63af5f363fe80d8db70c66f1da4bc3ca37047db868
3
- size 1465
 
 
 
 
human_enhancers_cohn/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_enhancers_cohn/base_3072/checkpoint-200/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_enhancers_cohn/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_enhancers_cohn/base_3072/checkpoint-200/trainer_state.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.1494252873563218,
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": 1.15,
13
- "eval_accuracy": 0.7286793810723282,
14
- "eval_f1": 0.7271360409211425,
15
- "eval_loss": 0.5445785522460938,
16
- "eval_matthews_correlation": 0.46663894149578333,
17
- "eval_precision": 0.7365956748590126,
18
- "eval_recall": 0.7300886331185719,
19
- "eval_runtime": 0.348,
20
- "eval_samples_per_second": 7985.407,
21
- "eval_steps_per_second": 63.217,
22
- "step": 200
23
- }
24
- ],
25
- "logging_steps": 100000,
26
- "max_steps": 522,
27
- "num_train_epochs": 3,
28
- "save_steps": 200,
29
- "total_flos": 1313499783364608.0,
30
- "trial_name": null,
31
- "trial_params": null
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_enhancers_cohn/base_3072/checkpoint-200/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8c6df0d1fd7a8910e91ac2e4665756964d043de7f403929bacfd9e34f1388b5
3
- size 5329
 
 
 
 
human_enhancers_cohn/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_enhancers_cohn/base_3072/checkpoint-400/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca1bb44d247fe4142437d9c68fc97ec540fca4ad0152b71adb5756435b631832
3
- size 353632152
 
 
 
 
human_enhancers_cohn/base_3072/checkpoint-400/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a2fcbac5e10b061d1fba1acef2b3672c839dbf49f2eb95f605f21b20d1303df
3
- size 707385995
 
 
 
 
human_enhancers_cohn/base_3072/checkpoint-400/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf4fe29cf4fa8f59481df0375c4e4cf281f735468b247420d21bee83dfb267a0
3
- size 14709
 
 
 
 
human_enhancers_cohn/base_3072/checkpoint-400/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c56e12e83caf66084bf3a11d3b018aa44e73d3fae41719bdf4ec4aebd71349b8
3
- size 1465
 
 
 
 
human_enhancers_cohn/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_enhancers_cohn/base_3072/checkpoint-400/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_enhancers_cohn/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_enhancers_cohn/base_3072/checkpoint-400/trainer_state.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.2988505747126435,
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": 1.15,
13
- "eval_accuracy": 0.7286793810723282,
14
- "eval_f1": 0.7271360409211425,
15
- "eval_loss": 0.5445785522460938,
16
- "eval_matthews_correlation": 0.46663894149578333,
17
- "eval_precision": 0.7365956748590126,
18
- "eval_recall": 0.7300886331185719,
19
- "eval_runtime": 0.348,
20
- "eval_samples_per_second": 7985.407,
21
- "eval_steps_per_second": 63.217,
22
- "step": 200
23
- },
24
- {
25
- "epoch": 2.3,
26
- "eval_accuracy": 0.7315581144296509,
27
- "eval_f1": 0.7303631758953757,
28
- "eval_loss": 0.5473530292510986,
29
- "eval_matthews_correlation": 0.4708754627902413,
30
- "eval_precision": 0.7380764695224866,
31
- "eval_recall": 0.7328282399166098,
32
- "eval_runtime": 0.3356,
33
- "eval_samples_per_second": 8281.835,
34
- "eval_steps_per_second": 65.563,
35
- "step": 400
36
- }
37
- ],
38
- "logging_steps": 100000,
39
- "max_steps": 522,
40
- "num_train_epochs": 3,
41
- "save_steps": 200,
42
- "total_flos": 2626999566729216.0,
43
- "trial_name": null,
44
- "trial_params": null
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_enhancers_cohn/base_3072/checkpoint-400/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8c6df0d1fd7a8910e91ac2e4665756964d043de7f403929bacfd9e34f1388b5
3
- size 5329
 
