Hugging Face's logo

nancyH
/
gue_save

Model card Files
xet
 Community
nancyH commited on
Commit
f2c46e8
·
verified ·
1 Parent(s): 191415b

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. GUE_3e-5_log_full_base_3072.txt +0 -0
  2. GUE_3e-5_log_full_base_4096.txt +0 -0
  3. GUE_3e-5_log_full_len2_2048.txt +0 -0
  4. GUE_3e-5_log_full_len2_3072.txt +0 -0
  5. GUE_3e-5_log_full_len2_4096.txt +0 -0
  6. output_multi/EMP/H3/base_3072/checkpoint-200/config.json +27 -0
  7. output_multi/EMP/H3/base_3072/checkpoint-200/model.safetensors +3 -0
  8. output_multi/EMP/H3/base_3072/checkpoint-200/optimizer.pt +3 -0
  9. output_multi/EMP/H3/base_3072/checkpoint-200/rng_state.pth +3 -0
  10. output_multi/EMP/H3/base_3072/checkpoint-200/scheduler.pt +3 -0
  11. output_multi/EMP/H3/base_3072/checkpoint-200/special_tokens_map.json +7 -0
  12. output_multi/EMP/H3/base_3072/checkpoint-200/tokenizer.json +0 -0
  13. output_multi/EMP/H3/base_3072/checkpoint-200/tokenizer_config.json +56 -0
  14. output_multi/EMP/H3/base_3072/checkpoint-200/trainer_state.json +32 -0
  15. output_multi/EMP/H3/base_3072/checkpoint-200/training_args.bin +3 -0
  16. output_multi/EMP/H3/base_3072/checkpoint-400/config.json +27 -0
  17. output_multi/EMP/H3/base_3072/checkpoint-400/model.safetensors +3 -0
  18. output_multi/EMP/H3/base_3072/checkpoint-400/optimizer.pt +3 -0
  19. output_multi/EMP/H3/base_3072/checkpoint-400/rng_state.pth +3 -0
  20. output_multi/EMP/H3/base_3072/checkpoint-400/scheduler.pt +3 -0
  21. output_multi/EMP/H3/base_3072/checkpoint-400/special_tokens_map.json +7 -0
  22. output_multi/EMP/H3/base_3072/checkpoint-400/tokenizer.json +0 -0
  23. output_multi/EMP/H3/base_3072/checkpoint-400/tokenizer_config.json +56 -0
  24. output_multi/EMP/H3/base_3072/checkpoint-400/trainer_state.json +45 -0
  25. output_multi/EMP/H3/base_3072/checkpoint-400/training_args.bin +3 -0
  26. output_multi/EMP/H3/base_3072/results/base_3072_hg38_BPE_3e-5_EMP_H3_seed42/eval_results.json +1 -0
  27. output_multi/EMP/H3/base_4096/checkpoint-200/config.json +27 -0
  28. output_multi/EMP/H3/base_4096/checkpoint-200/model.safetensors +3 -0
  29. output_multi/EMP/H3/base_4096/checkpoint-200/optimizer.pt +3 -0
  30. output_multi/EMP/H3/base_4096/checkpoint-200/rng_state.pth +3 -0
  31. output_multi/EMP/H3/base_4096/checkpoint-200/scheduler.pt +3 -0
  32. output_multi/EMP/H3/base_4096/checkpoint-200/special_tokens_map.json +7 -0
  33. output_multi/EMP/H3/base_4096/checkpoint-200/tokenizer.json +0 -0
  34. output_multi/EMP/H3/base_4096/checkpoint-200/tokenizer_config.json +56 -0
  35. output_multi/EMP/H3/base_4096/checkpoint-200/trainer_state.json +32 -0
  36. output_multi/EMP/H3/base_4096/checkpoint-200/training_args.bin +3 -0
  37. output_multi/EMP/H3/base_4096/checkpoint-400/config.json +27 -0
  38. output_multi/EMP/H3/base_4096/checkpoint-400/model.safetensors +3 -0
  39. output_multi/EMP/H3/base_4096/checkpoint-400/optimizer.pt +3 -0
  40. output_multi/EMP/H3/base_4096/checkpoint-400/rng_state.pth +3 -0
  41. output_multi/EMP/H3/base_4096/checkpoint-400/scheduler.pt +3 -0
  42. output_multi/EMP/H3/base_4096/checkpoint-400/special_tokens_map.json +7 -0
  43. output_multi/EMP/H3/base_4096/checkpoint-400/tokenizer.json +0 -0
  44. output_multi/EMP/H3/base_4096/checkpoint-400/tokenizer_config.json +56 -0
  45. output_multi/EMP/H3/base_4096/checkpoint-400/trainer_state.json +45 -0
  46. output_multi/EMP/H3/base_4096/checkpoint-400/training_args.bin +3 -0
  47. output_multi/EMP/H3/base_4096/results/base_4096_hg38_BPE_3e-5_EMP_H3_seed42/eval_results.json +1 -0
  48. output_multi/EMP/H3/len2_3072/checkpoint-200/config.json +27 -0
  49. output_multi/EMP/H3/len2_3072/checkpoint-200/model.safetensors +3 -0
  50. output_multi/EMP/H3/len2_3072/checkpoint-200/optimizer.pt +3 -0
GUE_3e-5_log_full_base_3072.txt ADDED
The diff for this file is too large to render. See raw diff
 
