Hugging Face's logo

nancyH
/
sft_save

Model card Files
xet
 Community
nancyH commited on
Commit
ef7d2db
·
verified ·
1 Parent(s): f750c8d

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +17 -0
  2. Finetune-species/super_all/super_log_1e-5_len2_4096.txt +0 -0
  3. Finetune-species/super_all/super_log_2e-5_len2_4096.txt +0 -0
  4. Finetune-species/super_all/super_log_3e-5_len2_3072.txt +0 -0
  5. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/config.json +27 -0
  6. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/model.safetensors +3 -0
  7. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/optimizer.pt +3 -0
  8. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/rng_state.pth +3 -0
  9. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/scheduler.pt +3 -0
  10. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/special_tokens_map.json +7 -0
  11. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/tokenizer.json +0 -0
  12. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/tokenizer_config.json +56 -0
  13. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/trainer_state.json +110 -0
  14. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/training_args.bin +3 -0
  15. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/config.json +27 -0
  16. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/model.safetensors +3 -0
  17. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/optimizer.pt +3 -0
  18. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/rng_state.pth +3 -0
  19. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/scheduler.pt +3 -0
  20. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/special_tokens_map.json +7 -0
  21. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/tokenizer.json +0 -0
  22. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/tokenizer_config.json +56 -0
  23. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/trainer_state.json +123 -0
  24. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/training_args.bin +3 -0
  25. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/config.json +27 -0
  26. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/model.safetensors +3 -0
  27. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/optimizer.pt +3 -0
  28. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/rng_state.pth +3 -0
  29. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/scheduler.pt +3 -0
  30. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/special_tokens_map.json +7 -0
  31. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/tokenizer.json +0 -0
  32. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/tokenizer_config.json +56 -0
  33. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/trainer_state.json +136 -0
  34. Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/training_args.bin +3 -0
  35. Finetune-species/super_binary_out/EXC/base_3072/1e-5/results/hg38_base_3072_binary_EXC_1e-5_seed42/eval_results.json +1 -0
  36. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/config.json +27 -0
  37. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/model.safetensors +3 -0
  38. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/optimizer.pt +3 -0
  39. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/rng_state.pth +3 -0
  40. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/scheduler.pt +3 -0
  41. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/special_tokens_map.json +7 -0
  42. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/tokenizer.json +0 -0
  43. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/tokenizer_config.json +56 -0