 
 
 
human_enhancers_cohn/base_3072/results/base_3072_hg38_BPE_3e-5_human_enhancers_cohn_seed42/eval_results.json DELETED
@@ -1 +0,0 @@
1
- {"eval_loss": 0.5286217331886292, "eval_accuracy": 0.7478417266187051, "eval_f1": 0.747571248577904, "eval_matthews_correlation": 0.4964151424232939, "eval_precision": 0.7486823947994081, "eval_recall": 0.7477336542318491, "eval_runtime": 0.3382, "eval_samples_per_second": 8219.743, "eval_steps_per_second": 65.048, "epoch": 3.0}
 
 
human_enhancers_cohn/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_enhancers_cohn/base_4096/checkpoint-200/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:17f8ea34fd87774272dee433615c534e78b812c987288cc29089ef02640c988c
3
- size 356777880
 
 
 
 
human_enhancers_cohn/base_4096/checkpoint-200/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae741782ffa1b91d2583dd6e1adf687fffe531777e99a7871a49bf36deaa1187
3
- size 713677451
 
 
 
 
human_enhancers_cohn/base_4096/checkpoint-200/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e42ae1e4d1487d5e895b4aedb9ab73c4b5e5e7cb820f8e2c7209169be990d46
3
- size 14709
 
 
 
 
human_enhancers_cohn/base_4096/checkpoint-200/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb8396a28d05435f8711ed63af5f363fe80d8db70c66f1da4bc3ca37047db868
3
- size 1465
 
 
 
 
human_enhancers_cohn/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_enhancers_cohn/base_4096/checkpoint-200/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_enhancers_cohn/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_enhancers_cohn/base_4096/checkpoint-200/trainer_state.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.1494252873563218,
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": 1.15,
13
- "eval_accuracy": 0.7272400143936668,
14
- "eval_f1": 0.726651008279048,
15
- "eval_loss": 0.5429649949073792,
16
- "eval_matthews_correlation": 0.4590420984631282,
17
- "eval_precision": 0.7308673322297692,
18
- "eval_recall": 0.7281826169669112,
19
- "eval_runtime": 0.3499,
20
- "eval_samples_per_second": 7943.048,
21
- "eval_steps_per_second": 62.881,
22
- "step": 200
23
- }
24
- ],
25
- "logging_steps": 100000,
26
- "max_steps": 522,
27
- "num_train_epochs": 3,
28
- "save_steps": 200,
29
- "total_flos": 1313499783364608.0,
30
- "trial_name": null,
31
- "trial_params": null
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_enhancers_cohn/base_4096/checkpoint-200/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a64e6cdb75d2c4c3c7a14d660dc111937f95bed2b6a6945ed2b775bb8a44575
3
- size 5329
 
 
 
 
human_enhancers_cohn/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_enhancers_cohn/base_4096/checkpoint-400/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a89e0fa0910b22b9665a40cf1ebc94092151a2e6a189c3722f0993a717f95f3
3
- size 356777880
 
 
 
 
human_enhancers_cohn/base_4096/checkpoint-400/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e696bee8175087f3b9982ebbb087e7cc5bda7fa2993eac0c6153c308dc8e5ee3
3
- size 713677451
 
 
 
 
human_enhancers_cohn/base_4096/checkpoint-400/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf4fe29cf4fa8f59481df0375c4e4cf281f735468b247420d21bee83dfb267a0
3
- size 14709
 
 
 
 
human_enhancers_cohn/base_4096/checkpoint-400/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c56e12e83caf66084bf3a11d3b018aa44e73d3fae41719bdf4ec4aebd71349b8
3
- size 1465
 
