Medyassino commited on
Commit
78989a6
·
verified ·
1 Parent(s): 7b7bf42

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. checkpoint-10/config.json +88 -0
  2. checkpoint-10/model.safetensors +3 -0
  3. checkpoint-10/optimizer.pt +3 -0
  4. checkpoint-10/rng_state.pth +3 -0
  5. checkpoint-10/scheduler.pt +3 -0
  6. checkpoint-10/tokenizer.json +0 -0
  7. checkpoint-10/tokenizer_config.json +21 -0
  8. checkpoint-10/trainer_state.json +84 -0
  9. checkpoint-10/training_args.bin +3 -0
  10. checkpoint-12/config.json +88 -0
  11. checkpoint-12/model.safetensors +3 -0
  12. checkpoint-12/optimizer.pt +3 -0
  13. checkpoint-12/rng_state.pth +3 -0
  14. checkpoint-12/scheduler.pt +3 -0
  15. checkpoint-12/tokenizer.json +0 -0
  16. checkpoint-12/tokenizer_config.json +21 -0
  17. checkpoint-12/trainer_state.json +94 -0
  18. checkpoint-12/training_args.bin +3 -0
  19. checkpoint-14/config.json +88 -0
  20. checkpoint-14/model.safetensors +3 -0
  21. checkpoint-14/optimizer.pt +3 -0
  22. checkpoint-14/rng_state.pth +3 -0
  23. checkpoint-14/scheduler.pt +3 -0
  24. checkpoint-14/tokenizer.json +0 -0
  25. checkpoint-14/tokenizer_config.json +21 -0
  26. checkpoint-14/trainer_state.json +104 -0
  27. checkpoint-14/training_args.bin +3 -0
  28. checkpoint-16/config.json +88 -0
  29. checkpoint-16/model.safetensors +3 -0
  30. checkpoint-16/optimizer.pt +3 -0
  31. checkpoint-16/rng_state.pth +3 -0
  32. checkpoint-16/scheduler.pt +3 -0
  33. checkpoint-16/tokenizer.json +0 -0
  34. checkpoint-16/tokenizer_config.json +21 -0
  35. checkpoint-16/trainer_state.json +114 -0
  36. checkpoint-16/training_args.bin +3 -0
  37. checkpoint-18/config.json +88 -0
  38. checkpoint-18/model.safetensors +3 -0
  39. checkpoint-18/optimizer.pt +3 -0
  40. checkpoint-18/rng_state.pth +3 -0
  41. checkpoint-18/scheduler.pt +3 -0
  42. checkpoint-18/tokenizer.json +0 -0
  43. checkpoint-18/tokenizer_config.json +21 -0
  44. checkpoint-18/trainer_state.json +124 -0
  45. checkpoint-18/training_args.bin +3 -0
  46. checkpoint-2/config.json +88 -0
  47. checkpoint-2/model.safetensors +3 -0
  48. checkpoint-2/optimizer.pt +3 -0
  49. checkpoint-2/rng_state.pth +3 -0
  50. checkpoint-2/scheduler.pt +3 -0
checkpoint-10/config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "Different",
24
+ "1": "Equivalent"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "Different": 0,
31
+ "Equivalent": 1
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "layer_types": [
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention"
57
+ ],
58
+ "local_attention": 128,
59
+ "max_position_embeddings": 8192,
60
+ "mlp_bias": false,
61
+ "mlp_dropout": 0.0,
62
+ "model_type": "modernbert",
63
+ "norm_bias": false,
64
+ "norm_eps": 1e-05,
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 22,
67
+ "pad_token_id": 50283,
68
+ "position_embedding_type": "absolute",
69
+ "problem_type": "single_label_classification",
70
+ "repad_logits_with_grad": false,
71
+ "rope_parameters": {
72
+ "full_attention": {
73
+ "rope_theta": 160000.0,
74
+ "rope_type": "default"
75
+ },
76
+ "sliding_attention": {
77
+ "rope_theta": 10000.0,
78
+ "rope_type": "default"
79
+ }
80
+ },
81
+ "sep_token_id": 50282,
82
+ "sparse_pred_ignore_index": -100,
83
+ "sparse_prediction": false,
84
+ "tie_word_embeddings": true,
85
+ "transformers_version": "5.20.2",
86
+ "use_cache": false,
87
+ "vocab_size": 50368
88
+ }
checkpoint-10/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:099fa3ec67dbede10b580c39ff01101150387d3200dc6b6006afd82b43e0f8ae
3
+ size 598439784
