Hugging Face's logo

agvidit1
/
distilbert-hate_speech18

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
agvidit1 commited on
Commit
d78cd3a
·
1 Parent(s): 18df8f0

Training in progress, epoch 1

Browse files
Files changed (32) hide show
  1. config.json +2 -14
  2. logs/events.out.tfevents.1702105708.tron63.umiacs.umd.edu +2 -2
  3. logs/events.out.tfevents.1702106188.tron63.umiacs.umd.edu +3 -0
  4. logs/events.out.tfevents.1702106526.tron63.umiacs.umd.edu +3 -0
  5. model.safetensors +2 -2
  6. run-0/checkpoint-1440/config.json +37 -0
  7. run-0/checkpoint-1440/model.safetensors +3 -0
  8. run-0/checkpoint-1440/optimizer.pt +3 -0
  9. run-0/checkpoint-1440/rng_state.pth +3 -0
  10. run-0/checkpoint-1440/scheduler.pt +3 -0
  11. run-0/checkpoint-1440/special_tokens_map.json +37 -0
  12. run-0/checkpoint-1440/tokenizer_config.json +57 -0
  13. run-0/checkpoint-1440/trainer_state.json +116 -0
  14. run-0/checkpoint-1440/training_args.bin +3 -0
  15. run-0/checkpoint-1440/vocab.txt +0 -0
  16. run-0/checkpoint-1920/config.json +37 -0
  17. run-0/checkpoint-1920/model.safetensors +3 -0
  18. run-0/checkpoint-1920/optimizer.pt +3 -0
  19. run-0/checkpoint-1920/rng_state.pth +3 -0
  20. run-0/checkpoint-1920/scheduler.pt +3 -0
  21. run-0/checkpoint-1920/special_tokens_map.json +37 -0
  22. run-0/checkpoint-1920/tokenizer_config.json +57 -0
  23. run-0/checkpoint-1920/trainer_state.json +146 -0
  24. run-0/checkpoint-1920/training_args.bin +3 -0
  25. run-0/checkpoint-1920/vocab.txt +0 -0
  26. run-1/checkpoint-240/model.safetensors +1 -1
  27. run-1/checkpoint-240/optimizer.pt +1 -1
  28. run-1/checkpoint-240/rng_state.pth +2 -2
  29. run-1/checkpoint-240/scheduler.pt +1 -1
  30. run-1/checkpoint-240/trainer_state.json +13 -11
  31. run-1/checkpoint-240/training_args.bin +1 -1
  32. training_args.bin +1 -1
config.json CHANGED
@@ -2,17 +2,12 @@
2
  "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
3
  "activation": "gelu",
4
  "architectures": [
5
- "BertForSequenceClassification"
6
  ],
7
  "attention_dropout": 0.1,
8
- "attention_probs_dropout_prob": 0.1,
9
- "classifier_dropout": null,
10
  "dim": 768,
11
  "dropout": 0.1,
12
- "hidden_act": "gelu",
13
  "hidden_dim": 3072,
14
- "hidden_dropout_prob": 0.1,
15
- "hidden_size": 768,
16
  "id2label": {
17
  "0": "noHate",
18
  "1": "hate",
@@ -20,22 +15,17 @@
20
  "3": "relation"
21
  },
22
  "initializer_range": 0.02,
23
- "intermediate_size": 3072,
24
  "label2id": {
25
  "hate": "1",
26
  "idk/skip": "2",
27
  "noHate": "0",
28
  "relation": "3"
29
  },
30
- "layer_norm_eps": 1e-12,
31
  "max_position_embeddings": 512,
32
- "model_type": "bert",
33
  "n_heads": 12,
34
  "n_layers": 6,
35
- "num_attention_heads": 12,
36
- "num_hidden_layers": 12,
37
  "pad_token_id": 0,
38
- "position_embedding_type": "absolute",
39
  "problem_type": "single_label_classification",
40
  "qa_dropout": 0.1,
41
  "seq_classif_dropout": 0.2,
@@ -43,7 +33,5 @@
43
  "tie_weights_": true,
44
  "torch_dtype": "float32",
45
  "transformers_version": "4.35.2",
46
- "type_vocab_size": 2,
47
- "use_cache": true,
48
  "vocab_size": 30522
49
  }
 
2
  "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
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": "noHate",
13
  "1": "hate",
 
15
  "3": "relation"
16
  },
17
  "initializer_range": 0.02,
 
18
  "label2id": {
19
  "hate": "1",
20
  "idk/skip": "2",
21
  "noHate": "0",
22
  "relation": "3"
23
  },
 
24
  "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
  "n_heads": 12,
27
  "n_layers": 6,
 