  44. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/trainer_state.json +110 -0
  45. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/training_args.bin +3 -0
  46. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/config.json +27 -0
  47. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/model.safetensors +3 -0
  48. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/optimizer.pt +3 -0
  49. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/rng_state.pth +3 -0
  50. Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/scheduler.pt +3 -0
.gitattributes CHANGED
@@ -33,3 +33,20 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ finetune_data/human_chr1/train.csv filter=lfs diff=lfs merge=lfs -text
37
+ finetune_data/human_mouse_superclass/train.csv filter=lfs diff=lfs merge=lfs -text
38
+ finetune_data/human_mouse_superclass_allchr/dev.csv filter=lfs diff=lfs merge=lfs -text
39
+ finetune_data/human_mouse_superclass_allchr/test.csv filter=lfs diff=lfs merge=lfs -text
40
+ finetune_data/human_mouse_superclass_allchr/train.csv filter=lfs diff=lfs merge=lfs -text
41
+ finetune_data/super_binary/EXC/dev.csv filter=lfs diff=lfs merge=lfs -text
42
+ finetune_data/super_binary/EXC/test.csv filter=lfs diff=lfs merge=lfs -text
43
+ finetune_data/super_binary/EXC/train.csv filter=lfs diff=lfs merge=lfs -text
44
+ finetune_data/super_binary/GLIA/dev.csv filter=lfs diff=lfs merge=lfs -text
45
+ finetune_data/super_binary/GLIA/test.csv filter=lfs diff=lfs merge=lfs -text
46
+ finetune_data/super_binary/GLIA/train.csv filter=lfs diff=lfs merge=lfs -text
47
+ finetune_data/super_binary/INH/dev.csv filter=lfs diff=lfs merge=lfs -text
48
+ finetune_data/super_binary/INH/test.csv filter=lfs diff=lfs merge=lfs -text
49
+ finetune_data/super_binary/INH/train.csv filter=lfs diff=lfs merge=lfs -text
50
+ finetune_data/super_binary/VASC/dev.csv filter=lfs diff=lfs merge=lfs -text
51
+ finetune_data/super_binary/VASC/test.csv filter=lfs diff=lfs merge=lfs -text
52
+ finetune_data/super_binary/VASC/train.csv filter=lfs diff=lfs merge=lfs -text
Finetune-species/super_all/super_log_1e-5_len2_4096.txt ADDED
The diff for this file is too large to render. See raw diff
 
Finetune-species/super_all/super_log_2e-5_len2_4096.txt ADDED
The diff for this file is too large to render. See raw diff
 
Finetune-species/super_all/super_log_3e-5_len2_3072.txt ADDED
The diff for this file is too large to render. See raw diff
 
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b16fee2813f01925a658af971d0625e9d7ab30673dab263e00137e2f6ee5f2
3
+ size 353632152
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea8928b0057cdc88bf129170a078b88780ce4e5a3a48c64157c34f2544393d41
3
+ size 707385995
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0963727d789ed8c5c4353e630d29b9e3b59de56f59ecce385cdc22c0e9064b0b
3
+ size 14709
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ba381e07add5e135217829284fed29b78d6b593ab562e0cb3993675f5b72f6e
3
+ size 1465
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/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
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 200,
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
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/trainer_state.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.826050769870995,
5
+ "eval_steps": 2000,
6
+ "global_step": 14000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.83,
13
+ "eval_accuracy": 0.6621315782627923,
14
+ "eval_f1": 0.6389272473588227,
15
+ "eval_loss": 0.6076656579971313,
16
+ "eval_matthews_correlation": 0.2804832428729253,
17
+ "eval_precision": 0.6435690012232795,
