Hanish2007 commited on
Commit
bd9e268
·
verified ·
1 Parent(s): d71c50b

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-130/config.json +101 -0
  2. checkpoint-130/model.safetensors +3 -0
  3. checkpoint-130/optimizer.pt +3 -0
  4. checkpoint-130/rng_state.pth +3 -0
  5. checkpoint-130/scheduler.pt +3 -0
  6. checkpoint-130/special_tokens_map.json +7 -0
  7. checkpoint-130/tokenizer.json +0 -0
  8. checkpoint-130/tokenizer_config.json +55 -0
  9. checkpoint-130/trainer_state.json +65 -0
  10. checkpoint-130/training_args.bin +3 -0
  11. checkpoint-130/vocab.txt +0 -0
  12. checkpoint-195/config.json +101 -0
  13. checkpoint-195/model.safetensors +3 -0
  14. checkpoint-195/optimizer.pt +3 -0
  15. checkpoint-195/rng_state.pth +3 -0
  16. checkpoint-195/scheduler.pt +3 -0
  17. checkpoint-195/special_tokens_map.json +7 -0
  18. checkpoint-195/tokenizer.json +0 -0
  19. checkpoint-195/tokenizer_config.json +55 -0
  20. checkpoint-195/trainer_state.json +81 -0
  21. checkpoint-195/training_args.bin +3 -0
  22. checkpoint-195/vocab.txt +0 -0
  23. checkpoint-260/config.json +101 -0
  24. checkpoint-260/model.safetensors +3 -0
  25. checkpoint-260/optimizer.pt +3 -0
  26. checkpoint-260/rng_state.pth +3 -0
  27. checkpoint-260/scheduler.pt +3 -0
  28. checkpoint-260/special_tokens_map.json +7 -0
  29. checkpoint-260/tokenizer.json +0 -0
  30. checkpoint-260/tokenizer_config.json +55 -0
  31. checkpoint-260/trainer_state.json +104 -0
  32. checkpoint-260/training_args.bin +3 -0
  33. checkpoint-260/vocab.txt +0 -0
  34. checkpoint-325/config.json +101 -0
  35. checkpoint-325/model.safetensors +3 -0
  36. checkpoint-325/optimizer.pt +3 -0
  37. checkpoint-325/rng_state.pth +3 -0
  38. checkpoint-325/scheduler.pt +3 -0
  39. checkpoint-325/special_tokens_map.json +7 -0
  40. checkpoint-325/tokenizer.json +0 -0
  41. checkpoint-325/tokenizer_config.json +55 -0
  42. checkpoint-325/trainer_state.json +120 -0
  43. checkpoint-325/training_args.bin +3 -0
  44. checkpoint-325/vocab.txt +0 -0
  45. checkpoint-390/config.json +101 -0
  46. checkpoint-390/model.safetensors +3 -0
  47. checkpoint-390/optimizer.pt +3 -0
  48. checkpoint-390/rng_state.pth +3 -0
  49. checkpoint-390/scheduler.pt +3 -0
  50. checkpoint-390/special_tokens_map.json +7 -0
checkpoint-130/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Pornography",
13
+ "1": "Erotica",
14
+ "2": "Adult Content",
15
+ "3": "Crime",
16
+ "4": "Sexual Assault",
17
+ "5": "Violent Crime",
18
+ "6": "Terrorist Attacks",
19
+ "7": "Counterterrorism",
20
+ "8": "Smoking",
21
+ "9": "Vaping",
22
+ "10": "Tobacco Use",
23
+ "11": "Military Conflict",
24
+ "12": "War",
25
+ "13": "International Relations",
26
+ "14": "Pandemic",
27
+ "15": "Vaccines",
28
+ "16": "Health Guidelines",
29
+ "17": "COVID-19 News",
30
+ "18": "Cybersecurity",
31
+ "19": "Hacking",
32
+ "20": "Malware",
33
+ "21": "Addiction",
34
+ "22": "Substance Abuse",
35
+ "23": "Rehabilitation",
36
+ "24": "Hate Speech",
37
+ "25": "Offensive Language",
38
+ "26": "Discrimination",
39
+ "27": "Racism",
40
+ "28": "Homophobia",
41
+ "29": "Accidents",
42
+ "30": "Disasters",
43
+ "31": "Public Safety",
44
+ "32": "Weapons",
45
+ "33": "Gun Control",
46
+ "34": "Firearms",
47
+ "35": "Death"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "label2id": {
51
+ "Accidents": 29,
52
+ "Addiction": 21,
53
+ "Adult Content": 2,