GUE_3e-5_log_full_base_4096.txt ADDED
The diff for this file is too large to render. See raw diff
 
GUE_3e-5_log_full_len2_2048.txt ADDED
The diff for this file is too large to render. See raw diff
 
GUE_3e-5_log_full_len2_3072.txt ADDED
The diff for this file is too large to render. See raw diff
 
GUE_3e-5_log_full_len2_4096.txt ADDED
The diff for this file is too large to render. See raw diff
 
output_multi/EMP/H3/base_3072/checkpoint-200/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
+ }
output_multi/EMP/H3/base_3072/checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131519c1a78737bdfce19a519b9e4677c2a60abf47dfbd2d3e1b606ea951cd4c
3
+ size 353632152
output_multi/EMP/H3/base_3072/checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d72fbb5265bd16a64c68f13e3bfb4f419f77872068692a4eefa0ec2347ae689
3
+ size 707385995
output_multi/EMP/H3/base_3072/checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108f1c53397aeac6618df00830a7f650ba5d880f2c986108dd28a9e9e52eef8e
3
+ size 14709
output_multi/EMP/H3/base_3072/checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1fd59e437a46fb5ba8b507e34cfa4f9660b7d7591e33f2faecdd140e127d7a9
3
+ size 1465
output_multi/EMP/H3/base_3072/checkpoint-200/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
+ }
output_multi/EMP/H3/base_3072/checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
output_multi/EMP/H3/base_3072/checkpoint-200/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": 128,
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
+ }
output_multi/EMP/H3/base_3072/checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.127659574468085,
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": 2.13,
13
+ "eval_accuracy": 0.8169672678690715,
14
+ "eval_f1": 0.81606235739808,
15
+ "eval_loss": 0.5055595636367798,
16
+ "eval_matthews_correlation": 0.6450283879859585,
17
+ "eval_precision": 0.826580436096007,
18
+ "eval_recall": 0.818498580534576,
19
+ "eval_runtime": 0.8245,
20
+ "eval_samples_per_second": 1815.756,
21
+ "eval_steps_per_second": 14.555,
22
+ "step": 200
23
+ }
24
+ ],
25
+ "logging_steps": 100000,
26
+ "max_steps": 470,
27
+ "num_train_epochs": 5,
28
+ "save_steps": 200,
29
+ "total_flos": 1584235865440256.0,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
output_multi/EMP/H3/base_3072/checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a9099ea18019c2b5927c6b5f7219d73e8ed1425615883086ac732dda7919dc
3
+ size 5201
output_multi/EMP/H3/base_3072/checkpoint-400/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
+ }
output_multi/EMP/H3/base_3072/checkpoint-400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7ab287c07197eed8266df8caf9026d5fa112c13256ff1a03f32baa0a2b27e2
3
+ size 353632152
output_multi/EMP/H3/base_3072/checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f8d6558167e01f585ebc3e36fefb699efc03844bdd0495c52e5ede4b2fedfb
3
+ size 707385995
output_multi/EMP/H3/base_3072/checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2a241f7a65eb0aa249264403bd9ab3e7024c7d10e0e0dcee71e0b377500331
3
+ size 14709
output_multi/EMP/H3/base_3072/checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c78ae650be845a5102342ce930207718c10579fa2d4dab72fe5e4a63c4d9eb
3
+ size 1465
output_multi/EMP/H3/base_3072/checkpoint-400/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
+ }
output_multi/EMP/H3/base_3072/checkpoint-400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
output_multi/EMP/H3/base_3072/checkpoint-400/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": 128,
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
+ }
