manjaveca commited on
Commit
1490f9d
·
verified ·
1 Parent(s): d84a116

Upload folder using huggingface_hub

Browse files
Files changed (44) hide show
  1. added_tokens.json +7 -0
  2. checkpoint-2138/added_tokens.json +7 -0
  3. checkpoint-2138/config.json +68 -0
  4. checkpoint-2138/optimizer.pt +3 -0
  5. checkpoint-2138/pytorch_model.bin +3 -0
  6. checkpoint-2138/rng_state.pth +3 -0
  7. checkpoint-2138/scheduler.pt +3 -0
  8. checkpoint-2138/special_tokens_map.json +7 -0
  9. checkpoint-2138/tokenizer.json +0 -0
  10. checkpoint-2138/tokenizer_config.json +58 -0
  11. checkpoint-2138/trainer_state.json +55 -0
  12. checkpoint-2138/training_args.bin +3 -0
  13. checkpoint-2138/vocab.txt +0 -0
  14. checkpoint-4276/added_tokens.json +7 -0
  15. checkpoint-4276/config.json +68 -0
  16. checkpoint-4276/optimizer.pt +3 -0
  17. checkpoint-4276/pytorch_model.bin +3 -0
  18. checkpoint-4276/rng_state.pth +3 -0
  19. checkpoint-4276/scheduler.pt +3 -0
  20. checkpoint-4276/special_tokens_map.json +7 -0
  21. checkpoint-4276/tokenizer.json +0 -0
  22. checkpoint-4276/tokenizer_config.json +58 -0
  23. checkpoint-4276/trainer_state.json +91 -0
  24. checkpoint-4276/training_args.bin +3 -0
  25. checkpoint-4276/vocab.txt +0 -0
  26. checkpoint-6414/added_tokens.json +7 -0
  27. checkpoint-6414/config.json +68 -0
  28. checkpoint-6414/optimizer.pt +3 -0
  29. checkpoint-6414/pytorch_model.bin +3 -0
  30. checkpoint-6414/rng_state.pth +3 -0
  31. checkpoint-6414/scheduler.pt +3 -0
  32. checkpoint-6414/special_tokens_map.json +7 -0
  33. checkpoint-6414/tokenizer.json +0 -0
  34. checkpoint-6414/tokenizer_config.json +58 -0
  35. checkpoint-6414/trainer_state.json +127 -0
  36. checkpoint-6414/training_args.bin +3 -0
  37. checkpoint-6414/vocab.txt +0 -0
  38. config.json +68 -0
  39. pytorch_model.bin +3 -0
  40. special_tokens_map.json +7 -0
  41. tokenizer.json +0 -0
  42. tokenizer_config.json +58 -0
  43. training_args.bin +3 -0
  44. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
checkpoint-2138/added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
checkpoint-2138/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../original",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "AskLink",
14
+ "1": "AskLocation",
15
+ "2": "AskRealness",
16
+ "3": "AskToMeet",
17
+ "4": "DeepOrPhilosophical",
18
+ "5": "EmotionalNeed",
19
+ "6": "FallbackUnknown",
20
+ "7": "Flirt",
21
+ "8": "Greeting",
22
+ "9": "IdleOrGhosting",
23
+ "10": "RefuseOnlyFans",
24
+ "11": "RequestPic",
25
+ "12": "SmallTalk",
26
+ "13": "SuccessfulSub",
27
+ "14": "UserBusyOrDelay",
28
+ "15": "UserInsultOrHate",
29
+ "16": "UserNoMoney",
30
+ "17": "UserShynessOrDoubt",
31
+ "18": "UserTestingBot"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "label2id": {
35
+ "AskLink": 0,
36
+ "AskLocation": 1,
37
+ "AskRealness": 2,
38
+ "AskToMeet": 3,
39
+ "DeepOrPhilosophical": 4,
40
+ "EmotionalNeed": 5,
41
+ "FallbackUnknown": 6,
42
+ "Flirt": 7,
43
+ "Greeting": 8,
44
+ "IdleOrGhosting": 9,
45
+ "RefuseOnlyFans": 10,
46
+ "RequestPic": 11,
47
+ "SmallTalk": 12,
48
+ "SuccessfulSub": 13,
49
+ "UserBusyOrDelay": 14,
50
+ "UserInsultOrHate": 15,
51
+ "UserNoMoney": 16,
52
+ "UserShynessOrDoubt": 17,
53
+ "UserTestingBot": 18
54
+ },
55
+ "max_position_embeddings": 512,
56
+ "model_type": "distilbert",
57
+ "n_heads": 12,
58