54
+ "COVID-19 News": 17,
55
+ "Counterterrorism": 7,
56
+ "Crime": 3,
57
+ "Cybersecurity": 18,
58
+ "Death": 35,
59
+ "Disasters": 30,
60
+ "Discrimination": 26,
61
+ "Erotica": 1,
62
+ "Firearms": 34,
63
+ "Gun Control": 33,
64
+ "Hacking": 19,
65
+ "Hate Speech": 24,
66
+ "Health Guidelines": 16,
67
+ "Homophobia": 28,
68
+ "International Relations": 13,
69
+ "Malware": 20,
70
+ "Military Conflict": 11,
71
+ "Offensive Language": 25,
72
+ "Pandemic": 14,
73
+ "Pornography": 0,
74
+ "Public Safety": 31,
75
+ "Racism": 27,
76
+ "Rehabilitation": 23,
77
+ "Sexual Assault": 4,
78
+ "Smoking": 8,
79
+ "Substance Abuse": 22,
80
+ "Terrorist Attacks": 6,
81
+ "Tobacco Use": 10,
82
+ "Vaccines": 15,
83
+ "Vaping": 9,
84
+ "Violent Crime": 5,
85
+ "War": 12,
86
+ "Weapons": 32
87
+ },
88
+ "max_position_embeddings": 512,
89
+ "model_type": "distilbert",
90
+ "n_heads": 12,
91
+ "n_layers": 6,
92
+ "pad_token_id": 0,
93
+ "problem_type": "single_label_classification",
94
+ "qa_dropout": 0.1,
95
+ "seq_classif_dropout": 0.2,
96
+ "sinusoidal_pos_embds": false,
97
+ "tie_weights_": true,
98
+ "torch_dtype": "float32",
99
+ "transformers_version": "4.44.0",
100
+ "vocab_size": 30522
101
+ }
checkpoint-130/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4f507d2e975992121a2f11451d0339a78b72791f472787eeef2a4ffb54f692
3
+ size 267937160
checkpoint-130/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b8362c4ae1aaaa8888ebd3e0b09881f37ca59131a71c3c513db2df78236435f
3
+ size 535936442
checkpoint-130/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86e150ce5bfa95d9cf3357222c6e802843f83fbe95406475580315f5fcfb796
3
+ size 14244
checkpoint-130/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb13d73f4adbd10440e729fa447721812103a0c91e8f258d5d084d9e2c7c3aad
3
+ size 1064
checkpoint-130/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
+ }
checkpoint-130/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-130/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-130/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5009746588693957,
3
+ "best_model_checkpoint": "brand-safety-model\\checkpoint-130",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 130,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7692307692307693,
13
+ "grad_norm": 2.6331872940063477,
14
+ "learning_rate": 2.7692307692307694e-05,
15
+ "loss": 3.319,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.42300194931773877,
21
+ "eval_loss": 2.7462074756622314,
22
+ "eval_runtime": 1.5522,
23
+ "eval_samples_per_second": 330.495,
24
+ "eval_steps_per_second": 10.952,
25
+ "step": 65
26
+ },
27
+ {
28
+ "epoch": 1.5384615384615383,
29
+ "grad_norm": 3.3225834369659424,
30
+ "learning_rate": 2.5384615384615386e-05,
31
+ "loss": 2.6272,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.5009746588693957,
37
+ "eval_loss": 2.07950758934021,
38
+ "eval_runtime": 1.523,
39
+ "eval_samples_per_second": 336.824,
40
+ "eval_steps_per_second": 11.162,
41
+ "step": 130
42
+ }
43
+ ],
44
+ "logging_steps": 50,
45
+ "max_steps": 650,
46
+ "num_input_tokens_seen": 0,
47
+ "num_train_epochs": 10,
48
+ "save_steps": 500,
49
+ "stateful_callbacks": {
50
+ "TrainerControl": {
51
+ "args": {
52
+ "should_epoch_stop": false,
53
+ "should_evaluate": false,
54
+ "should_log": false,
55
+ "should_save": true,
56
+ "should_training_stop": false
57
+ },
58
+ "attributes": {}