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e82baa9ead0c2e6cb30948ca2d8a4c0a80a0f825d54add5a0daadd3f210caa3e
3
+ size 1196969803
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17cd930da9783ca70bad4b9cdeee6a06c0acea8f34645a333c93341f487f66a3
3
+ size 14645
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d310dc7744488422d2e08282f176a0d7bd1c485c1f31624b33358a92664bf0
3
+ size 1465
checkpoint-10/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "max_length": 512,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 8192,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "stride": 0,
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "truncation_side": "right",
19
+ "truncation_strategy": "longest_first",
20
+ "unk_token": "[UNK]"
21
+ }
checkpoint-10/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 4,
3
+ "best_metric": 0.8246153846153846,
4
+ "best_model_checkpoint": "/content/devSECV3_20261023_141400/model/checkpoint-4",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 10,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.7368421052631579,
15
+ "eval_f1_macro": 0.7076923076923077,
16
+ "eval_loss": 0.5971037745475769,
17
+ "eval_runtime": 0.0371,
18
+ "eval_samples_per_second": 512.435,
19
+ "eval_steps_per_second": 26.97,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8421052631578947,
25
+ "eval_f1_macro": 0.8246153846153846,
26
+ "eval_loss": 0.5457956194877625,
27
+ "eval_runtime": 0.0395,
28
+ "eval_samples_per_second": 481.004,
29
+ "eval_steps_per_second": 25.316,
30
+ "step": 4
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_accuracy": 0.8421052631578947,
35
+ "eval_f1_macro": 0.8080808080808081,
36
+ "eval_loss": 0.447509765625,
37
+ "eval_runtime": 0.0392,
38
+ "eval_samples_per_second": 484.911,
39
+ "eval_steps_per_second": 25.522,
40
+ "step": 6
41
+ },
42
+ {
43
+ "epoch": 4.0,
44
+ "eval_accuracy": 0.7894736842105263,
45
+ "eval_f1_macro": 0.7564102564102564,
46
+ "eval_loss": 0.44001850485801697,
47
+ "eval_runtime": 0.0385,
48
+ "eval_samples_per_second": 493.139,
49
+ "eval_steps_per_second": 25.955,
50
+ "step": 8
51
+ },
52
+ {
53
+ "epoch": 5.0,
54
+ "eval_accuracy": 0.7894736842105263,
55
+ "eval_f1_macro": 0.7564102564102564,
56
+ "eval_loss": 0.4917088449001312,
57
+ "eval_runtime": 0.0393,
58
+ "eval_samples_per_second": 483.396,
59
+ "eval_steps_per_second": 25.442,
60
+ "step": 10
61
+ }
62
+ ],
63
+ "logging_steps": 500,
64
+ "max_steps": 20,
65
+ "num_input_tokens_seen": 0,
66
+ "num_train_epochs": 10,
67
+ "save_steps": 500,
68
+ "stateful_callbacks": {
69
+ "TrainerControl": {
70
+ "args": {
71
+ "should_epoch_stop": false,
72
+ "should_evaluate": false,
73
+ "should_log": false,
74
+ "should_save": true,
75
+ "should_training_stop": false
76
+ },
77
+ "attributes": {}
78
+ }
79
+ },
80
+ "total_flos": 6076404558840.0,
81
+ "train_batch_size": 16,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ed1dcf2ef105ac35e5978389c323ec0918c689be19ffd12cde3133039293bb
3
+ size 5265
checkpoint-12/config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "Different",
24
+ "1": "Equivalent"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "Different": 0,
31
+ "Equivalent": 1
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "layer_types": [
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention"
57
+ ],
58
+ "local_attention": 128,
59
+ "max_position_embeddings": 8192,
60
+ "mlp_bias": false,
61
+ "mlp_dropout": 0.0,
62
+ "model_type": "modernbert",
63
+ "norm_bias": false,
64
+ "norm_eps": 1e-05,
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 22,
67
+ "pad_token_id": 50283,
68
+ "position_embedding_type": "absolute",