output_multi/EMP/H3/base_3072/checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.25531914893617,
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": 2.13,
13
+ "eval_accuracy": 0.8169672678690715,
14
+ "eval_f1": 0.81606235739808,
15
+ "eval_loss": 0.5055595636367798,
16
+ "eval_matthews_correlation": 0.6450283879859585,
17
+ "eval_precision": 0.826580436096007,
18
+ "eval_recall": 0.818498580534576,
19
+ "eval_runtime": 0.8245,
20
+ "eval_samples_per_second": 1815.756,
21
+ "eval_steps_per_second": 14.555,
22
+ "step": 200
23
+ },
24
+ {
25
+ "epoch": 4.26,
26
+ "eval_accuracy": 0.843687374749499,
27
+ "eval_f1": 0.843687304998465,
28
+ "eval_loss": 0.438511461019516,
29
+ "eval_matthews_correlation": 0.6879651322731688,
30
+ "eval_precision": 0.8439911649483431,
31
+ "eval_recall": 0.8439739675397718,
32
+ "eval_runtime": 0.8183,
33
+ "eval_samples_per_second": 1829.417,
34
+ "eval_steps_per_second": 14.665,
35
+ "step": 400
36
+ }
37
+ ],
38
+ "logging_steps": 100000,
39
+ "max_steps": 470,
40
+ "num_train_epochs": 5,
41
+ "save_steps": 200,
42
+ "total_flos": 3168471730880512.0,
43
+ "trial_name": null,
44
+ "trial_params": null
45
+ }
output_multi/EMP/H3/base_3072/checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a9099ea18019c2b5927c6b5f7219d73e8ed1425615883086ac732dda7919dc
3
+ size 5201
output_multi/EMP/H3/base_3072/results/base_3072_hg38_BPE_3e-5_EMP_H3_seed42/eval_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 0.42567524313926697, "eval_accuracy": 0.8537074148296593, "eval_f1": 0.8536812982541799, "eval_matthews_correlation": 0.7081929500498014, "eval_precision": 0.8543052452863908, "eval_recall": 0.8538878277788686, "eval_runtime": 0.8195, "eval_samples_per_second": 1826.652, "eval_steps_per_second": 14.643, "epoch": 5.0}
output_multi/EMP/H3/base_4096/checkpoint-200/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
+ }
output_multi/EMP/H3/base_4096/checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072a3bba37dfd48fae718a8aca14bff87aa418db521ca2e4f624879e24ef5b4d
3
+ size 356777880
output_multi/EMP/H3/base_4096/checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0a8e664f1f15629b20d4bc6be2ed34bbc2d39c75956a7ccad3cb9012fa4d2c
3
+ size 713677451
output_multi/EMP/H3/base_4096/checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff0aeb04b1fb1b0c2c61127bfa2ffd9d0d95a1bf2eb3a3f7dee3d1075b32522
3
+ size 14709
output_multi/EMP/H3/base_4096/checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1fd59e437a46fb5ba8b507e34cfa4f9660b7d7591e33f2faecdd140e127d7a9
3
+ size 1465
output_multi/EMP/H3/base_4096/checkpoint-200/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
+ }
output_multi/EMP/H3/base_4096/checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
output_multi/EMP/H3/base_4096/checkpoint-200/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": 128,
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
+ }
output_multi/EMP/H3/base_4096/checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.127659574468085,
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": 2.13,
13
+ "eval_accuracy": 0.8410153640614563,
14
+ "eval_f1": 0.8406962602614776,
15
+ "eval_loss": 0.4335564374923706,
16
+ "eval_matthews_correlation": 0.6880726813201785,
17
+ "eval_precision": 0.8459871571693767,
18
+ "eval_recall": 0.8420965236488296,
19
+ "eval_runtime": 0.8011,
20
+ "eval_samples_per_second": 1868.746,
21
+ "eval_steps_per_second": 14.98,
22
+ "step": 200
23
+ }
24
+ ],
25
+ "logging_steps": 100000,
26
+ "max_steps": 470,
27
+ "num_train_epochs": 5,
28
+ "save_steps": 200,
29
+ "total_flos": 1518771571261440.0,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