59
+ }
60
+ },
61
+ "total_flos": 163268759672352.0,
62
+ "train_batch_size": 32,
63
+ "trial_name": null,
64
+ "trial_params": null
65
+ }
checkpoint-130/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9a68dcb35447df75f0612c9054154ae4966d21ea11f108d3320c9e29bf8278
3
+ size 5112
checkpoint-130/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-195/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Pornography",
13
+ "1": "Erotica",
14
+ "2": "Adult Content",
15
+ "3": "Crime",
16
+ "4": "Sexual Assault",
17
+ "5": "Violent Crime",
18
+ "6": "Terrorist Attacks",
19
+ "7": "Counterterrorism",
20
+ "8": "Smoking",
21
+ "9": "Vaping",
22
+ "10": "Tobacco Use",
23
+ "11": "Military Conflict",
24
+ "12": "War",
25
+ "13": "International Relations",
26
+ "14": "Pandemic",
27
+ "15": "Vaccines",
28
+ "16": "Health Guidelines",
29
+ "17": "COVID-19 News",
30
+ "18": "Cybersecurity",
31
+ "19": "Hacking",
32
+ "20": "Malware",
33
+ "21": "Addiction",
34
+ "22": "Substance Abuse",
35
+ "23": "Rehabilitation",
36
+ "24": "Hate Speech",
37
+ "25": "Offensive Language",
38
+ "26": "Discrimination",
39
+ "27": "Racism",
40
+ "28": "Homophobia",
41
+ "29": "Accidents",
42
+ "30": "Disasters",
43
+ "31": "Public Safety",
44
+ "32": "Weapons",
45
+ "33": "Gun Control",
46
+ "34": "Firearms",
47
+ "35": "Death"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "label2id": {
51
+ "Accidents": 29,
52
+ "Addiction": 21,
53
+ "Adult Content": 2,
54
+ "COVID-19 News": 17,
55
+ "Counterterrorism": 7,
56
+ "Crime": 3,
57
+ "Cybersecurity": 18,
58
+ "Death": 35,
59
+ "Disasters": 30,
60
+ "Discrimination": 26,
61
+ "Erotica": 1,
62
+ "Firearms": 34,
63
+ "Gun Control": 33,
64
+ "Hacking": 19,
65
+ "Hate Speech": 24,
66
+ "Health Guidelines": 16,
67
+ "Homophobia": 28,
68
+ "International Relations": 13,
69
+ "Malware": 20,
70
+ "Military Conflict": 11,
71
+ "Offensive Language": 25,
72
+ "Pandemic": 14,
73
+ "Pornography": 0,
74
+ "Public Safety": 31,
75
+ "Racism": 27,
76
+ "Rehabilitation": 23,
77
+ "Sexual Assault": 4,
78
+ "Smoking": 8,
79
+ "Substance Abuse": 22,
80
+ "Terrorist Attacks": 6,
81
+ "Tobacco Use": 10,
82
+ "Vaccines": 15,
83
+ "Vaping": 9,
84
+ "Violent Crime": 5,
85
+ "War": 12,
86
+ "Weapons": 32
87
+ },
88
+ "max_position_embeddings": 512,
89
+ "model_type": "distilbert",
90
+ "n_heads": 12,
91
+ "n_layers": 6,
92
+ "pad_token_id": 0,
93
+ "problem_type": "single_label_classification",
94
+ "qa_dropout": 0.1,
95
+ "seq_classif_dropout": 0.2,
96
+ "sinusoidal_pos_embds": false,
97
+ "tie_weights_": true,
98
+ "torch_dtype": "float32",
99
+ "transformers_version": "4.44.0",
100
+ "vocab_size": 30522
101
+ }
checkpoint-195/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9029b4f641b86c7cc7c315a5e689fd3c17bc23f097ec80612a0e0d80b93442fb
3
+ size 267937160
checkpoint-195/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f692c5809d83d23ba7720f9d51f7f0aed5e204be08ca3db7c85354f8381922f
3
+ size 535936442
checkpoint-195/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:769e40e9036a95ce829fab1fac85265032e5b192e0797fb28a01ff55541941dc
3
+ size 14244
checkpoint-195/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3901049ab3dde7eb25fb6710db6ba8581baa899bbb5bbea83888f8967f13ca79
3
+ size 1064
checkpoint-195/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
+ }
