Hugging Face's logo

xuancoblab2023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
90a34dc
·
verified ·
1 Parent(s): b959cee

Training in progress, epoch 1

Browse files
Files changed (32) hide show
  1. logs/events.out.tfevents.1709883981.6c1c016b0e3e.7263.32 +2 -2
  2. logs/events.out.tfevents.1709884441.6c1c016b0e3e.7263.33 +3 -0
  3. model.safetensors +1 -1
  4. run-32/checkpoint-144/config.json +34 -0
  5. run-32/checkpoint-144/model.safetensors +3 -0
  6. run-32/checkpoint-144/optimizer.pt +3 -0
  7. run-32/checkpoint-144/rng_state.pth +3 -0
  8. run-32/checkpoint-144/scheduler.pt +3 -0
  9. run-32/checkpoint-144/special_tokens_map.json +7 -0
  10. run-32/checkpoint-144/tokenizer.json +0 -0
  11. run-32/checkpoint-144/tokenizer_config.json +57 -0
  12. run-32/checkpoint-144/trainer_state.json +83 -0
  13. run-32/checkpoint-144/training_args.bin +3 -0
  14. run-32/checkpoint-144/vocab.txt +0 -0
  15. run-32/checkpoint-192/model.safetensors +1 -1
  16. run-32/checkpoint-192/optimizer.pt +1 -1
  17. run-32/checkpoint-192/rng_state.pth +1 -1
  18. run-32/checkpoint-192/scheduler.pt +1 -1
  19. run-32/checkpoint-192/trainer_state.json +72 -34
  20. run-32/checkpoint-192/training_args.bin +1 -1
  21. run-33/checkpoint-48/config.json +34 -0
  22. run-33/checkpoint-48/model.safetensors +3 -0
  23. run-33/checkpoint-48/optimizer.pt +3 -0
  24. run-33/checkpoint-48/rng_state.pth +3 -0
  25. run-33/checkpoint-48/scheduler.pt +3 -0
  26. run-33/checkpoint-48/special_tokens_map.json +7 -0
  27. run-33/checkpoint-48/tokenizer.json +0 -0
  28. run-33/checkpoint-48/tokenizer_config.json +57 -0
  29. run-33/checkpoint-48/trainer_state.json +45 -0
  30. run-33/checkpoint-48/training_args.bin +3 -0
  31. run-33/checkpoint-48/vocab.txt +0 -0
  32. training_args.bin +1 -1
logs/events.out.tfevents.1709883981.6c1c016b0e3e.7263.32 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d965583deee1b0a6c1dc62d101c45f1c2a1dc755bcd2dd6fee0149eea0655aa8
3
- size 5985
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494dd0641746a1f73e05872a12b758a572e897fd19199b41b7364bb5a66324d1
3
+ size 7705
logs/events.out.tfevents.1709884441.6c1c016b0e3e.7263.33 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec778dbbe55c07bda3ac658bcdc0a31429273a9925f03fd579dac8eb78ca6ff
3
+ size 5315
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43d3503823ef2bcbe38ff878357c431f28b985ea22543733c85d57ebc5cebde2
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56218f772328f5c26a9e20dba2e720b46b270c6093f3e718bcd0a5f543007533
3
  size 17549312
run-32/checkpoint-144/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-32/checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7ad2189185cac18cfa5bd4b7f97eddec5a99609d9bcfbe43a94fb37c985fed
3
+ size 17549312
run-32/checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223398384961b9ba95c9ce8790dcfa651d4cf8d4d4eaf951269d665821006150
3
+ size 35122746
run-32/checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117413c2e4c616775c2a2540a012ac63a1e136326812b679f4206af03d68f7d5
3
+ size 14054
run-32/checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78b2c41c8c6837b7d592c6dd8344718c9f9a30f01205f7e6c7eb243a4757e54
3
+ size 1064
run-32/checkpoint-144/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
+ }
run-32/checkpoint-144/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-32/checkpoint-144/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": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-32/checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8287671232876712,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-144",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 144,
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
+ "grad_norm": 1.7776581048965454,
14
+ "learning_rate": 0.000302143376211333,