 
 
 
human_enhancers_cohn/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_enhancers_cohn/base_4096/checkpoint-400/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_enhancers_cohn/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_enhancers_cohn/base_4096/checkpoint-400/trainer_state.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.2988505747126435,
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": 1.15,
13
- "eval_accuracy": 0.7272400143936668,
14
- "eval_f1": 0.726651008279048,
15
- "eval_loss": 0.5429649949073792,
16
- "eval_matthews_correlation": 0.4590420984631282,
17
- "eval_precision": 0.7308673322297692,
18
- "eval_recall": 0.7281826169669112,
19
- "eval_runtime": 0.3499,
20
- "eval_samples_per_second": 7943.048,
21
- "eval_steps_per_second": 62.881,
22
- "step": 200
23
- },
24
- {
25
- "epoch": 2.3,
26
- "eval_accuracy": 0.7311982727599856,
27
- "eval_f1": 0.7303485546869165,
28
- "eval_loss": 0.5538003444671631,
29
- "eval_matthews_correlation": 0.46841885139218503,
30
- "eval_precision": 0.7361352778105461,
31
- "eval_recall": 0.7322992802833276,
32
- "eval_runtime": 0.3367,
33
- "eval_samples_per_second": 8254.814,
34
- "eval_steps_per_second": 65.349,
35
- "step": 400
36
- }
37
- ],
38
- "logging_steps": 100000,
39
- "max_steps": 522,
40
- "num_train_epochs": 3,
41
- "save_steps": 200,
42
- "total_flos": 2626999566729216.0,
43
- "trial_name": null,
44
- "trial_params": null
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
human_enhancers_cohn/base_4096/checkpoint-400/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a64e6cdb75d2c4c3c7a14d660dc111937f95bed2b6a6945ed2b775bb8a44575
3
- size 5329
 
 
 
 
human_enhancers_cohn/base_4096/results/base_4096_hg38_BPE_3e-5_human_enhancers_cohn_seed42/eval_results.json DELETED
@@ -1 +0,0 @@
1
- {"eval_loss": 0.5185958743095398, "eval_accuracy": 0.7568345323741007, "eval_f1": 0.7568344065185065, "eval_matthews_correlation": 0.5136970171361614, "eval_precision": 0.7568501038533662, "eval_recall": 0.7568469132927035, "eval_runtime": 0.3402, "eval_samples_per_second": 8172.163, "eval_steps_per_second": 64.672, "epoch": 3.0}
 
 
human_enhancers_cohn/len2_4096/checkpoint-200/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/model_len2_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_enhancers_cohn/len2_4096/checkpoint-200/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:efcd4d4cbed93bfdbaacc31b84d83bc08e5f225251adfc0636182562c7003d6b
3
- size 356777880
 
 
 
 
human_enhancers_cohn/len2_4096/checkpoint-200/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:744f69f215485b9463065926fd18c83fe8a9e9470e0addacb1b680e537c30c66
3
- size 713677451
 
 
 
 
human_enhancers_cohn/len2_4096/checkpoint-200/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e42ae1e4d1487d5e895b4aedb9ab73c4b5e5e7cb820f8e2c7209169be990d46
3
- size 14709
 
 
 
 
human_enhancers_cohn/len2_4096/checkpoint-200/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb8396a28d05435f8711ed63af5f363fe80d8db70c66f1da4bc3ca37047db868
3
- size 1465
 
 
 
 
human_enhancers_cohn/len2_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_enhancers_cohn/len2_4096/checkpoint-200/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
human_enhancers_cohn/len2_4096/checkpoint-200/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "added_tokens_decoder": {},
3
- "cache_dir": null,
4
- "clean_up_tokenization_spaces": true,
5
- "cls_token": "[CLS]",
6
- "mask_token": "[MASK]",
7
- "model_max_length": 100,
8
- "pad_token": "[PAD]",
9
- "padding_side": "right",
10
- "sep_token": "[SEP]",
11
- "tokenizer_class": "PreTrainedTokenizerFast",
12
- "trust_remote_code": true,
13
- "unk_token": "[UNK]",
14
- "use_fast": true
15
- }