checkpoint-195/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-195/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-195/trainer_state.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5769980506822612,
3
+ "best_model_checkpoint": "brand-safety-model\\checkpoint-195",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 195,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7692307692307693,
13
+ "grad_norm": 2.6331872940063477,
14
+ "learning_rate": 2.7692307692307694e-05,
15
+ "loss": 3.319,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.42300194931773877,
21
+ "eval_loss": 2.7462074756622314,
22
+ "eval_runtime": 1.5522,
23
+ "eval_samples_per_second": 330.495,
24
+ "eval_steps_per_second": 10.952,
25
+ "step": 65
26
+ },
27
+ {
28
+ "epoch": 1.5384615384615383,
29
+ "grad_norm": 3.3225834369659424,
30
+ "learning_rate": 2.5384615384615386e-05,
31
+ "loss": 2.6272,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.5009746588693957,
37
+ "eval_loss": 2.07950758934021,
38
+ "eval_runtime": 1.523,
39
+ "eval_samples_per_second": 336.824,
40
+ "eval_steps_per_second": 11.162,
41
+ "step": 130
42
+ },
43
+ {
44
+ "epoch": 2.3076923076923075,
45
+ "grad_norm": 3.2619457244873047,
46
+ "learning_rate": 2.307692307692308e-05,
47
+ "loss": 2.137,
48
+ "step": 150
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.5769980506822612,
53
+ "eval_loss": 1.6682791709899902,
54
+ "eval_runtime": 1.5108,
55
+ "eval_samples_per_second": 339.548,
56
+ "eval_steps_per_second": 11.252,
57
+ "step": 195
58
+ }
59
+ ],
60
+ "logging_steps": 50,
61
+ "max_steps": 650,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 10,
64
+ "save_steps": 500,
65
+ "stateful_callbacks": {
66
+ "TrainerControl": {
67
+ "args": {
68
+ "should_epoch_stop": false,
69
+ "should_evaluate": false,
70
+ "should_log": false,
71
+ "should_save": true,
72
+ "should_training_stop": false
73
+ },
74
+ "attributes": {}
75
+ }
76
+ },
77
+ "total_flos": 243952006070592.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": null
81
+ }
checkpoint-195/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9a68dcb35447df75f0612c9054154ae4966d21ea11f108d3320c9e29bf8278
3
+ size 5112
checkpoint-195/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-260/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Pornography",
13
+ "1": "Erotica",
14
+ "2": "Adult Content",
15
+ "3": "Crime",
16
+ "4": "Sexual Assault",
17
+ "5": "Violent Crime",
18
+ "6": "Terrorist Attacks",
19
+ "7": "Counterterrorism",
20
+ "8": "Smoking",
21
+ "9": "Vaping",
22
+ "10": "Tobacco Use",
23
+ "11": "Military Conflict",
24
+ "12": "War",
25
+ "13": "International Relations",
26
+ "14": "Pandemic",
27
+ "15": "Vaccines",
28
+ "16": "Health Guidelines",
29
+ "17": "COVID-19 News",
30
+ "18": "Cybersecurity",
31
+ "19": "Hacking",
32
+ "20": "Malware",
33
+ "21": "Addiction",
34
+ "22": "Substance Abuse",
35
+ "23": "Rehabilitation",
36
+ "24": "Hate Speech",
37
+ "25": "Offensive Language",
38
+ "26": "Discrimination",
39
+ "27": "Racism",
40
+ "28": "Homophobia",
41
+ "29": "Accidents",
42
+ "30": "Disasters",
43
+ "31": "Public Safety",
44
+ "32": "Weapons",
45
+ "33": "Gun Control",
46
+ "34": "Firearms",
47
+ "35": "Death"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "label2id": {
51
+ "Accidents": 29,
52
+ "Addiction": 21,
53
+ "Adult Content": 2,
54
+ "COVID-19 News": 17,
55
+ "Counterterrorism": 7,
56
+ "Crime": 3,
57
