Hugging Face's logo

joseph10
/
distilbert-hate_speech18

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
joseph10 commited on
Commit
eec69da
•
1 Parent(s): 1d3bd00

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1702166495.joseph_legion.21448.7 +2 -2
  2. logs/events.out.tfevents.1702168178.joseph_legion.21448.8 +3 -0
  3. logs/events.out.tfevents.1702168240.joseph_legion.21448.9 +3 -0
  4. logs/events.out.tfevents.1702168470.joseph_legion.21448.10 +3 -0
  5. model.safetensors +1 -1
  6. run-6/checkpoint-1920/config.json +37 -0
  7. run-6/checkpoint-1920/model.safetensors +3 -0
  8. run-6/checkpoint-1920/optimizer.pt +3 -0
  9. run-6/checkpoint-1920/rng_state.pth +3 -0
  10. run-6/checkpoint-1920/scheduler.pt +3 -0
  11. run-6/checkpoint-1920/special_tokens_map.json +37 -0
  12. run-6/checkpoint-1920/tokenizer_config.json +57 -0
  13. run-6/checkpoint-1920/trainer_state.json +147 -0
  14. run-6/checkpoint-1920/training_args.bin +3 -0
  15. run-6/checkpoint-1920/vocab.txt +0 -0
  16. run-9/checkpoint-479/config.json +37 -0
  17. run-9/checkpoint-479/model.safetensors +3 -0
  18. run-9/checkpoint-479/optimizer.pt +3 -0
  19. run-9/checkpoint-479/rng_state.pth +3 -0
  20. run-9/checkpoint-479/scheduler.pt +3 -0
  21. run-9/checkpoint-479/special_tokens_map.json +37 -0
  22. run-9/checkpoint-479/tokenizer_config.json +57 -0
  23. run-9/checkpoint-479/trainer_state.json +42 -0
  24. run-9/checkpoint-479/training_args.bin +3 -0
  25. run-9/checkpoint-479/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1702166495.joseph_legion.21448.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1ff709ec6ab9511bf74c5d9665e21da1dd77992b21acf7dea355838a97c0dda
3
- size 7815
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffdc6f5eed0c75b81508163260cb64fa0a224c513552acdc8aba739375638f45
3
+ size 8649
logs/events.out.tfevents.1702168178.joseph_legion.21448.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:491497c98674165614176a58573c6d4786fe6bc23f73b8fb5a34ad4792be5968
3
+ size 4936
logs/events.out.tfevents.1702168240.joseph_legion.21448.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d7a143d76a76ebbccb87eb26b2ac5bdc3176b9aa4f76cc6cea5bdeaa722df48
3
+ size 4935
logs/events.out.tfevents.1702168470.joseph_legion.21448.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b328e648d2e29bacd1d144e0e731b3eaa62485376a79fa12bb62117c38308d4
3
+ size 4935
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7efc57d8c469ab9aed60cd6e695635782d9028046889070b616a2a33b4686051
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa2ee73f8ef5e2aba8dc8552e2c60d53e640beb1de82bde1dd2ef5494cffb85b
3
  size 267838720
run-6/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": 0,
13
+ "1": 1,
14
+ "2": 2,
15
+ "3": 3
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "0": 0,
20
+ "1": 1,
21
+ "2": 2,
22
+ "3": 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": "4.36.0.dev0",
36
+ "vocab_size": 30522
37
+ }
run-6/checkpoint-1920/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1dbb0da9f3e797edd210e64c0394ba8bcc567992aed5c0df85ca1136c23c3a5
3
+ size 267838720
run-6/checkpoint-1920/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b8d3d402c67735968174b8c16510da7dc4ea93fd2e44aef491ffe960c39a225
3
+ size 535739578
run-6/checkpoint-1920/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3944fa5e21d9ab7c62c3e2d7d129a9d71b9e95f302ec40731368b3beda4f45d3
3
+ size 14308
run-6/checkpoint-1920/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b0e5f24cfc806c0420cd021151842d854373a9540661cbb5d56bb10dcb4c10
3
+ size 1064
run-6/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-6/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-6/checkpoint-1920/trainer_state.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8903107861060329,
3
+ "best_model_checkpoint": "distilbert-hate_speech18\\run-6\\checkpoint-1680",
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": 4.4189080485362326e-06,
14
+ "loss": 0.4732,
15
+ "step": 240
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8706581352833638,
20
+ "eval_loss": 0.45438072085380554,
21
+ "eval_runtime": 8.0476,
22
+ "eval_samples_per_second": 271.882,
23
+ "eval_steps_per_second": 17.024,
24
+ "step": 240
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 3.7876354701739137e-06,
29
+ "loss": 0.4459,
30
+ "step": 480
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8857404021937842,
35
+ "eval_loss": 0.4488455057144165,
36
+ "eval_runtime": 7.9963,
37
+ "eval_samples_per_second": 273.628,
38
+ "eval_steps_per_second": 17.133,
39
+ "step": 480
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 3.1563628918115945e-06,
44
+ "loss": 0.4356,
45
+ "step": 720
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8893967093235832,
50
+ "eval_loss": 0.4489736258983612,
51
+ "eval_runtime": 8.1712,
52
+ "eval_samples_per_second": 267.77,
53
+ "eval_steps_per_second": 16.766,
54
+ "step": 720