output_multi/EMP/H3/base_4096/checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc872827756ded67d16562e4a4c47de970645a52c571c1cc4d3367bfba451ff
3
+ size 5201
output_multi/EMP/H3/base_4096/checkpoint-400/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
+ }
output_multi/EMP/H3/base_4096/checkpoint-400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e9b88b1c9163e439079ad5f66c352d61152af2b0b84a9b4a048625fa1943fd
3
+ size 356777880
output_multi/EMP/H3/base_4096/checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca94dcb2613555ae5e5016071031b4aecd1b2b748a9704da2e823a014a0c04a
3
+ size 713677451
output_multi/EMP/H3/base_4096/checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36fe15c7ffc033f17cbc9ea949b3bfd1623784c55150d1dff0beaec54f51c83
3
+ size 14709
output_multi/EMP/H3/base_4096/checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c78ae650be845a5102342ce930207718c10579fa2d4dab72fe5e4a63c4d9eb
3
+ size 1465
output_multi/EMP/H3/base_4096/checkpoint-400/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
+ }
output_multi/EMP/H3/base_4096/checkpoint-400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
output_multi/EMP/H3/base_4096/checkpoint-400/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": 128,
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
+ }
output_multi/EMP/H3/base_4096/checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.25531914893617,
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": 2.13,
13
+ "eval_accuracy": 0.8410153640614563,
14
+ "eval_f1": 0.8406962602614776,
15
+ "eval_loss": 0.4335564374923706,
16
+ "eval_matthews_correlation": 0.6880726813201785,
17
+ "eval_precision": 0.8459871571693767,
18
+ "eval_recall": 0.8420965236488296,
19
+ "eval_runtime": 0.8011,
20
+ "eval_samples_per_second": 1868.746,
21
+ "eval_steps_per_second": 14.98,
22
+ "step": 200
23
+ },
24
+ {
25
+ "epoch": 4.26,
26
+ "eval_accuracy": 0.8550434201736807,
27
+ "eval_f1": 0.8550341051335087,
28
+ "eval_loss": 0.4523474872112274,
29
+ "eval_matthews_correlation": 0.7112297794027241,
30
+ "eval_precision": 0.8557635605305198,
31
+ "eval_recall": 0.8554662810005892,
32
+ "eval_runtime": 0.7951,
33
+ "eval_samples_per_second": 1882.782,
34
+ "eval_steps_per_second": 15.092,
35
+ "step": 400
36
+ }
37
+ ],
38
+ "logging_steps": 100000,
39
+ "max_steps": 470,
40
+ "num_train_epochs": 5,
41
+ "save_steps": 200,
42
+ "total_flos": 3037543142522880.0,
43
+ "trial_name": null,
44
+ "trial_params": null
45
+ }
output_multi/EMP/H3/base_4096/checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc872827756ded67d16562e4a4c47de970645a52c571c1cc4d3367bfba451ff
3
+ size 5201
output_multi/EMP/H3/base_4096/results/base_4096_hg38_BPE_3e-5_EMP_H3_seed42/eval_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 0.3891415596008301, "eval_accuracy": 0.8577154308617234, "eval_f1": 0.8576991752326115, "eval_matthews_correlation": 0.7154052410588636, "eval_precision": 0.8577179458799419, "eval_recall": 0.8576872958354902, "eval_runtime": 0.7968, "eval_samples_per_second": 1878.651, "eval_steps_per_second": 15.059, "epoch": 5.0}
output_multi/EMP/H3/len2_3072/checkpoint-200/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/len2_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
+ }
output_multi/EMP/H3/len2_3072/checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16183ce2b7caedd70bad10c9b6af021690abdb4d96541c697545fe48096e8c37
3
+ size 353632152
output_multi/EMP/H3/len2_3072/checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00549e15ff4c4802b11f15ff29593e1da649c7a8a852a20977d0f59873be169
3
+ size 707385995