69
+ "problem_type": "single_label_classification",
70
+ "repad_logits_with_grad": false,
71
+ "rope_parameters": {
72
+ "full_attention": {
73
+ "rope_theta": 160000.0,
74
+ "rope_type": "default"
75
+ },
76
+ "sliding_attention": {
77
+ "rope_theta": 10000.0,
78
+ "rope_type": "default"
79
+ }
80
+ },
81
+ "sep_token_id": 50282,
82
+ "sparse_pred_ignore_index": -100,
83
+ "sparse_prediction": false,
84
+ "tie_word_embeddings": true,
85
+ "transformers_version": "5.20.2",
86
+ "use_cache": false,
87
+ "vocab_size": 50368
88
+ }
checkpoint-12/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73286e84824888845a3cc6e4c89f48afadcae35cccee0448537f8df33c081a70
3
+ size 598439784
checkpoint-12/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5349baedc94f04e174836f86e1c1f9ad8738897718487eca263f865fdcf3cbcb
3
+ size 1196969803
checkpoint-12/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1255b82ec9f462fef6f8c2f4a8ee876c4b6d998a53c99546a4eddcc1aabaefc7
3
+ size 14645
checkpoint-12/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8481f9cf5a7a90e6d26f50e7738493bf9fa7fb46812c2aba377e2627cc00c6
3
+ size 1465
checkpoint-12/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "max_length": 512,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 8192,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "stride": 0,
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "truncation_side": "right",
19
+ "truncation_strategy": "longest_first",
20
+ "unk_token": "[UNK]"
21
+ }
checkpoint-12/trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 4,
3
+ "best_metric": 0.8246153846153846,
4
+ "best_model_checkpoint": "/content/devSECV3_20261023_141400/model/checkpoint-4",
5
+ "epoch": 6.0,
6
+ "eval_steps": 500,
7
+ "global_step": 12,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.7368421052631579,
15
+ "eval_f1_macro": 0.7076923076923077,
16
+ "eval_loss": 0.5971037745475769,
17
+ "eval_runtime": 0.0371,
18
+ "eval_samples_per_second": 512.435,
19
+ "eval_steps_per_second": 26.97,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8421052631578947,
25
+ "eval_f1_macro": 0.8246153846153846,
26
+ "eval_loss": 0.5457956194877625,
27
+ "eval_runtime": 0.0395,
28
+ "eval_samples_per_second": 481.004,
29
+ "eval_steps_per_second": 25.316,
30
+ "step": 4
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_accuracy": 0.8421052631578947,
35
+ "eval_f1_macro": 0.8080808080808081,
36
+ "eval_loss": 0.447509765625,
37
+ "eval_runtime": 0.0392,
38
+ "eval_samples_per_second": 484.911,
39
+ "eval_steps_per_second": 25.522,
40
+ "step": 6
41
+ },
42
+ {
43
+ "epoch": 4.0,
44
+ "eval_accuracy": 0.7894736842105263,
45
+ "eval_f1_macro": 0.7564102564102564,
46
+ "eval_loss": 0.44001850485801697,
47
+ "eval_runtime": 0.0385,
48
+ "eval_samples_per_second": 493.139,
49
+ "eval_steps_per_second": 25.955,
50
+ "step": 8
51
+ },
52
+ {
53
+ "epoch": 5.0,
54
+ "eval_accuracy": 0.7894736842105263,
55
+ "eval_f1_macro": 0.7564102564102564,
56
+ "eval_loss": 0.4917088449001312,
57
+ "eval_runtime": 0.0393,
58
+ "eval_samples_per_second": 483.396,
59
+ "eval_steps_per_second": 25.442,
60
+ "step": 10
61
+ },
62
+ {
63
+ "epoch": 6.0,
64
+ "eval_accuracy": 0.7368421052631579,
65
+ "eval_f1_macro": 0.6801346801346801,
66
+ "eval_loss": 0.5435437560081482,
67
+ "eval_runtime": 0.0379,
68
+ "eval_samples_per_second": 501.449,
69
+ "eval_steps_per_second": 26.392,
70
+ "step": 12
71
+ }
72
+ ],
73
+ "logging_steps": 500,
74
+ "max_steps": 20,
75
+ "num_input_tokens_seen": 0,
76
+ "num_train_epochs": 10,
77
+ "save_steps": 500,
78
+ "stateful_callbacks": {
79
+ "TrainerControl": {