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 2.5250903134492757e-06,
59
+ "loss": 0.4283,
60
+ "step": 960
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8889396709323584,
65
+ "eval_loss": 0.44683799147605896,
66
+ "eval_runtime": 8.1009,
67
+ "eval_samples_per_second": 270.094,
68
+ "eval_steps_per_second": 16.912,
69
+ "step": 960
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 1.8938177350869569e-06,
74
+ "loss": 0.4229,
75
+ "step": 1200
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8889396709323584,
80
+ "eval_loss": 0.4480336308479309,
81
+ "eval_runtime": 8.1801,
82
+ "eval_samples_per_second": 267.477,
83
+ "eval_steps_per_second": 16.748,
84
+ "step": 1200
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 1.2625451567246378e-06,
89
+ "loss": 0.4196,
90
+ "step": 1440
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8871115173674589,
95
+ "eval_loss": 0.450763076543808,
96
+ "eval_runtime": 8.0343,
97
+ "eval_samples_per_second": 272.332,
98
+ "eval_steps_per_second": 17.052,
99
+ "step": 1440
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 6.312725783623189e-07,
104
+ "loss": 0.4169,
105
+ "step": 1680
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8903107861060329,
110
+ "eval_loss": 0.4496695101261139,
111
+ "eval_runtime": 8.0794,
112
+ "eval_samples_per_second": 270.811,
113
+ "eval_steps_per_second": 16.957,
114
+ "step": 1680
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 0.0,
119
+ "loss": 0.4159,
120
+ "step": 1920
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8898537477148081,
125
+ "eval_loss": 0.4497666656970978,
126
+ "eval_runtime": 8.166,
127
+ "eval_samples_per_second": 267.941,
128
+ "eval_steps_per_second": 16.777,
129
+ "step": 1920
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 1920,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 8,
136
+ "save_steps": 500,
137
+ "total_flos": 1306917187523808.0,
138
+ "trial_name": null,
139
+ "trial_params": {
140
+ "alpha": 0.4787113643124785,
141
+ "learning_rate": 5.050180626898551e-06,
142
+ "num_train_epochs": 8,
143
+ "per_device_eval_batch_size": 16,
144
+ "per_device_train_batch_size": 32,
145
+ "temperature": 27
146
+ }
147
+ }
run-6/checkpoint-1920/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2caa169e337c2cdce989f2ae2edb46d990d83d311ad8d0fa7b6a8a2e8b15c867
3
+ size 4792
run-6/checkpoint-1920/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-479/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": 0,
13
+ "1": 1,
14
+ "2": 2,
15
+ "3": 3
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "0": 0,
20
+ "1": 1,
21
+ "2": 2,
22
+ "3": 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": "4.36.0.dev0",
36
+ "vocab_size": 30522
37
+ }
run-9/checkpoint-479/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa2ee73f8ef5e2aba8dc8552e2c60d53e640beb1de82bde1dd2ef5494cffb85b
3
+ size 267838720
run-9/checkpoint-479/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4083ab2526f5b0ab1076118468d582d8144dbafeeb155660936bdc25cce9257
3
+ size 535739578
run-9/checkpoint-479/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d46f5609acc4df73766b0f33b30656411024250c2f745a536c9e1d5d95ae5105
3
+ size 14308
run-9/checkpoint-479/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256ab8def47e754fd3cb8a86ef05e60f62d9dfe9b109d4ee6787a485ea69156e
3
+ size 1064
run-9/checkpoint-479/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-9/checkpoint-479/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-9/checkpoint-479/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8555758683729433,
3
+ "best_model_checkpoint": "distilbert-hate_speech18\\run-9\\checkpoint-479",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 479,
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": 1.2059359541097392e-06,
14
+ "loss": 0.6218,
15
+ "step": 479
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8555758683729433,
20
+ "eval_loss": 0.5179561376571655,
21
+ "eval_runtime": 9.4907,
22
+ "eval_samples_per_second": 230.542,
23
+ "eval_steps_per_second": 7.27,
24
+ "step": 479
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 1437,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 3,
31
+ "save_steps": 500,
32
+ "total_flos": 128356173120672.0,
33
+ "trial_name": null,
34
+ "trial_params": {
35
+ "alpha": 0.8817369109821054,
36
+ "learning_rate": 1.808903931164609e-06,
37
+ "num_train_epochs": 3,
38
+ "per_device_eval_batch_size": 32,
39
+ "per_device_train_batch_size": 16,
40
+ "temperature": 20
41
+ }
42
+ }
run-9/checkpoint-479/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d867fd6fc4a219ef921faa090af65c09ea1d32483558946d8c240940c28b9f0
3
+ size 4792
run-9/checkpoint-479/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2caa169e337c2cdce989f2ae2edb46d990d83d311ad8d0fa7b6a8a2e8b15c867
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d867fd6fc4a219ef921faa090af65c09ea1d32483558946d8c240940c28b9f0
3
  size 4792