18
+ "eval_recall": 0.6369913575740542,
19
+ "eval_runtime": 9.4141,
20
+ "eval_samples_per_second": 4083.36,
21
+ "eval_steps_per_second": 31.973,
22
+ "step": 2000
23
+ },
24
+ {
25
+ "epoch": 1.66,
26
+ "eval_accuracy": 0.685726177778934,
27
+ "eval_f1": 0.6519193721992602,
28
+ "eval_loss": 0.58486407995224,
29
+ "eval_matthews_correlation": 0.31963621430985056,
30
+ "eval_precision": 0.6715556126964769,
31
+ "eval_recall": 0.6488836592001965,
32
+ "eval_runtime": 9.3933,
33
+ "eval_samples_per_second": 4092.365,
34
+ "eval_steps_per_second": 32.044,
35
+ "step": 4000
36
+ },
37
+ {
38
+ "epoch": 2.5,
39
+ "eval_accuracy": 0.6954293592778543,
40
+ "eval_f1": 0.66558915972636,
41
+ "eval_loss": 0.5786334276199341,
42
+ "eval_matthews_correlation": 0.34328529923986345,
43
+ "eval_precision": 0.6819929153238782,
44
+ "eval_recall": 0.6618810222151831,
45
+ "eval_runtime": 9.3974,
46
+ "eval_samples_per_second": 4090.585,
47
+ "eval_steps_per_second": 32.03,
48
+ "step": 6000
49
+ },
50
+ {
51
+ "epoch": 3.33,
52
+ "eval_accuracy": 0.6939725813584454,
53
+ "eval_f1": 0.6724349617776113,
54
+ "eval_loss": 0.575185239315033,
55
+ "eval_matthews_correlation": 0.3480476794165012,
56
+ "eval_precision": 0.6784947619655025,
57
+ "eval_recall": 0.6696649047474901,
58
+ "eval_runtime": 9.3996,
59
+ "eval_samples_per_second": 4089.659,
60
+ "eval_steps_per_second": 32.023,
61
+ "step": 8000
62
+ },
63
+ {
64
+ "epoch": 4.16,
65
+ "eval_accuracy": 0.6942067063812075,
66
+ "eval_f1": 0.6810690087892022,
67
+ "eval_loss": 0.5835163593292236,
68
+ "eval_matthews_correlation": 0.3622167783712192,
69
+ "eval_precision": 0.6805447649547932,
70
+ "eval_recall": 0.6816737729372497,
71
+ "eval_runtime": 9.4022,
72
+ "eval_samples_per_second": 4088.519,
73
+ "eval_steps_per_second": 32.014,
74
+ "step": 10000
75
+ },
76
+ {
77
+ "epoch": 4.99,
78
+ "eval_accuracy": 0.6953253037121823,
79
+ "eval_f1": 0.6819717121560409,
80
+ "eval_loss": 0.5859789848327637,
81
+ "eval_matthews_correlation": 0.36398608412393796,
82
+ "eval_precision": 0.6815722568486511,
83
+ "eval_recall": 0.6824148024253389,
84
+ "eval_runtime": 9.3963,
85
+ "eval_samples_per_second": 4091.074,
86
+ "eval_steps_per_second": 32.034,
87
+ "step": 12000
88
+ },
89
+ {
90
+ "epoch": 5.83,
91
+ "eval_accuracy": 0.6944148175125517,
92
+ "eval_f1": 0.6810035650876347,
93
+ "eval_loss": 0.5960980653762817,
94
+ "eval_matthews_correlation": 0.3620477057961027,
95
+ "eval_precision": 0.6806150772404629,
96
+ "eval_recall": 0.6814335537139422,
97
+ "eval_runtime": 9.3999,
98
+ "eval_samples_per_second": 4089.503,
99
+ "eval_steps_per_second": 32.022,
100
+ "step": 14000
101
+ }
102
+ ],
103
+ "logging_steps": 100000,
104
+ "max_steps": 19224,
105
+ "num_train_epochs": 8,
106
+ "save_steps": 2000,
107
+ "total_flos": 1.3442911984785818e+17,
108
+ "trial_name": null,
109
+ "trial_params": null
110
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-14000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052f5e59f37198a420891d569948a9d14d826d9b2581f670b828968c10bba7ae
3
+ size 5265
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c38de488c828379051dd091913424a30cfa28b7eb16f9de3770e73e68b8fe9
3
+ size 353632152
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a3bc219971003b2f72b7174361cf94381dc6cdc3dc4c3c6fd05622f2eeee7e
3
+ size 707385995
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582db6c10e2e144f265a8f72396158d38ffd0b29c89124d29d3b864320a4f8af
3
+ size 14709
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9f3f186cba40eaea3fc8577787126749ae54a95842094a4cb89ba56eb801d2
3
+ size 1465