+ "Cybersecurity": 18,
58
+ "Death": 35,
59
+ "Disasters": 30,
60
+ "Discrimination": 26,
61
+ "Erotica": 1,
62
+ "Firearms": 34,
63
+ "Gun Control": 33,
64
+ "Hacking": 19,
65
+ "Hate Speech": 24,
66
+ "Health Guidelines": 16,
67
+ "Homophobia": 28,
68
+ "International Relations": 13,
69
+ "Malware": 20,
70
+ "Military Conflict": 11,
71
+ "Offensive Language": 25,
72
+ "Pandemic": 14,
73
+ "Pornography": 0,
74
+ "Public Safety": 31,
75
+ "Racism": 27,
76
+ "Rehabilitation": 23,
77
+ "Sexual Assault": 4,
78
+ "Smoking": 8,
79
+ "Substance Abuse": 22,
80
+ "Terrorist Attacks": 6,
81
+ "Tobacco Use": 10,
82
+ "Vaccines": 15,
83
+ "Vaping": 9,
84
+ "Violent Crime": 5,
85
+ "War": 12,
86
+ "Weapons": 32
87
+ },
88
+ "max_position_embeddings": 512,
89
+ "model_type": "distilbert",
90
+ "n_heads": 12,
91
+ "n_layers": 6,
92
+ "pad_token_id": 0,
93
+ "problem_type": "single_label_classification",
94
+ "qa_dropout": 0.1,
95
+ "seq_classif_dropout": 0.2,
96
+ "sinusoidal_pos_embds": false,
97
+ "tie_weights_": true,
98
+ "torch_dtype": "float32",
99
+ "transformers_version": "4.44.0",
100
+ "vocab_size": 30522
101
+ }
checkpoint-260/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e7bec929efc660218f00dbf5f17d57a4e9fbdb4e46e3772783d56411797521
3
+ size 267937160
checkpoint-260/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cd7b4420575cc63543aa39d31910a1e983fd90fcf2d1c0a5f448e5532a44200
3
+ size 535936442
checkpoint-260/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60f2b050f91f508c2965e30db712a9dc47a9438b96766bf2e2d7a0ced6bbf23
3
+ size 14244
checkpoint-260/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e95f0c177e2ba3fc34b6b7d2d47a7917a6116a066c1694ff0b95eb660ba1ecd
3
+ size 1064
checkpoint-260/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
+ }
checkpoint-260/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-260/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-260/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6101364522417154,
3
+ "best_model_checkpoint": "brand-safety-model\\checkpoint-260",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 260,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7692307692307693,
13
+ "grad_norm": 2.6331872940063477,
14
+ "learning_rate": 2.7692307692307694e-05,
15
+ "loss": 3.319,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.42300194931773877,
21
+ "eval_loss": 2.7462074756622314,
22
+ "eval_runtime": 1.5522,
23
+ "eval_samples_per_second": 330.495,
24
+ "eval_steps_per_second": 10.952,
25
+ "step": 65
26
+ },
27
+ {
28
+ "epoch": 1.5384615384615383,
29
+ "grad_norm": 3.3225834369659424,
30
+ "learning_rate": 2.5384615384615386e-05,
31
+ "loss": 2.6272,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.5009746588693957,
37
+ "eval_loss": 2.07950758934021,
38
+ "eval_runtime": 1.523,
39
+ "eval_samples_per_second": 336.824,
40
+ "eval_steps_per_second": 11.162,
41
+ "step": 130
42
+ },
43
+ {
44
+ "epoch": 2.3076923076923075,
45
+ "grad_norm": 3.2619457244873047,
46
+ "learning_rate": 2.307692307692308e-05,
47
+ "loss": 2.137,
48
+ "step": 150
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.5769980506822612,
53
+ "eval_loss": 1.6682791709899902,
54
+ "eval_runtime": 1.5108,
55
+ "eval_samples_per_second": 339.548,
56
+ "eval_steps_per_second": 11.252,
57
+ "step": 195
58
+ },
59
+ {
60
+ "epoch": 3.076923076923077,
61
+ "grad_norm": 3.448869228363037,