 
28
  "pad_token_id": 0,
 
29
  "problem_type": "single_label_classification",
30
  "qa_dropout": 0.1,
31
  "seq_classif_dropout": 0.2,
 
33
  "tie_weights_": true,
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.35.2",
 
 
36
  "vocab_size": 30522
37
  }
logs/events.out.tfevents.1702105708.tron63.umiacs.umd.edu CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e992d3dfe65d6766c6b7d3ac6350018c80f21750e5f2cd52f497869818db9d27
3
- size 7199
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0808a2954df0f32459dd795104b06f392d44c4ce82cf575c5ec24ed24c1e5262
3
+ size 8356
logs/events.out.tfevents.1702106188.tron63.umiacs.umd.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6e871daf3108ba2352dc645853944a216e486a0faba3c2747391b65960fe27
3
+ size 8516
logs/events.out.tfevents.1702106526.tron63.umiacs.umd.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfbe9f86228d76534e06d35b6fe65e9120df7dbf8be7a0e814b1ad3a37a01c35
3
+ size 4479
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ae35fe12a79fe903df917f7a179907bd3a6e97c27423c48bf851db059a7649c
3
- size 437964800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73537d7997df9458560070a80179a5a41ac15d2e6ba5e22fc9a7bd887ab6505
3
+ size 267838720
run-0/checkpoint-1440/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
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": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "hate": "1",
20
+ "idk/skip": "2",
21
+ "noHate": "0",
22
+ "relation": "3"
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "pad_token_id": 0,
29
+ "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.35.2",
36
+ "vocab_size": 30522
37
+ }
run-0/checkpoint-1440/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1bc0a979ae387f41958297792851e54b66268ad21bea3481105a7b3cde85022
3
+ size 267838720
run-0/checkpoint-1440/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f4122971e79be3503dd0a978964b7ecc2922f2cf7adbf199d1caeda930fdc5
3
+ size 535739578
run-0/checkpoint-1440/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb1288b64ff1a5b3bac8d30c872d6ab3ae969d3da3f856bad40dd7f07088225
3
+ size 14308
run-0/checkpoint-1440/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ad0e0f6f76c214a47a4ecca85378c89f230f9121ebd7e6ab6ca3a1383fddc2
3
+ size 1064
run-0/checkpoint-1440/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-0/checkpoint-1440/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-0/checkpoint-1440/trainer_state.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8925959780621572,
3
+ "best_model_checkpoint": "distilbert-hate_speech18/run-0/checkpoint-1440",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1440,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 9.613280674880518e-06,
14
+ "loss": 0.4875,
15
+ "step": 240
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8903107861060329,
20
+ "eval_loss": 0.46170517802238464,
21
+ "eval_runtime": 5.6023,
22
+ "eval_samples_per_second": 390.556,
23
+ "eval_steps_per_second": 12.316,
24
+ "step": 240
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 8.239954864183301e-06,
29
+ "loss": 0.4434,
30
+ "step": 480
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8893967093235832,
35
+ "eval_loss": 0.46410441398620605,
36
+ "eval_runtime": 5.3073,
37
+ "eval_samples_per_second": 412.263,
38
+ "eval_steps_per_second": 13.001,
39
+ "step": 480
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 6.866629053486084e-06,
44
+ "loss": 0.4205,
45
+ "step": 720
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8884826325411335,
50
+ "eval_loss": 0.4671436846256256,
51
+ "eval_runtime": 5.3438,
52
+ "eval_samples_per_second": 409.444,
53
+ "eval_steps_per_second": 12.912,
54
+ "step": 720
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 5.493303242788867e-06,
59
+ "loss": 0.4088,
60
+ "step": 960
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8871115173674589,
65
+ "eval_loss": 0.47038260102272034,
66
+ "eval_runtime": 5.4107,
67
+ "eval_samples_per_second": 404.383,
68
+ "eval_steps_per_second": 12.752,
69
+ "step": 960
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 4.1199774320916505e-06,
74
+ "loss": 0.4001,
75
+ "step": 1200
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8861974405850092,
80
+ "eval_loss": 0.4723927080631256,
81
+ "eval_runtime": 5.3255,
82
+ "eval_samples_per_second": 410.857,
83
+ "eval_steps_per_second": 12.957,
84
+ "step": 1200
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 2.7466516213944336e-06,
89
+ "loss": 0.3936,
90
+ "step": 1440
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8925959780621572,
95
+ "eval_loss": 0.47667697072029114,
96
+ "eval_runtime": 5.2992,
97
+ "eval_samples_per_second": 412.893,
98
+ "eval_steps_per_second": 13.021,
99
+ "step": 1440
100
+ }
101
+ ],
102
+ "logging_steps": 500,
103
+ "max_steps": 1920,
104
+ "num_train_epochs": 8,
105
+ "save_steps": 500,
106
+ "total_flos": 977555265925056.0,
107
+ "trial_name": null,
108
+ "trial_params": {
109
+ "alpha": 0.6052303340139199,
110
+ "learning_rate": 1.0986606485577735e-05,
111
+ "num_train_epochs": 8,
112
+ "per_device_eval_batch_size": 32,
113
+ "per_device_train_batch_size": 32,
114
+ "temperature": 6
115
+ }
116
+ }
run-0/checkpoint-1440/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcde4b334fdc297fe0315e07b77f2327253af98126e5c7b8537298826a536bbc
3
+ size 4664
run-0/checkpoint-1440/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-1920/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
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": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "hate": "1",
20
+ "idk/skip": "2",
21
+ "noHate": "0",
22
+ "relation": "3"
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "pad_token_id": 0,
29
+ "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.35.2",
36
+ "vocab_size": 30522
37
+ }
run-0/checkpoint-1920/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8005388865f21acbb26a8e212822d2f894e4c65265191cd2b4267b5c466a69b9
3
+ size 267838720
run-0/checkpoint-1920/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd44c5f696da86b5a38196dc6487e6da683ac3866f347e2a06003de79f5732e9