80
+ "args": {
81
+ "should_epoch_stop": false,
82
+ "should_evaluate": false,
83
+ "should_log": false,
84
+ "should_save": true,
85
+ "should_training_stop": false
86
+ },
87
+ "attributes": {}
88
+ }
89
+ },
90
+ "total_flos": 7321634890668.0,
91
+ "train_batch_size": 16,
92
+ "trial_name": null,
93
+ "trial_params": null
94
+ }
checkpoint-12/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ed1dcf2ef105ac35e5978389c323ec0918c689be19ffd12cde3133039293bb
3
+ size 5265
checkpoint-14/config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "Different",
24
+ "1": "Equivalent"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "Different": 0,
31
+ "Equivalent": 1
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "layer_types": [
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention"
57
+ ],
58
+ "local_attention": 128,
59
+ "max_position_embeddings": 8192,
60
+ "mlp_bias": false,
61
+ "mlp_dropout": 0.0,
62
+ "model_type": "modernbert",
63
+ "norm_bias": false,
64
+ "norm_eps": 1e-05,
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 22,
67
+ "pad_token_id": 50283,
68
+ "position_embedding_type": "absolute",
69
+ "problem_type": "single_label_classification",
70
+ "repad_logits_with_grad": false,
71
+ "rope_parameters": {
72
+ "full_attention": {
73
+ "rope_theta": 160000.0,
74
+ "rope_type": "default"
75
+ },
76
+ "sliding_attention": {
77
+ "rope_theta": 10000.0,
78
+ "rope_type": "default"
79
+ }
80
+ },
81
+ "sep_token_id": 50282,
82
+ "sparse_pred_ignore_index": -100,
83
+ "sparse_prediction": false,
84
+ "tie_word_embeddings": true,
85
+ "transformers_version": "5.20.2",
86
+ "use_cache": false,
87
+ "vocab_size": 50368
88
+ }
checkpoint-14/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e016914f702ac396614d3636d01e66c53c8840274ba62f7ec7c67287676cf
3
+ size 598439784
checkpoint-14/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14480fa023c019c4677b13305bafaa582a3ddcd3b01c1cd98db7afaa8bbfefea
3
+ size 1196969803
checkpoint-14/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ea3a198ff666cb4ace1c684b598fe43fc7c3c276b83efc553a1b787e12a304
3
+ size 14645
checkpoint-14/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c023cd6d5674e702f04e6365c1db48b89e2c415f4d4b6e30be38f327e5c062c3
3
+ size 1465
checkpoint-14/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "max_length": 512,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 8192,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "stride": 0,
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "truncation_side": "right",
19
+ "truncation_strategy": "longest_first",
20
+ "unk_token": "[UNK]"
21
+ }
checkpoint-14/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 4,
3
+ "best_metric": 0.8246153846153846,
4
+ "best_model_checkpoint": "/content/devSECV3_20261023_141400/model/checkpoint-4",
5
+ "epoch": 7.0,
6
+ "eval_steps": 500,
7
+ "global_step": 14,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.7368421052631579,
15
+ "eval_f1_macro": 0.7076923076923077,
16
+ "eval_loss": 0.5971037745475769,
17
+ "eval_runtime": 0.0371,
18
+ "eval_samples_per_second": 512.435,
19
+ "eval_steps_per_second": 26.97,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8421052631578947,
25
+ "eval_f1_macro": 0.8246153846153846,
26
+ "eval_loss": 0.5457956194877625,
27
+ "eval_runtime": 0.0395,
28
+ "eval_samples_per_second": 481.004,
29
+ "eval_steps_per_second": 25.316,
30
+ "step": 4
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_accuracy": 0.8421052631578947,
35
+ "eval_f1_macro": 0.8080808080808081,
36
+ "eval_loss": 0.447509765625,
37
+ "eval_runtime": 0.0392,