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/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
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 200,
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
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/trainer_state.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.658343736995422,
5
+ "eval_steps": 2000,
6
+ "global_step": 16000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.83,
13
+ "eval_accuracy": 0.6621315782627923,
14
+ "eval_f1": 0.6389272473588227,
15
+ "eval_loss": 0.6076656579971313,
16
+ "eval_matthews_correlation": 0.2804832428729253,
17
+ "eval_precision": 0.6435690012232795,
18
+ "eval_recall": 0.6369913575740542,
19
+ "eval_runtime": 9.4141,
20
+ "eval_samples_per_second": 4083.36,
21
+ "eval_steps_per_second": 31.973,
22
+ "step": 2000
23
+ },
24
+ {
25
+ "epoch": 1.66,
26
+ "eval_accuracy": 0.685726177778934,
27
+ "eval_f1": 0.6519193721992602,
28
+ "eval_loss": 0.58486407995224,
29
+ "eval_matthews_correlation": 0.31963621430985056,
30
+ "eval_precision": 0.6715556126964769,
31
+ "eval_recall": 0.6488836592001965,
32
+ "eval_runtime": 9.3933,
33
+ "eval_samples_per_second": 4092.365,
34
+ "eval_steps_per_second": 32.044,
35
+ "step": 4000
36
+ },
37
+ {
38
+ "epoch": 2.5,
39
+ "eval_accuracy": 0.6954293592778543,
40
+ "eval_f1": 0.66558915972636,
41
+ "eval_loss": 0.5786334276199341,
42
+ "eval_matthews_correlation": 0.34328529923986345,
43
+ "eval_precision": 0.6819929153238782,
44
+ "eval_recall": 0.6618810222151831,
45
+ "eval_runtime": 9.3974,
46
+ "eval_samples_per_second": 4090.585,
47
+ "eval_steps_per_second": 32.03,
48
+ "step": 6000
49
+ },
50
+ {
51
+ "epoch": 3.33,
52
+ "eval_accuracy": 0.6939725813584454,
53
+ "eval_f1": 0.6724349617776113,
54
+ "eval_loss": 0.575185239315033,
55
+ "eval_matthews_correlation": 0.3480476794165012,
56
+ "eval_precision": 0.6784947619655025,
57
+ "eval_recall": 0.6696649047474901,
58
+ "eval_runtime": 9.3996,
59
+ "eval_samples_per_second": 4089.659,
60
+ "eval_steps_per_second": 32.023,
61
+ "step": 8000
62
+ },
63
+ {
64
+ "epoch": 4.16,
65
+ "eval_accuracy": 0.6942067063812075,
66
+ "eval_f1": 0.6810690087892022,
67
+ "eval_loss": 0.5835163593292236,
68
+ "eval_matthews_correlation": 0.3622167783712192,
69
+ "eval_precision": 0.6805447649547932,
70
+ "eval_recall": 0.6816737729372497,
71
+ "eval_runtime": 9.4022,
72
+ "eval_samples_per_second": 4088.519,
73
+ "eval_steps_per_second": 32.014,
74
+ "step": 10000
75
+ },
76
+ {
77
+ "epoch": 4.99,
78
+ "eval_accuracy": 0.6953253037121823,
79
+ "eval_f1": 0.6819717121560409,
80
+ "eval_loss": 0.5859789848327637,
81
+ "eval_matthews_correlation": 0.36398608412393796,
82
+ "eval_precision": 0.6815722568486511,
83
+ "eval_recall": 0.6824148024253389,
84
+ "eval_runtime": 9.3963,
85
+ "eval_samples_per_second": 4091.074,
86
+ "eval_steps_per_second": 32.034,
87
+ "step": 12000
88
+ },
89
+ {
90
+ "epoch": 5.83,
91
+ "eval_accuracy": 0.6944148175125517,
92
+ "eval_f1": 0.6810035650876347,
93
+ "eval_loss": 0.5960980653762817,
94
+ "eval_matthews_correlation": 0.3620477057961027,
95
+ "eval_precision": 0.6806150772404629,
96
+ "eval_recall": 0.6814335537139422,
97
+ "eval_runtime": 9.3999,
98
+ "eval_samples_per_second": 4089.503,
99
+ "eval_steps_per_second": 32.022,
100
+ "step": 14000
101
+ },
102
+ {
103
+ "epoch": 6.66,
104
+ "eval_accuracy": 0.6955854426263625,
105
+ "eval_f1": 0.680756229628503,
106
+ "eval_loss": 0.6167765259742737,
107
+ "eval_matthews_correlation": 0.36155211034902845,
108
+ "eval_precision": 0.681201736918476,
109
+ "eval_recall": 0.6803513734482689,
110
+ "eval_runtime": 9.4009,
111
+ "eval_samples_per_second": 4089.094,