+ "n_layers": 6,
59
+ "output_past": true,
60
+ "pad_token_id": 0,
61
+ "qa_dropout": 0.1,
62
+ "seq_classif_dropout": 0.2,
63
+ "sinusoidal_pos_embds": false,
64
+ "tie_weights_": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.34.0",
67
+ "vocab_size": 30522
68
+ }
checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f112b799dd0d302c7888e6e822ea609201091d794667da5c2ca0d18d63018842
3
+ size 535831866
checkpoint-2138/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd9d818c7fc21a559921a108653bb843d350efcaf54c30af3744400c4848d83
3
+ size 267908266
checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe93dd439637f8d261327755467663b0c88237c117ba83b744dacf9f96469a1
3
+ size 14244
checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5593b1bc02d8723e7dbc3e88ba81a7436b5ce38719c3bcdf775de2b7862c0943
3
+ size 1064
checkpoint-2138/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-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2138/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "../FINAL/checkpoint-2138",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2138,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 2e-05,
14
+ "loss": 0.3679,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 1.8758072528564333e-05,
20
+ "loss": 0.0029,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 1.7516145057128665e-05,
26
+ "loss": 0.0006,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 1.6274217585692997e-05,
32
+ "loss": 0.0003,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 1.0,
38
+ "eval_f1": 1.0,
39
+ "eval_loss": 5.122346919961274e-05,
40
+ "eval_precision": 1.0,
41
+ "eval_recall": 1.0,
42
+ "eval_runtime": 1.22,
43
+ "eval_samples_per_second": 3114.786,
44
+ "eval_steps_per_second": 195.084,
45
+ "step": 2138
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 8552,
50
+ "num_train_epochs": 4,
51
+ "save_steps": 500,
52
+ "total_flos": 94983074572608.0,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a067afdd27f1ad2f727fe17e38b0dc1e79b5b70ee8f9258f1cbc6a3f4da54b
3
+ size 4472
checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4276/added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
checkpoint-4276/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../original",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "AskLink",
14
+ "1": "AskLocation",
15
+ "2": "AskRealness",
16
+ "3": "AskToMeet",
17
+ "4": "DeepOrPhilosophical",
18
+ "5": "EmotionalNeed",
19
+ "6": "FallbackUnknown",
20
+ "7": "Flirt",
21
+ "8": "Greeting",
22
+ "9": "IdleOrGhosting",
23
+ "10": "RefuseOnlyFans",
24
+ "11": "RequestPic",
25
+ "12": "SmallTalk",
26
+ "13": "SuccessfulSub",
27
+ "14": "UserBusyOrDelay",
28
+ "15": "UserInsultOrHate",
29
+ "16": "UserNoMoney",
30
+ "17": "UserShynessOrDoubt",
31
+ "18": "UserTestingBot"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "label2id": {
35
+ "AskLink": 0,
36
+ "AskLocation": 1,
37
+ "AskRealness": 2,
38
+ "AskToMeet": 3,
39
+ "DeepOrPhilosophical": 4,
40
+ "EmotionalNeed": 5,
41
+ "FallbackUnknown": 6,
42
+ "Flirt": 7,
43
+ "Greeting": 8,
44
+ "IdleOrGhosting": 9,
45
+ "RefuseOnlyFans": 10,
46
+ "RequestPic": 11,
47
+ "SmallTalk": 12,
48
+ "SuccessfulSub": 13,
49
+ "UserBusyOrDelay": 14,
50
+ "UserInsultOrHate": 15,
51
+ "UserNoMoney": 16,
52
+ "UserShynessOrDoubt": 17,
53
+ "UserTestingBot": 18
54
+ },
55