38
+ "eval_samples_per_second": 484.911,
39
+ "eval_steps_per_second": 25.522,
40
+ "step": 6
41
+ },
42
+ {
43
+ "epoch": 4.0,
44
+ "eval_accuracy": 0.7894736842105263,
45
+ "eval_f1_macro": 0.7564102564102564,
46
+ "eval_loss": 0.44001850485801697,
47
+ "eval_runtime": 0.0385,
48
+ "eval_samples_per_second": 493.139,
49
+ "eval_steps_per_second": 25.955,
50
+ "step": 8
51
+ },
52
+ {
53
+ "epoch": 5.0,
54
+ "eval_accuracy": 0.7894736842105263,
55
+ "eval_f1_macro": 0.7564102564102564,
56
+ "eval_loss": 0.4917088449001312,
57
+ "eval_runtime": 0.0393,
58
+ "eval_samples_per_second": 483.396,
59
+ "eval_steps_per_second": 25.442,
60
+ "step": 10
61
+ },
62
+ {
63
+ "epoch": 6.0,
64
+ "eval_accuracy": 0.7368421052631579,
65
+ "eval_f1_macro": 0.6801346801346801,
66
+ "eval_loss": 0.5435437560081482,
67
+ "eval_runtime": 0.0379,
68
+ "eval_samples_per_second": 501.449,
69
+ "eval_steps_per_second": 26.392,
70
+ "step": 12
71
+ },
72
+ {
73
+ "epoch": 7.0,
74
+ "eval_accuracy": 0.7368421052631579,
75
+ "eval_f1_macro": 0.6801346801346801,
76
+ "eval_loss": 0.5466565489768982,
77
+ "eval_runtime": 0.0376,
78
+ "eval_samples_per_second": 505.935,
79
+ "eval_steps_per_second": 26.628,
80
+ "step": 14
81
+ }
82
+ ],
83
+ "logging_steps": 500,
84
+ "max_steps": 20,
85
+ "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 10,
87
+ "save_steps": 500,
88
+ "stateful_callbacks": {
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": false
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 8500976498364.0,
101
+ "train_batch_size": 16,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
checkpoint-14/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ed1dcf2ef105ac35e5978389c323ec0918c689be19ffd12cde3133039293bb
3
+ size 5265
checkpoint-16/config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "Different",
24
+ "1": "Equivalent"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "Different": 0,
31
+ "Equivalent": 1
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "layer_types": [
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention"
57
+ ],
58
+ "local_attention": 128,
59
+ "max_position_embeddings": 8192,
60
+ "mlp_bias": false,
61
+ "mlp_dropout": 0.0,
62
+ "model_type": "modernbert",
63
+ "norm_bias": false,
64
+ "norm_eps": 1e-05,
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 22,
67
+ "pad_token_id": 50283,
68
+ "position_embedding_type": "absolute",
69
+ "problem_type": "single_label_classification",
70
+ "repad_logits_with_grad": false,
71
+ "rope_parameters": {
72
+ "full_attention": {
73
+ "rope_theta": 160000.0,
74
+ "rope_type": "default"
75
+ },
76
+ "sliding_attention": {
77
+ "rope_theta": 10000.0,
78
+ "rope_type": "default"
79
+ }
80
+ },
81
+ "sep_token_id": 50282,
82
+ "sparse_pred_ignore_index": -100,
83
+ "sparse_prediction": false,
84
+ "tie_word_embeddings": true,
85
+ "transformers_version": "5.20.2",
86
+ "use_cache": false,
87
+ "vocab_size": 50368
88
+ }
checkpoint-16/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4180b87cb2a3eedc6079ccf2cce523b3806e7b9c9653bdbc5bad924dbbad34e
3
+ size 598439784
checkpoint-16/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3a428640c8c48d5757a77b808a8b5f95c2dc07a87e5e107e364afce4c7ff63
3
+ size 1196969803
checkpoint-16/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f621c40c37c796d75663f728f7490ddcd9db068eaa82d92691bb9a37ff256f
3
+ size 14645
checkpoint-16/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb7afd8f1e7a447cf1bd96cd081257238c7029c620b7cec4de1e9475cb8abfb
3
+ size 1465