112
+ "eval_steps_per_second": 32.018,
113
+ "step": 16000
114
+ }
115
+ ],
116
+ "logging_steps": 100000,
117
+ "max_steps": 19224,
118
+ "num_train_epochs": 8,
119
+ "save_steps": 2000,
120
+ "total_flos": 1.5363210116438426e+17,
121
+ "trial_name": null,
122
+ "trial_params": null
123
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-16000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052f5e59f37198a420891d569948a9d14d826d9b2581f670b828968c10bba7ae
3
+ size 5265
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7710d82c155185728e0dc145638a961d575fa74c20f03d6aa334b77b5790ff03
3
+ size 353632152
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3302841f947f753031903c4d56feabc9da66e2eb2e1c39fc4e5d2bc7dc2984fb
3
+ size 707385995
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c030c0ec9093c4179f2ebb4b55bec5c6d659a771f533fb7b6f9c0ffe26bf5b16
3
+ size 14709
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f677d3c5981d7b2ee138b6dee3eed349cf9acbac54a08f15997226974bad87c1
3
+ size 1465
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/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
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 200,
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
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.49063670411985,
5
+ "eval_steps": 2000,
6
+ "global_step": 18000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.83,
13
+ "eval_accuracy": 0.6621315782627923,
14
+ "eval_f1": 0.6389272473588227,
15
+ "eval_loss": 0.6076656579971313,
16
+ "eval_matthews_correlation": 0.2804832428729253,
17
+ "eval_precision": 0.6435690012232795,
18
+ "eval_recall": 0.6369913575740542,
19
+ "eval_runtime": 9.4141,
20
+ "eval_samples_per_second": 4083.36,
21
+ "eval_steps_per_second": 31.973,
22
+ "step": 2000
23
+ },
24
+ {
25
+ "epoch": 1.66,
26
+ "eval_accuracy": 0.685726177778934,
27
+ "eval_f1": 0.6519193721992602,
28
+ "eval_loss": 0.58486407995224,
29
+ "eval_matthews_correlation": 0.31963621430985056,
30
+ "eval_precision": 0.6715556126964769,
31
+ "eval_recall": 0.6488836592001965,
32
+ "eval_runtime": 9.3933,
33
+ "eval_samples_per_second": 4092.365,
34
+ "eval_steps_per_second": 32.044,
35
+ "step": 4000
36
+ },
37
+ {
38
+ "epoch": 2.5,
39
+ "eval_accuracy": 0.6954293592778543,
40
+ "eval_f1": 0.66558915972636,
41
+ "eval_loss": 0.5786334276199341,
42
+ "eval_matthews_correlation": 0.34328529923986345,
43
+ "eval_precision": 0.6819929153238782,
44
+ "eval_recall": 0.6618810222151831,
45
+ "eval_runtime": 9.3974,
46
+ "eval_samples_per_second": 4090.585,
47
+ "eval_steps_per_second": 32.03,
48
+ "step": 6000
49
+ },
50
+ {
51
+ "epoch": 3.33,
52
+ "eval_accuracy": 0.6939725813584454,
53
+ "eval_f1": 0.6724349617776113,
54
+ "eval_loss": 0.575185239315033,
55
+ "eval_matthews_correlation": 0.3480476794165012,
56
+ "eval_precision": 0.6784947619655025,
57
+ "eval_recall": 0.6696649047474901,
58
+ "eval_runtime": 9.3996,
59
+ "eval_samples_per_second": 4089.659,
60
+ "eval_steps_per_second": 32.023,
61
+ "step": 8000
62
+ },
63
+ {
64
+ "epoch": 4.16,
65
+ "eval_accuracy": 0.6942067063812075,
66
+ "eval_f1": 0.6810690087892022,
67
+ "eval_loss": 0.5835163593292236,
68
+ "eval_matthews_correlation": 0.3622167783712192,
69
+ "eval_precision": 0.6805447649547932,
70
+ "eval_recall": 0.6816737729372497,
71
+ "eval_runtime": 9.4022,
72
+ "eval_samples_per_second": 4088.519,
73
+ "eval_steps_per_second": 32.014,
74
+ "step": 10000
75
+ },
76
+ {
77
+ "epoch": 4.99,
78
+ "eval_accuracy": 0.6953253037121823,
79
+ "eval_f1": 0.6819717121560409,
80
+ "eval_loss": 0.5859789848327637,
81
+ "eval_matthews_correlation": 0.36398608412393796,