3
+ size 535739578
run-0/checkpoint-1920/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f656a4d2ae111286eda9679f9946c605a00fa50692b20c142629dc08891a5aba
3
+ size 14308
run-0/checkpoint-1920/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24d9f09126f0d8248c6f716ab4687ec7d6f6ea528cbb0477f731525e95c68339
3
+ size 1064
run-0/checkpoint-1920/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-0/checkpoint-1920/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-0/checkpoint-1920/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8925959780621572,
3
+ "best_model_checkpoint": "distilbert-hate_speech18/run-0/checkpoint-1440",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1920,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 9.613280674880518e-06,
14
+ "loss": 0.4875,
15
+ "step": 240
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8903107861060329,
20
+ "eval_loss": 0.46170517802238464,
21
+ "eval_runtime": 5.6023,
22
+ "eval_samples_per_second": 390.556,
23
+ "eval_steps_per_second": 12.316,
24
+ "step": 240
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 8.239954864183301e-06,
29
+ "loss": 0.4434,
30
+ "step": 480
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8893967093235832,
35
+ "eval_loss": 0.46410441398620605,
36
+ "eval_runtime": 5.3073,
37
+ "eval_samples_per_second": 412.263,
38
+ "eval_steps_per_second": 13.001,
39
+ "step": 480
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 6.866629053486084e-06,
44
+ "loss": 0.4205,
45
+ "step": 720
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8884826325411335,
50
+ "eval_loss": 0.4671436846256256,
51
+ "eval_runtime": 5.3438,
52
+ "eval_samples_per_second": 409.444,
53
+ "eval_steps_per_second": 12.912,
54
+ "step": 720
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 5.493303242788867e-06,
59
+ "loss": 0.4088,
60
+ "step": 960
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8871115173674589,
65
+ "eval_loss": 0.47038260102272034,
66
+ "eval_runtime": 5.4107,
67
+ "eval_samples_per_second": 404.383,
68
+ "eval_steps_per_second": 12.752,
69
+ "step": 960
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 4.1199774320916505e-06,
74
+ "loss": 0.4001,
75
+ "step": 1200
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8861974405850092,
80
+ "eval_loss": 0.4723927080631256,
81
+ "eval_runtime": 5.3255,
82
+ "eval_samples_per_second": 410.857,
83
+ "eval_steps_per_second": 12.957,
84
+ "step": 1200
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 2.7466516213944336e-06,
89
+ "loss": 0.3936,
90
+ "step": 1440
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8925959780621572,
95
+ "eval_loss": 0.47667697072029114,
96
+ "eval_runtime": 5.2992,
97
+ "eval_samples_per_second": 412.893,
98
+ "eval_steps_per_second": 13.021,
99
+ "step": 1440
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 1.3733258106972168e-06,
104
+ "loss": 0.3908,
105
+ "step": 1680
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8884826325411335,
110
+ "eval_loss": 0.47796693444252014,
111
+ "eval_runtime": 5.3385,
112
+ "eval_samples_per_second": 409.852,
113
+ "eval_steps_per_second": 12.925,
114
+ "step": 1680
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 0.0,
119
+ "loss": 0.3877,
120
+ "step": 1920
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8884826325411335,
125
+ "eval_loss": 0.4775611460208893,
126
+ "eval_runtime": 5.4926,
127
+ "eval_samples_per_second": 398.354,
128
+ "eval_steps_per_second": 12.562,
129
+ "step": 1920
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 1920,
134
+ "num_train_epochs": 8,
135
+ "save_steps": 500,
136
+ "total_flos": 1306917187523808.0,
137
+ "trial_name": null,
138
+ "trial_params": {
139
+ "alpha": 0.6052303340139199,
140
+ "learning_rate": 1.0986606485577735e-05,
141
+ "num_train_epochs": 8,
142
+ "per_device_eval_batch_size": 32,
143
+ "per_device_train_batch_size": 32,
144
+ "temperature": 6
145
+ }
146
+ }
run-0/checkpoint-1920/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcde4b334fdc297fe0315e07b77f2327253af98126e5c7b8537298826a536bbc
3
+ size 4664
run-0/checkpoint-1920/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-240/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebfddde93807f948334ad5c293fbfd78568a487d880194d4c88cdda08728a2a5
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73537d7997df9458560070a80179a5a41ac15d2e6ba5e22fc9a7bd887ab6505
3
  size 267838720
run-1/checkpoint-240/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e967f79e90f0fa5a6dc3c5e68c94e958a361e553bee31c09810b619bef9fd906
3
  size 535739578
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23cf1274bef1fa6d39d4ba932477938e9bd130f00d3b3be8a5f637f3a5b73558
3
  size 535739578
run-1/checkpoint-240/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcfb469108f4fe42dfbf056bdbb073c67246d11e797340929b1acdbb801a8afe
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082855662849cb813f628cb5b8a89eade0ed624c4f3190fa908581277e77b52b
3
+ size 14308
run-1/checkpoint-240/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:795f6ca89ebe56910e4cca4ea5d3dea06f640c55d35a40638ebc1a94f679694a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f7e38f1f4103ca3e5dba0bb0b2519b69356b865e47b99876a8126fcbb44f43
3
  size 1064
run-1/checkpoint-240/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.8555758683729433,
3
  "best_model_checkpoint": "distilbert-hate_speech18/run-1/checkpoint-240",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,17 +10,17 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "learning_rate": 8.685044606939477e-07,
14
- "loss": 0.5038,
15
  "step": 240
16
  },
17
  {
18
  "epoch": 1.0,
19
- "eval_accuracy": 0.8555758683729433,
20
- "eval_loss": 0.46875882148742676,
21
- "eval_runtime": 5.3242,
22
- "eval_samples_per_second": 410.952,
23
- "eval_steps_per_second": 12.96,
24
  "step": 240
25
  }
26
  ],
@@ -28,12 +28,14 @@
28
  "max_steps": 720,
29
  "num_train_epochs": 3,
30
  "save_steps": 500,
31
- "total_flos": 162095167047072.0,
32
  "trial_name": null,
33
  "trial_params": {
34
- "learning_rate": 1.3027566910409216e-06,
 