checkpoint-16/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "max_length": 512,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 8192,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "stride": 0,
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "truncation_side": "right",
19
+ "truncation_strategy": "longest_first",
20
+ "unk_token": "[UNK]"
21
+ }
checkpoint-16/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 4,
3
+ "best_metric": 0.8246153846153846,
4
+ "best_model_checkpoint": "/content/devSECV3_20261023_141400/model/checkpoint-4",
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 16,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.7368421052631579,
15
+ "eval_f1_macro": 0.7076923076923077,
16
+ "eval_loss": 0.5971037745475769,
17
+ "eval_runtime": 0.0371,
18
+ "eval_samples_per_second": 512.435,
19
+ "eval_steps_per_second": 26.97,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8421052631578947,
25
+ "eval_f1_macro": 0.8246153846153846,
26
+ "eval_loss": 0.5457956194877625,
27
+ "eval_runtime": 0.0395,
28
+ "eval_samples_per_second": 481.004,
29
+ "eval_steps_per_second": 25.316,
30
+ "step": 4
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_accuracy": 0.8421052631578947,
35
+ "eval_f1_macro": 0.8080808080808081,
36
+ "eval_loss": 0.447509765625,
37
+ "eval_runtime": 0.0392,
38
+ "eval_samples_per_second": 484.911,
39
+ "eval_steps_per_second": 25.522,
40
+ "step": 6
41
+ },
42
+ {
43
+ "epoch": 4.0,
44
+ "eval_accuracy": 0.7894736842105263,
45
+ "eval_f1_macro": 0.7564102564102564,
46
+ "eval_loss": 0.44001850485801697,
47
+ "eval_runtime": 0.0385,
48
+ "eval_samples_per_second": 493.139,
49
+ "eval_steps_per_second": 25.955,
50
+ "step": 8
51
+ },
52
+ {
53
+ "epoch": 5.0,
54
+ "eval_accuracy": 0.7894736842105263,
55
+ "eval_f1_macro": 0.7564102564102564,
56
+ "eval_loss": 0.4917088449001312,
57
+ "eval_runtime": 0.0393,
58
+ "eval_samples_per_second": 483.396,
59
+ "eval_steps_per_second": 25.442,
60
+ "step": 10
61
+ },
62
+ {
63
+ "epoch": 6.0,
64
+ "eval_accuracy": 0.7368421052631579,
65
+ "eval_f1_macro": 0.6801346801346801,
66
+ "eval_loss": 0.5435437560081482,
67
+ "eval_runtime": 0.0379,
68
+ "eval_samples_per_second": 501.449,
69
+ "eval_steps_per_second": 26.392,
70
+ "step": 12
71
+ },
72
+ {
73
+ "epoch": 7.0,
74
+ "eval_accuracy": 0.7368421052631579,
75
+ "eval_f1_macro": 0.6801346801346801,
76
+ "eval_loss": 0.5466565489768982,
77
+ "eval_runtime": 0.0376,
78
+ "eval_samples_per_second": 505.935,
79
+ "eval_steps_per_second": 26.628,
80
+ "step": 14
81
+ },
82
+ {
83
+ "epoch": 8.0,
84
+ "eval_accuracy": 0.7368421052631579,
85
+ "eval_f1_macro": 0.6801346801346801,
86
+ "eval_loss": 0.5339547991752625,
87
+ "eval_runtime": 0.0381,
88
+ "eval_samples_per_second": 498.563,
89
+ "eval_steps_per_second": 26.24,
90
+ "step": 16
91
+ }
92
+ ],
93
+ "logging_steps": 500,
94
+ "max_steps": 20,
95
+ "num_input_tokens_seen": 0,
96
+ "num_train_epochs": 10,
97
+ "save_steps": 500,
98
+ "stateful_callbacks": {
99
+ "TrainerControl": {
100
+ "args": {
101
+ "should_epoch_stop": false,
102
+ "should_evaluate": false,
103
+ "should_log": false,
104
+ "should_save": true,
105
+ "should_training_stop": false
106
+ },
107
+ "attributes": {}
108
+ }
109
+ },
110
+ "total_flos": 9733561519500.0,
111
+ "train_batch_size": 16,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-16/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ed1dcf2ef105ac35e5978389c323ec0918c689be19ffd12cde3133039293bb
3
+ size 5265
checkpoint-18/config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "Different",
24
+ "1": "Equivalent"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "Different": 0,