62
+ "learning_rate": 2.076923076923077e-05,
63
+ "loss": 1.7515,
64
+ "step": 200
65
+ },
66
+ {
67
+ "epoch": 3.8461538461538463,
68
+ "grad_norm": 3.639822483062744,
69
+ "learning_rate": 1.8461538461538465e-05,
70
+ "loss": 1.469,
71
+ "step": 250
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.6101364522417154,
76
+ "eval_loss": 1.472076654434204,
77
+ "eval_runtime": 1.5018,
78
+ "eval_samples_per_second": 341.601,
79
+ "eval_steps_per_second": 11.32,
80
+ "step": 260
81
+ }
82
+ ],
83
+ "logging_steps": 50,
84
+ "max_steps": 650,
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": 325268996251104.0,
101
+ "train_batch_size": 32,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
checkpoint-260/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9a68dcb35447df75f0612c9054154ae4966d21ea11f108d3320c9e29bf8278
3
+ size 5112
checkpoint-260/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-325/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Pornography",
13
+ "1": "Erotica",
14
+ "2": "Adult Content",
15
+ "3": "Crime",
16
+ "4": "Sexual Assault",
17
+ "5": "Violent Crime",
18
+ "6": "Terrorist Attacks",
19
+ "7": "Counterterrorism",
20
+ "8": "Smoking",
21
+ "9": "Vaping",
22
+ "10": "Tobacco Use",
23
+ "11": "Military Conflict",
24
+ "12": "War",
25
+ "13": "International Relations",
26
+ "14": "Pandemic",
27
+ "15": "Vaccines",
28
+ "16": "Health Guidelines",
29
+ "17": "COVID-19 News",
30
+ "18": "Cybersecurity",
31
+ "19": "Hacking",
32
+ "20": "Malware",
33
+ "21": "Addiction",
34
+ "22": "Substance Abuse",
35
+ "23": "Rehabilitation",
36
+ "24": "Hate Speech",
37
+ "25": "Offensive Language",
38
+ "26": "Discrimination",
39
+ "27": "Racism",
40
+ "28": "Homophobia",
41
+ "29": "Accidents",
42
+ "30": "Disasters",
43
+ "31": "Public Safety",
44
+ "32": "Weapons",
45
+ "33": "Gun Control",
46
+ "34": "Firearms",
47
+ "35": "Death"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "label2id": {
51
+ "Accidents": 29,
52
+ "Addiction": 21,
53
+ "Adult Content": 2,
54
+ "COVID-19 News": 17,
55
+ "Counterterrorism": 7,
56
+ "Crime": 3,
57
+ "Cybersecurity": 18,
58
+ "Death": 35,
59
+ "Disasters": 30,
60
+ "Discrimination": 26,
61
+ "Erotica": 1,
62
+ "Firearms": 34,
63
+ "Gun Control": 33,
64
+ "Hacking": 19,
65
+ "Hate Speech": 24,
66
+ "Health Guidelines": 16,
67
+ "Homophobia": 28,
68
+ "International Relations": 13,
69
+ "Malware": 20,
70
+ "Military Conflict": 11,
71
+ "Offensive Language": 25,
72
+ "Pandemic": 14,
73
+ "Pornography": 0,
74
+ "Public Safety": 31,
75
+ "Racism": 27,
76
+ "Rehabilitation": 23,
77
+ "Sexual Assault": 4,
78
+ "Smoking": 8,
79
+ "Substance Abuse": 22,
80
+ "Terrorist Attacks": 6,
81
+ "Tobacco Use": 10,
82
+ "Vaccines": 15,
83
+ "Vaping": 9,
84
+ "Violent Crime": 5,
85
+ "War": 12,
86
+ "Weapons": 32
87
+ },
88
+ "max_position_embeddings": 512,
89
+ "model_type": "distilbert",
90
+ "n_heads": 12,
91
+ "n_layers": 6,
92
+ "pad_token_id": 0,
93
+ "problem_type": "single_label_classification",
94
+ "qa_dropout": 0.1,
95
+ "seq_classif_dropout": 0.2,
96
+ "sinusoidal_pos_embds": false,
97
+ "tie_weights_": true,
98
+ "torch_dtype": "float32",
99
+ "transformers_version": "4.44.0",
100
+ "vocab_size": 30522
101
+ }
checkpoint-325/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c8c1cf03c6864b2956e5235f34b02bcd3ea51f808ba94f5e30e78c84d468bb
3
+ size 267937160