15
+ "loss": 0.5977,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7455968688845401,
21
+ "eval_f1": 0.7906602254428341,
22
+ "eval_loss": 0.5077403783798218,
23
+ "eval_precision": 0.6716826265389877,
24
+ "eval_recall": 0.9608610567514677,
25
+ "eval_runtime": 27.3787,
26
+ "eval_samples_per_second": 37.328,
27
+ "eval_steps_per_second": 0.584,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 9.869495391845703,
33
+ "learning_rate": 0.00020142891747422203,
34
+ "loss": 0.4879,
35
+ "step": 96
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8052837573385518,
40
+ "eval_f1": 0.8062317429406036,
41
+ "eval_loss": 0.45489782094955444,
42
+ "eval_precision": 0.8023255813953488,
43
+ "eval_recall": 0.8101761252446184,
44
+ "eval_runtime": 27.3555,
45
+ "eval_samples_per_second": 37.36,
46
+ "eval_steps_per_second": 0.585,
47
+ "step": 96
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 4.101070880889893,
52
+ "learning_rate": 0.00010071445873711101,
53
+ "loss": 0.4431,
54
+ "step": 144
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8287671232876712,
59
+ "eval_f1": 0.8381128584643849,
60
+ "eval_loss": 0.4164314568042755,
61
+ "eval_precision": 0.7947368421052632,
62
+ "eval_recall": 0.8864970645792564,
63
+ "eval_runtime": 27.378,
64
+ "eval_samples_per_second": 37.329,
65
+ "eval_steps_per_second": 0.584,
66
+ "step": 144
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 192,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 4,
73
+ "save_steps": 500,
74
+ "total_flos": 707085591840.0,
75
+ "train_batch_size": 64,
76
+ "trial_name": null,
77
+ "trial_params": {
78
+ "alpha": 0.9963289128276592,
79
+ "learning_rate": 0.00040285783494844405,
80
+ "num_train_epochs": 4,
81
+ "temperature": 26
82
+ }
83
+ }
run-32/checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b981331b7e11065eeb20a82cac9e704d68d3e3b85deac08ed79b4a3a2b48e41
3
+ size 4920
run-32/checkpoint-144/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-32/checkpoint-192/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bb00e455b644f9e5927df934270917d43a35fc1f5aaebf45803100174efdd07
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:611d6b49b5327c802b876b52c263405ec7b44184d00f8c014fba296532e62768
3
  size 17549312
run-32/checkpoint-192/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dd9a1aedc49cd047bbeb5183389c14a72ff1533e5f3203dd308f8383d758cb9
3
  size 35122746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25237fa364bdfc1039edf859953278be052f16c1ea23b92c762a2259aae107d3
3
  size 35122746
run-32/checkpoint-192/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
3
  size 14054
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d267b33c0df8c744bb62ca8fc0e243d0ddded8c46ea62639c56f51d1dc7a548
3
  size 14054
run-32/checkpoint-192/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:037ede4c52d494eb4b71cb4e33b62a0a56fb537a14c80f555bc6fa590cb2c636
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f549b04061f7d1b18170dc23c298e5ba7c76408af4a6a4382f4c1732b87482c8
3
  size 1064
run-32/checkpoint-192/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.8072407045009785,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-192",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 192,
7
  "is_hyper_param_search": true,
@@ -10,55 +10,93 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "grad_norm": 1.7263739109039307,
14
- "learning_rate": 0.00011867778606566929,
15
- "loss": 0.5622,
16
- "step": 96
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.7710371819960861,
21
- "eval_f1": 0.8006814310051107,
22
- "eval_loss": 0.4762067198753357,
23
- "eval_precision": 0.7088989441930619,
24
- "eval_recall": 0.9197651663405088,
25
- "eval_runtime": 25.5548,
26
- "eval_samples_per_second": 39.993,
27
- "eval_steps_per_second": 1.252,
 