31
+ "Equivalent": 1
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "layer_types": [
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention"
57
+ ],
58
+ "local_attention": 128,
59
+ "max_position_embeddings": 8192,
60
+ "mlp_bias": false,
61
+ "mlp_dropout": 0.0,
62
+ "model_type": "modernbert",
63
+ "norm_bias": false,
64
+ "norm_eps": 1e-05,
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 22,
67
+ "pad_token_id": 50283,
68
+ "position_embedding_type": "absolute",
69
+ "problem_type": "single_label_classification",
70
+ "repad_logits_with_grad": false,
71
+ "rope_parameters": {
72
+ "full_attention": {
73
+ "rope_theta": 160000.0,
74
+ "rope_type": "default"
75
+ },
76
+ "sliding_attention": {
77
+ "rope_theta": 10000.0,
78
+ "rope_type": "default"
79
+ }
80
+ },
81
+ "sep_token_id": 50282,
82
+ "sparse_pred_ignore_index": -100,
83
+ "sparse_prediction": false,
84
+ "tie_word_embeddings": true,
85
+ "transformers_version": "5.20.2",
86
+ "use_cache": false,
87
+ "vocab_size": 50368
88
+ }
checkpoint-18/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b205a1432a9e25e85588dec6816d57904a1420dc80af3c0f58da4d0dad9cc8a
3
+ size 598439784
checkpoint-18/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73dcb11efa34c32aaed1378ead986233f85d57f224867566990975a45d1e667
3
+ size 1196969803
checkpoint-18/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9445552595536daf5bd8731be4eabb308bd26e76a3f4f0c20c4aa55fcf9ea202
3
+ size 14645
checkpoint-18/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b67d17ffc6be821a0babbf9da511f6bcaac55fb0b59344986b80aee953eab3
3
+ size 1465
checkpoint-18/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-18/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "max_length": 512,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 8192,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "stride": 0,
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "truncation_side": "right",
19
+ "truncation_strategy": "longest_first",
20
+ "unk_token": "[UNK]"
21
+ }
checkpoint-18/trainer_state.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 4,
3
+ "best_metric": 0.8246153846153846,
4
+ "best_model_checkpoint": "/content/devSECV3_20261023_141400/model/checkpoint-4",
5
+ "epoch": 9.0,
6
+ "eval_steps": 500,
7
+ "global_step": 18,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.7368421052631579,
15
+ "eval_f1_macro": 0.7076923076923077,
16
+ "eval_loss": 0.5971037745475769,
17
+ "eval_runtime": 0.0371,
18
+ "eval_samples_per_second": 512.435,
19
+ "eval_steps_per_second": 26.97,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8421052631578947,
25
+ "eval_f1_macro": 0.8246153846153846,
26
+ "eval_loss": 0.5457956194877625,
27
+ "eval_runtime": 0.0395,
28
+ "eval_samples_per_second": 481.004,
29
+ "eval_steps_per_second": 25.316,
30
+ "step": 4
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_accuracy": 0.8421052631578947,
35
+ "eval_f1_macro": 0.8080808080808081,
36
+ "eval_loss": 0.447509765625,
37
+ "eval_runtime": 0.0392,
38
+ "eval_samples_per_second": 484.911,
39
+ "eval_steps_per_second": 25.522,
40
+ "step": 6
41
+ },
42
+ {
43
+ "epoch": 4.0,
44
+ "eval_accuracy": 0.7894736842105263,
45
+ "eval_f1_macro": 0.7564102564102564,
46
+ "eval_loss": 0.44001850485801697,
47
+ "eval_runtime": 0.0385,
48
+ "eval_samples_per_second": 493.139,
49
+ "eval_steps_per_second": 25.955,
50
+ "step": 8
51
+ },
52
+ {
53
+ "epoch": 5.0,
54
+ "eval_accuracy": 0.7894736842105263,
55
+ "eval_f1_macro": 0.7564102564102564,
56
+ "eval_loss": 0.4917088449001312,
57
+ "eval_runtime": 0.0393,
58