checkpoint-325/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f63e5142f1ff4c0cb061c3d21678fcb24f2af2b7c75b5ef06d0a39e6c1068fc7
3
+ size 535936442
checkpoint-325/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae988e902711e21f3f7149d74604506375498fdb44c03db56206af31012c815b
3
+ size 14244
checkpoint-325/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8388375c9f5e18503d2a2c6b8c63bb077affec6d53bf17417e3d310aaa19b6d4
3
+ size 1064
checkpoint-325/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
+ }
checkpoint-325/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-325/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-325/trainer_state.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6354775828460039,
3
+ "best_model_checkpoint": "brand-safety-model\\checkpoint-325",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 325,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7692307692307693,
13
+ "grad_norm": 2.6331872940063477,
14
+ "learning_rate": 2.7692307692307694e-05,
15
+ "loss": 3.319,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.42300194931773877,
21
+ "eval_loss": 2.7462074756622314,
22
+ "eval_runtime": 1.5522,
23
+ "eval_samples_per_second": 330.495,
24
+ "eval_steps_per_second": 10.952,
25
+ "step": 65
26
+ },
27
+ {
28
+ "epoch": 1.5384615384615383,
29
+ "grad_norm": 3.3225834369659424,
30
+ "learning_rate": 2.5384615384615386e-05,
31
+ "loss": 2.6272,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.5009746588693957,
37
+ "eval_loss": 2.07950758934021,
38
+ "eval_runtime": 1.523,
39
+ "eval_samples_per_second": 336.824,
40
+ "eval_steps_per_second": 11.162,
41
+ "step": 130
42
+ },
43
+ {
44
+ "epoch": 2.3076923076923075,
45
+ "grad_norm": 3.2619457244873047,
46
+ "learning_rate": 2.307692307692308e-05,
47
+ "loss": 2.137,
48
+ "step": 150
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.5769980506822612,
53
+ "eval_loss": 1.6682791709899902,
54
+ "eval_runtime": 1.5108,
55
+ "eval_samples_per_second": 339.548,
56
+ "eval_steps_per_second": 11.252,
57
+ "step": 195
58
+ },
59
+ {
60
+ "epoch": 3.076923076923077,
61
+ "grad_norm": 3.448869228363037,
62
+ "learning_rate": 2.076923076923077e-05,
63
+ "loss": 1.7515,
64
+ "step": 200
65
+ },
66
+ {
67
+ "epoch": 3.8461538461538463,
68
+ "grad_norm": 3.639822483062744,
69
+ "learning_rate": 1.8461538461538465e-05,
70
+ "loss": 1.469,
71
+ "step": 250
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.6101364522417154,
76
+ "eval_loss": 1.472076654434204,
77
+ "eval_runtime": 1.5018,
78
+ "eval_samples_per_second": 341.601,
79
+ "eval_steps_per_second": 11.32,
80
+ "step": 260
81
+ },
82
+ {
83
+ "epoch": 4.615384615384615,
84
+ "grad_norm": 4.488701820373535,
85
+ "learning_rate": 1.6153846153846154e-05,
86
+ "loss": 1.2405,
87
+ "step": 300
88
+ },
89
+ {
90
+ "epoch": 5.0,
91
+ "eval_accuracy": 0.6354775828460039,
92
+ "eval_loss": 1.34968101978302,
93
+ "eval_runtime": 1.5205,
94
+ "eval_samples_per_second": 337.4,
95
+ "eval_steps_per_second": 11.181,
96
+ "step": 325
97
+ }
98
+ ],
99
+ "logging_steps": 50,
100
+ "max_steps": 650,
101
+ "num_input_tokens_seen": 0,
102
+ "num_train_epochs": 10,
103
+ "save_steps": 500,
104
+ "stateful_callbacks": {
105
+ "TrainerControl": {
106
+ "args": {
107
+ "should_epoch_stop": false,
108
+ "should_evaluate": false,
109
+ "should_log": false,
110
+ "should_save": true,
111