+ "max_position_embeddings": 512,
56
+ "model_type": "distilbert",
57
+ "n_heads": 12,
58
+ "n_layers": 6,
59
+ "output_past": true,
60
+ "pad_token_id": 0,
61
+ "qa_dropout": 0.1,
62
+ "seq_classif_dropout": 0.2,
63
+ "sinusoidal_pos_embds": false,
64
+ "tie_weights_": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.34.0",
67
+ "vocab_size": 30522
68
+ }
checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d3303cdb83b3a01103497c04e7fca233a7da903d2db2f5452cd7c4500e49d2
3
+ size 535831866
checkpoint-4276/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b88c66611cddce1f982ec1d219b7e5cab5697a342f6fb5380357842f81acda
3
+ size 267908266
checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1bc38aef5603d4d9ff9198322216440424258eac4ef37b385dc0e0250e14bec
3
+ size 14244
checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a876bd7832f8c3c3afca2daa6a3dd9a5fed84a7e7ecdbc952c0e74e9011f04a
3
+ size 1064
checkpoint-4276/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-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4276/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "../FINAL/checkpoint-2138",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4276,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 2e-05,
14
+ "loss": 0.3679,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 1.8758072528564333e-05,
20
+ "loss": 0.0029,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 1.7516145057128665e-05,
26
+ "loss": 0.0006,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 1.6274217585692997e-05,
32
+ "loss": 0.0003,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 1.0,
38
+ "eval_f1": 1.0,
39
+ "eval_loss": 5.122346919961274e-05,
40
+ "eval_precision": 1.0,
41
+ "eval_recall": 1.0,
42
+ "eval_runtime": 1.22,
43
+ "eval_samples_per_second": 3114.786,
44
+ "eval_steps_per_second": 195.084,
45
+ "step": 2138
46
+ },
47
+ {
48
+ "epoch": 1.17,
49
+ "learning_rate": 1.5032290114257329e-05,
50
+ "loss": 0.0002,
51
+ "step": 2500
52
+ },
53
+ {
54
+ "epoch": 1.4,
55
+ "learning_rate": 1.379036264282166e-05,
56
+ "loss": 0.0001,
57
+ "step": 3000
58
+ },
59
+ {
60
+ "epoch": 1.64,
61
+ "learning_rate": 1.2548435171385993e-05,
62
+ "loss": 0.0001,
63
+ "step": 3500
64
+ },
65
+ {
66
+ "epoch": 1.87,
67
+ "learning_rate": 1.1306507699950325e-05,
68
+ "loss": 0.0001,
69
+ "step": 4000
70
+ },
71
+ {
72
+ "epoch": 2.0,
73
+ "eval_accuracy": 1.0,
74
+ "eval_f1": 1.0,
75
+ "eval_loss": 1.0265763194183819e-05,
76
+ "eval_precision": 1.0,
77
+ "eval_recall": 1.0,
78
+ "eval_runtime": 1.1652,
79
+ "eval_samples_per_second": 3261.207,
80
+ "eval_steps_per_second": 204.255,
81
+ "step": 4276
82
+ }
83
+ ],
84
+ "logging_steps": 500,
85
+ "max_steps": 8552,
86
+ "num_train_epochs": 4,
87
+ "save_steps": 500,
88
+ "total_flos": 190003416896160.0,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }
checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a067afdd27f1ad2f727fe17e38b0dc1e79b5b70ee8f9258f1cbc6a3f4da54b
3
+ size 4472
checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6414/added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
checkpoint-6414/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../original",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "AskLink",
14
+ "1": "AskLocation",
15
+ "2": "AskRealness",
16
+ "3": "AskToMeet",
17
+ "4": "DeepOrPhilosophical",
18