82
+ "eval_precision": 0.6815722568486511,
83
+ "eval_recall": 0.6824148024253389,
84
+ "eval_runtime": 9.3963,
85
+ "eval_samples_per_second": 4091.074,
86
+ "eval_steps_per_second": 32.034,
87
+ "step": 12000
88
+ },
89
+ {
90
+ "epoch": 5.83,
91
+ "eval_accuracy": 0.6944148175125517,
92
+ "eval_f1": 0.6810035650876347,
93
+ "eval_loss": 0.5960980653762817,
94
+ "eval_matthews_correlation": 0.3620477057961027,
95
+ "eval_precision": 0.6806150772404629,
96
+ "eval_recall": 0.6814335537139422,
97
+ "eval_runtime": 9.3999,
98
+ "eval_samples_per_second": 4089.503,
99
+ "eval_steps_per_second": 32.022,
100
+ "step": 14000
101
+ },
102
+ {
103
+ "epoch": 6.66,
104
+ "eval_accuracy": 0.6955854426263625,
105
+ "eval_f1": 0.680756229628503,
106
+ "eval_loss": 0.6167765259742737,
107
+ "eval_matthews_correlation": 0.36155211034902845,
108
+ "eval_precision": 0.681201736918476,
109
+ "eval_recall": 0.6803513734482689,
110
+ "eval_runtime": 9.4009,
111
+ "eval_samples_per_second": 4089.094,
112
+ "eval_steps_per_second": 32.018,
113
+ "step": 16000
114
+ },
115
+ {
116
+ "epoch": 7.49,
117
+ "eval_accuracy": 0.6977185817226399,
118
+ "eval_f1": 0.6774914738536546,
119
+ "eval_loss": 0.634030282497406,
120
+ "eval_matthews_correlation": 0.35739553112751943,
121
+ "eval_precision": 0.6825770328006973,
122
+ "eval_recall": 0.6749009222443584,
123
+ "eval_runtime": 9.4151,
124
+ "eval_samples_per_second": 4082.895,
125
+ "eval_steps_per_second": 31.97,
126
+ "step": 18000
127
+ }
128
+ ],
129
+ "logging_steps": 100000,
130
+ "max_steps": 19224,
131
+ "num_train_epochs": 8,
132
+ "save_steps": 2000,
133
+ "total_flos": 1.7283508248091034e+17,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
Finetune-species/super_binary_out/EXC/base_3072/1e-5/checkpoint-18000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052f5e59f37198a420891d569948a9d14d826d9b2581f670b828968c10bba7ae
3
+ size 5265
Finetune-species/super_binary_out/EXC/base_3072/1e-5/results/hg38_base_3072_binary_EXC_1e-5_seed42/eval_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 0.6359288096427917, "eval_accuracy": 0.6668661065008714, "eval_f1": 0.6475056317418, "eval_matthews_correlation": 0.29624960241945913, "eval_precision": 0.6503217497169653, "eval_recall": 0.6459599610484419, "eval_runtime": 9.3751, "eval_samples_per_second": 4100.336, "eval_steps_per_second": 32.106, "epoch": 8.0}
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354cbb0aa453071a8134929bd1e5e21515f1d9374e28f3cd87f3b73e6b40613c
3
+ size 356777880
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33aedc0cddb9950f5047669762142ba7e18008dee9e0ad4f992c371636c53bf9
3
+ size 713677451
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906e75159cd904da0a85f2ee57b89395c96e5b39ba041f4773cd508ea6c22093
3
+ size 14709
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ba381e07add5e135217829284fed29b78d6b593ab562e0cb3993675f5b72f6e
3
+ size 1465
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/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
+ }
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 200,
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
+ }
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/trainer_state.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.826050769870995,
5
+ "eval_steps": 2000,
6
+ "global_step": 14000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.83,
13
+ "eval_accuracy": 0.6652272313415364,
14
+ "eval_f1": 0.63496632905615,
15
+ "eval_loss": 0.6065113544464111,
16
+ "eval_matthews_correlation": 0.2786614979481554,
17
+ "eval_precision": 0.6463405361021529,
18
+ "eval_recall": 0.6326567342634729,