35
  "num_train_epochs": 3,
 
36
  "per_device_train_batch_size": 32,
37
- "seed": 19
38
  }
39
  }
 
1
  {
2
+ "best_metric": 0.8711151736745887,
3
  "best_model_checkpoint": "distilbert-hate_speech18/run-1/checkpoint-240",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "learning_rate": 0.00016353274034701048,
14
+ "loss": 0.5029,
15
  "step": 240
16
  },
17
  {
18
  "epoch": 1.0,
19
+ "eval_accuracy": 0.8711151736745887,
20
+ "eval_loss": 0.4920285642147064,
21
+ "eval_runtime": 4.6413,
22
+ "eval_samples_per_second": 471.415,
23
+ "eval_steps_per_second": 29.517,
24
  "step": 240
25
  }
26
  ],
 
28
  "max_steps": 720,
29
  "num_train_epochs": 3,
30
  "save_steps": 500,
31
+ "total_flos": 163370211234720.0,
32
  "trial_name": null,
33
  "trial_params": {
34
+ "alpha": 0.7869465445797107,
35
+ "learning_rate": 0.00024529911052051574,
36
  "num_train_epochs": 3,
37
+ "per_device_eval_batch_size": 16,
38
  "per_device_train_batch_size": 32,
39
+ "temperature": 8
40
  }
41
  }
run-1/checkpoint-240/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c666d890baed2eb73a07d44d6ca3b95d5bac3889eca1e29d0fb21a74a77b62d
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5cf8e7a2068df224737fe73e81f82a38099b33d3cb85f661a109ee424e9884b
3
  size 4664
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4abc820b850c9310641fdfe15f571816fe81813a3fbf263e984c08868ff47c73
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5cf8e7a2068df224737fe73e81f82a38099b33d3cb85f661a109ee424e9884b
3
  size 4664