+ "5": "EmotionalNeed",
19
+ "6": "FallbackUnknown",
20
+ "7": "Flirt",
21
+ "8": "Greeting",
22
+ "9": "IdleOrGhosting",
23
+ "10": "RefuseOnlyFans",
24
+ "11": "RequestPic",
25
+ "12": "SmallTalk",
26
+ "13": "SuccessfulSub",
27
+ "14": "UserBusyOrDelay",
28
+ "15": "UserInsultOrHate",
29
+ "16": "UserNoMoney",
30
+ "17": "UserShynessOrDoubt",
31
+ "18": "UserTestingBot"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "label2id": {
35
+ "AskLink": 0,
36
+ "AskLocation": 1,
37
+ "AskRealness": 2,
38
+ "AskToMeet": 3,
39
+ "DeepOrPhilosophical": 4,
40
+ "EmotionalNeed": 5,
41
+ "FallbackUnknown": 6,
42
+ "Flirt": 7,
43
+ "Greeting": 8,
44
+ "IdleOrGhosting": 9,
45
+ "RefuseOnlyFans": 10,
46
+ "RequestPic": 11,
47
+ "SmallTalk": 12,
48
+ "SuccessfulSub": 13,
49
+ "UserBusyOrDelay": 14,
50
+ "UserInsultOrHate": 15,
51
+ "UserNoMoney": 16,
52
+ "UserShynessOrDoubt": 17,
53
+ "UserTestingBot": 18
54
+ },
55
+ "max_position_embeddings": 512,
56
+ "model_type": "distilbert",
57
+ "n_heads": 12,
58
+ "n_layers": 6,
59
+ "output_past": true,
60
+ "pad_token_id": 0,
61
+ "qa_dropout": 0.1,
62
+ "seq_classif_dropout": 0.2,
63
+ "sinusoidal_pos_embds": false,
64
+ "tie_weights_": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.34.0",
67
+ "vocab_size": 30522
68
+ }
checkpoint-6414/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9d194235ca95721832730e9e5e66f9aee07f35a8ac6cc24ab7bc73b3cf1e98
3
+ size 535831866
checkpoint-6414/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e12c9d0f8bf71b60f667659de491b51f83563852cc18698fa30f614b2cddae9
3
+ size 267908266
checkpoint-6414/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac2cb5890a25c5aa85a557689e6c8f1edd789ffea8f79aaed8b7ed3cea2da56
3
+ size 14244
checkpoint-6414/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480cf537f8d63a566c2aee115a01e83dfc1de6f4f360095dd0d3615057b964c7
3
+ size 1064
checkpoint-6414/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-6414/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6414/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
checkpoint-6414/trainer_state.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "../FINAL/checkpoint-2138",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6414,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 2e-05,
14
+ "loss": 0.3679,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 1.8758072528564333e-05,
20
+ "loss": 0.0029,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 1.7516145057128665e-05,
26
+ "loss": 0.0006,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 1.6274217585692997e-05,
32
+ "loss": 0.0003,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 1.0,
38
+ "eval_f1": 1.0,
39
+ "eval_loss": 5.122346919961274e-05,
40
+ "eval_precision": 1.0,
41
+ "eval_recall": 1.0,
42
+ "eval_runtime": 1.22,
43
+ "eval_samples_per_second": 3114.786,
44
+ "eval_steps_per_second": 195.084,
45
+ "step": 2138
46
+ },
47
+ {
48
+ "epoch": 1.17,
49
+ "learning_rate": 1.5032290114257329e-05,
50
+ "loss": 0.0002,
51
+ "step": 2500
52
+ },
53
+ {
54
+ "epoch": 1.4,
55
+ "learning_rate": 1.379036264282166e-05,
56
+ "loss": 0.0001,
57
+ "step": 3000
58
+ },
59
+ {
60
+ "epoch": 1.64,
61
+ "learning_rate": 1.2548435171385993e-05,
62
+ "loss": 0.0001,
63
+ "step": 3500
64
+ },
65
+ {
66
+ "epoch": 1.87,
67
+ "learning_rate": 1.1306507699950325e-05,
68
+ "loss": 0.0001,