+ "should_training_stop": false
112
+ },
113
+ "attributes": {}
114
+ }
115
+ },
116
+ "total_flos": 406125176001696.0,
117
+ "train_batch_size": 32,
118
+ "trial_name": null,
119
+ "trial_params": null
120
+ }
checkpoint-325/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9a68dcb35447df75f0612c9054154ae4966d21ea11f108d3320c9e29bf8278
3
+ size 5112
checkpoint-325/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-390/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Pornography",
13
+ "1": "Erotica",
14
+ "2": "Adult Content",
15
+ "3": "Crime",
16
+ "4": "Sexual Assault",
17
+ "5": "Violent Crime",
18
+ "6": "Terrorist Attacks",
19
+ "7": "Counterterrorism",
20
+ "8": "Smoking",
21
+ "9": "Vaping",
22
+ "10": "Tobacco Use",
23
+ "11": "Military Conflict",
24
+ "12": "War",
25
+ "13": "International Relations",
26
+ "14": "Pandemic",
27
+ "15": "Vaccines",
28
+ "16": "Health Guidelines",
29
+ "17": "COVID-19 News",
30
+ "18": "Cybersecurity",
31
+ "19": "Hacking",
32
+ "20": "Malware",
33
+ "21": "Addiction",
34
+ "22": "Substance Abuse",
35
+ "23": "Rehabilitation",
36
+ "24": "Hate Speech",
37
+ "25": "Offensive Language",
38
+ "26": "Discrimination",
39
+ "27": "Racism",
40
+ "28": "Homophobia",
41
+ "29": "Accidents",
42
+ "30": "Disasters",
43
+ "31": "Public Safety",
44
+ "32": "Weapons",
45
+ "33": "Gun Control",
46
+ "34": "Firearms",
47
+ "35": "Death"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "label2id": {
51
+ "Accidents": 29,
52
+ "Addiction": 21,
53
+ "Adult Content": 2,
54
+ "COVID-19 News": 17,
55
+ "Counterterrorism": 7,
56
+ "Crime": 3,
57
+ "Cybersecurity": 18,
58
+ "Death": 35,
59
+ "Disasters": 30,
60
+ "Discrimination": 26,
61
+ "Erotica": 1,
62
+ "Firearms": 34,
63
+ "Gun Control": 33,
64
+ "Hacking": 19,
65
+ "Hate Speech": 24,
66
+ "Health Guidelines": 16,
67
+ "Homophobia": 28,
68
+ "International Relations": 13,
69
+ "Malware": 20,
70
+ "Military Conflict": 11,
71
+ "Offensive Language": 25,
72
+ "Pandemic": 14,
73
+ "Pornography": 0,
74
+ "Public Safety": 31,
75
+ "Racism": 27,
76
+ "Rehabilitation": 23,
77
+ "Sexual Assault": 4,
78
+ "Smoking": 8,
79
+ "Substance Abuse": 22,
80
+ "Terrorist Attacks": 6,
81
+ "Tobacco Use": 10,
82
+ "Vaccines": 15,
83
+ "Vaping": 9,
84
+ "Violent Crime": 5,
85
+ "War": 12,
86
+ "Weapons": 32
87
+ },
88
+ "max_position_embeddings": 512,
89
+ "model_type": "distilbert",
90
+ "n_heads": 12,
91
+ "n_layers": 6,
92
+ "pad_token_id": 0,
93
+ "problem_type": "single_label_classification",
94
+ "qa_dropout": 0.1,
95
+ "seq_classif_dropout": 0.2,
96
+ "sinusoidal_pos_embds": false,
97
+ "tie_weights_": true,
98
+ "torch_dtype": "float32",
99
+ "transformers_version": "4.44.0",
100
+ "vocab_size": 30522
101
+ }
checkpoint-390/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66aec30c180ee0343c611a40b9bdec395cbfc7826b54cfc04f3362c542b2a365
3
+ size 267937160
checkpoint-390/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31a903f961212e110c5e223e2f9122c834882a2df312fd4f33d7ebf017c6881
3
+ size 535936442
checkpoint-390/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e966e4014fc9448d4d84213affd2608400b1c15330a0a06f7a907f39b8d50a7c
3
+ size 14244
checkpoint-390/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01db32e95a13ca44ceba4092cf2bbe2a02fcda94da6ba1e9f445300d2daf822e
3
+ size 1064
checkpoint-390/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
+ }