+ "eval_samples_per_second": 483.396,
59
+ "eval_steps_per_second": 25.442,
60
+ "step": 10
61
+ },
62
+ {
63
+ "epoch": 6.0,
64
+ "eval_accuracy": 0.7368421052631579,
65
+ "eval_f1_macro": 0.6801346801346801,
66
+ "eval_loss": 0.5435437560081482,
67
+ "eval_runtime": 0.0379,
68
+ "eval_samples_per_second": 501.449,
69
+ "eval_steps_per_second": 26.392,
70
+ "step": 12
71
+ },
72
+ {
73
+ "epoch": 7.0,
74
+ "eval_accuracy": 0.7368421052631579,
75
+ "eval_f1_macro": 0.6801346801346801,
76
+ "eval_loss": 0.5466565489768982,
77
+ "eval_runtime": 0.0376,
78
+ "eval_samples_per_second": 505.935,
79
+ "eval_steps_per_second": 26.628,
80
+ "step": 14
81
+ },
82
+ {
83
+ "epoch": 8.0,
84
+ "eval_accuracy": 0.7368421052631579,
85
+ "eval_f1_macro": 0.6801346801346801,
86
+ "eval_loss": 0.5339547991752625,
87
+ "eval_runtime": 0.0381,
88
+ "eval_samples_per_second": 498.563,
89
+ "eval_steps_per_second": 26.24,
90
+ "step": 16
91
+ },
92
+ {
93
+ "epoch": 9.0,
94
+ "eval_accuracy": 0.7368421052631579,
95
+ "eval_f1_macro": 0.6801346801346801,
96
+ "eval_loss": 0.5449908971786499,
97
+ "eval_runtime": 0.0375,
98
+ "eval_samples_per_second": 507.232,
99
+ "eval_steps_per_second": 26.696,
100
+ "step": 18
101
+ }
102
+ ],
103
+ "logging_steps": 500,
104
+ "max_steps": 20,
105
+ "num_input_tokens_seen": 0,
106
+ "num_train_epochs": 10,
107
+ "save_steps": 500,
108
+ "stateful_callbacks": {
109
+ "TrainerControl": {
110
+ "args": {
111
+ "should_epoch_stop": false,
112
+ "should_evaluate": false,
113
+ "should_log": false,
114
+ "should_save": true,
115
+ "should_training_stop": false
116
+ },
117
+ "attributes": {}
118
+ }
119
+ },
120
+ "total_flos": 10912903127196.0,
121
+ "train_batch_size": 16,
122
+ "trial_name": null,
123
+ "trial_params": null
124
+ }
checkpoint-18/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ed1dcf2ef105ac35e5978389c323ec0918c689be19ffd12cde3133039293bb
3
+ size 5265
checkpoint-2/config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "Different",
24
+ "1": "Equivalent"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "Different": 0,
31
+ "Equivalent": 1
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "layer_types": [
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention"
57
+ ],
58
+ "local_attention": 128,
59
+ "max_position_embeddings": 8192,
60
+ "mlp_bias": false,
61
+ "mlp_dropout": 0.0,
62
+ "model_type": "modernbert",
63
+ "norm_bias": false,
64
+ "norm_eps": 1e-05,
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 22,
67
+ "pad_token_id": 50283,
68
+ "position_embedding_type": "absolute",
69
+ "problem_type": "single_label_classification",
70
+ "repad_logits_with_grad": false,
71
+ "rope_parameters": {
72
+ "full_attention": {
73
+ "rope_theta": 160000.0,
74
+ "rope_type": "default"
75
+ },
76
+ "sliding_attention": {
77
+ "rope_theta": 10000.0,
78
+ "rope_type": "default"
79
+ }
80
+ },
81
+ "sep_token_id": 50282,
82
+ "sparse_pred_ignore_index": -100,
83
+ "sparse_prediction": false,
84
+ "tie_word_embeddings": true,
85
+ "transformers_version": "5.20.2",
86
+ "use_cache": false,
87
+ "vocab_size": 50368
88
+ }
checkpoint-2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:181ede440f0480438c836df8a95e006b5b7c50ba249b80d63493b1d67e52c64e
3
+ size 598439784
checkpoint-2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8b20d6fb891f1ffbbcf1724f1e4566b88b49d3dab5c1351b3431ce83f778320
3
+ size 1196969803
checkpoint-2/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
checkpoint-2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe30af0886dc3484e8092633d83c47d0fe2449c80a78989e4e0b6aa02d8324b
3
+ size 1465