19
+ "eval_runtime": 9.4594,
20
+ "eval_samples_per_second": 4063.77,
21
+ "eval_steps_per_second": 31.82,
22
+ "step": 2000
23
+ },
24
+ {
25
+ "epoch": 1.66,
26
+ "eval_accuracy": 0.6794308160557738,
27
+ "eval_f1": 0.6420934477956566,
28
+ "eval_loss": 0.5921186208724976,
29
+ "eval_matthews_correlation": 0.3036815232440659,
30
+ "eval_precision": 0.6649173539308555,
31
+ "eval_recall": 0.6398010357334832,
32
+ "eval_runtime": 9.4451,
33
+ "eval_samples_per_second": 4069.956,
34
+ "eval_steps_per_second": 31.868,
35
+ "step": 4000
36
+ },
37
+ {
38
+ "epoch": 2.5,
39
+ "eval_accuracy": 0.6931141229416509,
40
+ "eval_f1": 0.666994245444585,
41
+ "eval_loss": 0.5809217691421509,
42
+ "eval_matthews_correlation": 0.34137692115355334,
43
+ "eval_precision": 0.6781242067939044,
44
+ "eval_recall": 0.6635631175485288,
45
+ "eval_runtime": 9.4478,
46
+ "eval_samples_per_second": 4068.763,
47
+ "eval_steps_per_second": 31.859,
48
+ "step": 6000
49
+ },
50
+ {
51
+ "epoch": 3.33,
52
+ "eval_accuracy": 0.6932181785073229,
53
+ "eval_f1": 0.6700710423261076,
54
+ "eval_loss": 0.5803326964378357,
55
+ "eval_matthews_correlation": 0.3446123261503502,
56
+ "eval_precision": 0.6777648328408507,
57
+ "eval_recall": 0.6670151140651603,
58
+ "eval_runtime": 9.4447,
59
+ "eval_samples_per_second": 4070.112,
60
+ "eval_steps_per_second": 31.87,
61
+ "step": 8000
62
+ },
63
+ {
64
+ "epoch": 4.16,
65
+ "eval_accuracy": 0.6915532894565698,
66
+ "eval_f1": 0.6759080942934329,
67
+ "eval_loss": 0.5845178365707397,
68
+ "eval_matthews_correlation": 0.35194477451380307,
69
+ "eval_precision": 0.6767371318847131,
70
+ "eval_recall": 0.675210951692327,
71
+ "eval_runtime": 9.4473,
72
+ "eval_samples_per_second": 4068.988,
73
+ "eval_steps_per_second": 31.861,
74
+ "step": 10000
75
+ },
76
+ {
77
+ "epoch": 4.99,
78
+ "eval_accuracy": 0.6906948310397752,
79
+ "eval_f1": 0.6782402070388853,
80
+ "eval_loss": 0.5920831561088562,
81
+ "eval_matthews_correlation": 0.3567461786272344,
82
+ "eval_precision": 0.6773841712981156,
83
+ "eval_recall": 0.6793675205540826,
84
+ "eval_runtime": 9.4422,
85
+ "eval_samples_per_second": 4071.181,
86
+ "eval_steps_per_second": 31.878,
87
+ "step": 12000
88
+ },
89
+ {
90
+ "epoch": 5.83,
91
+ "eval_accuracy": 0.6886397336177519,
92
+ "eval_f1": 0.6761540328482354,
93
+ "eval_loss": 0.6101893186569214,
94
+ "eval_matthews_correlation": 0.35258834305918024,
95
+ "eval_precision": 0.6752909097685162,
96
+ "eval_recall": 0.677303175369147,
97
+ "eval_runtime": 9.4463,
98
+ "eval_samples_per_second": 4069.416,
99
+ "eval_steps_per_second": 31.864,
100
+ "step": 14000
101
+ }
102
+ ],
103
+ "logging_steps": 100000,
104
+ "max_steps": 19224,
105
+ "num_train_epochs": 8,
106
+ "save_steps": 2000,
107
+ "total_flos": 1.2798389006001766e+17,
108
+ "trial_name": null,
109
+ "trial_params": null
110
+ }
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-14000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c0f47123da1e6329ce09a33bc845c31342974724ed60e7a039b9c3e23f06ca
3
+ size 5265
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c3c83d63979f60d9e0f6bef8fb1097f2f9442b37c29baee12bfeb3d319b1277
3
+ size 356777880
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:813e90b3b2376eedec609395007e97d0a1d8bd94f1244bb44b5c62538c9f7363
3
+ size 713677451
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab1c8051f0fd2553331d9d1dda81d5d8cf80e2b065856fb54eb14712ec8b7ed9
3
+ size 14709
Finetune-species/super_binary_out/EXC/base_4096/1e-5/checkpoint-16000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d774cc3903e6e634a16cac4822b85fc10b42d3153cc63ac882e6de1030740d
3
+ size 1465