69
+ "step": 4000
70
+ },
71
+ {
72
+ "epoch": 2.0,
73
+ "eval_accuracy": 1.0,
74
+ "eval_f1": 1.0,
75
+ "eval_loss": 1.0265763194183819e-05,
76
+ "eval_precision": 1.0,
77
+ "eval_recall": 1.0,
78
+ "eval_runtime": 1.1652,
79
+ "eval_samples_per_second": 3261.207,
80
+ "eval_steps_per_second": 204.255,
81
+ "step": 4276
82
+ },
83
+ {
84
+ "epoch": 2.1,
85
+ "learning_rate": 1.0064580228514655e-05,
86
+ "loss": 0.0,
87
+ "step": 4500
88
+ },
89
+ {
90
+ "epoch": 2.34,
91
+ "learning_rate": 8.822652757078988e-06,
92
+ "loss": 0.0,
93
+ "step": 5000
94
+ },
95
+ {
96
+ "epoch": 2.57,
97
+ "learning_rate": 7.580725285643319e-06,
98
+ "loss": 0.0,
99
+ "step": 5500
100
+ },
101
+ {
102
+ "epoch": 2.81,
103
+ "learning_rate": 6.338797814207651e-06,
104
+ "loss": 0.0,
105
+ "step": 6000
106
+ },
107
+ {
108
+ "epoch": 3.0,
109
+ "eval_accuracy": 1.0,
110
+ "eval_f1": 1.0,
111
+ "eval_loss": 3.873569767165463e-06,
112
+ "eval_precision": 1.0,
113
+ "eval_recall": 1.0,
114
+ "eval_runtime": 1.1741,
115
+ "eval_samples_per_second": 3236.562,
116
+ "eval_steps_per_second": 202.711,
117
+ "step": 6414
118
+ }
119
+ ],
120
+ "logging_steps": 500,
121
+ "max_steps": 8552,
122
+ "num_train_epochs": 4,
123
+ "save_steps": 500,
124
+ "total_flos": 285137632903152.0,
125
+ "trial_name": null,
126
+ "trial_params": null
127
+ }
checkpoint-6414/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a067afdd27f1ad2f727fe17e38b0dc1e79b5b70ee8f9258f1cbc6a3f4da54b
3
+ size 4472
checkpoint-6414/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../original",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "AskLink",
14
+ "1": "AskLocation",
15
+ "2": "AskRealness",
16
+ "3": "AskToMeet",
17
+ "4": "DeepOrPhilosophical",
18
+ "5": "EmotionalNeed",
19
+ "6": "FallbackUnknown",
20
+ "7": "Flirt",
21
+ "8": "Greeting",
22
+ "9": "IdleOrGhosting",
23
+ "10": "RefuseOnlyFans",
24
+ "11": "RequestPic",
25
+ "12": "SmallTalk",
26
+ "13": "SuccessfulSub",
27
+ "14": "UserBusyOrDelay",
28
+ "15": "UserInsultOrHate",
29
+ "16": "UserNoMoney",
30
+ "17": "UserShynessOrDoubt",
31
+ "18": "UserTestingBot"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "label2id": {
35
+ "AskLink": 0,
36
+ "AskLocation": 1,
37
+ "AskRealness": 2,
38
+ "AskToMeet": 3,
39
+ "DeepOrPhilosophical": 4,
40
+ "EmotionalNeed": 5,
41
+ "FallbackUnknown": 6,
42
+ "Flirt": 7,
43
+ "Greeting": 8,
44
+ "IdleOrGhosting": 9,
45
+ "RefuseOnlyFans": 10,
46
+ "RequestPic": 11,
47
+ "SmallTalk": 12,
48
+ "SuccessfulSub": 13,
49
+ "UserBusyOrDelay": 14,
50
+ "UserInsultOrHate": 15,
51
+ "UserNoMoney": 16,
52
+ "UserShynessOrDoubt": 17,
53
+ "UserTestingBot": 18
54
+ },
55
+ "max_position_embeddings": 512,
56
+ "model_type": "distilbert",
57
+ "n_heads": 12,
58
+ "n_layers": 6,
59
+ "output_past": true,
60
+ "pad_token_id": 0,
61
+ "qa_dropout": 0.1,
62
+ "seq_classif_dropout": 0.2,
63
+ "sinusoidal_pos_embds": false,
64
+ "tie_weights_": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.34.0",
67
+ "vocab_size": 30522
68
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd9d818c7fc21a559921a108653bb843d350efcaf54c30af3744400c4848d83
3
+ size 267908266
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a067afdd27f1ad2f727fe17e38b0dc1e79b5b70ee8f9258f1cbc6a3f4da54b
3
+ size 4472
vocab.txt ADDED
The diff for this file is too large to render. See raw diff