 
 
 
 
 
 
28
  "step": 96
29
  },
30
  {
31
  "epoch": 2.0,
32
- "grad_norm": 1.8613439798355103,
33
- "learning_rate": 0.00010384306280746064,
34
- "loss": 0.4724,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  "step": 192
36
  },
37
  {
38
- "epoch": 2.0,
39
- "eval_accuracy": 0.8072407045009785,
40
- "eval_f1": 0.8273444347063978,
41
- "eval_loss": 0.43931350111961365,
42
- "eval_precision": 0.7492063492063492,
43
- "eval_recall": 0.923679060665362,
44
- "eval_runtime": 25.0105,
45
- "eval_samples_per_second": 40.863,
46
- "eval_steps_per_second": 1.279,
47
  "step": 192
48
  }
49
  ],
50
  "logging_steps": 500,
51
- "max_steps": 864,
52
  "num_input_tokens_seen": 0,
53
- "num_train_epochs": 9,
54
  "save_steps": 500,
55
- "total_flos": 471390394560.0,
56
- "train_batch_size": 32,
57
  "trial_name": null,
58
  "trial_params": {
59
- "alpha": 0.8475925399213161,
60
- "learning_rate": 0.00013351250932387796,
61
- "num_train_epochs": 9,
62
- "temperature": 10
63
  }
64
  }
 
1
  {
2
+ "best_metric": 0.8317025440313112,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-192",
4
+ "epoch": 4.0,
5
  "eval_steps": 500,
6
  "global_step": 192,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "grad_norm": 1.7776581048965454,
14
+ "learning_rate": 0.000302143376211333,
15
+ "loss": 0.5977,
16
+ "step": 48
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.7455968688845401,
21
+ "eval_f1": 0.7906602254428341,
22
+ "eval_loss": 0.5077403783798218,
23
+ "eval_precision": 0.6716826265389877,
24
+ "eval_recall": 0.9608610567514677,
25
+ "eval_runtime": 27.3787,
26
+ "eval_samples_per_second": 37.328,
27
+ "eval_steps_per_second": 0.584,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 9.869495391845703,
33
+ "learning_rate": 0.00020142891747422203,
34
+ "loss": 0.4879,
35
  "step": 96
36
  },
37
  {
38
  "epoch": 2.0,
39
+ "eval_accuracy": 0.8052837573385518,
40
+ "eval_f1": 0.8062317429406036,
41
+ "eval_loss": 0.45489782094955444,
42
+ "eval_precision": 0.8023255813953488,
43
+ "eval_recall": 0.8101761252446184,
44
+ "eval_runtime": 27.3555,
45
+ "eval_samples_per_second": 37.36,
46
+ "eval_steps_per_second": 0.585,
47
+ "step": 96
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 4.101070880889893,
52
+ "learning_rate": 0.00010071445873711101,
53
+ "loss": 0.4431,
54
+ "step": 144
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8287671232876712,
59
+ "eval_f1": 0.8381128584643849,
60
+ "eval_loss": 0.4164314568042755,
61
+ "eval_precision": 0.7947368421052632,
62
+ "eval_recall": 0.8864970645792564,
63
+ "eval_runtime": 27.378,
64
+ "eval_samples_per_second": 37.329,
65
+ "eval_steps_per_second": 0.584,
66
+ "step": 144
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 4.311736583709717,
71
+ "learning_rate": 0.0,
72
+ "loss": 0.4194,
73
  "step": 192
74
  },
75
  {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8317025440313112,
78
+ "eval_f1": 0.845601436265709,
79
+ "eval_loss": 0.4077454209327698,
80
+ "eval_precision": 0.7810945273631841,
81
+ "eval_recall": 0.9217221135029354,
82
+ "eval_runtime": 27.5799,
83
+ "eval_samples_per_second": 37.056,
84
+ "eval_steps_per_second": 0.58,
85
  "step": 192
86
  }
87
  ],
88
  "logging_steps": 500,
89
+ "max_steps": 192,
90
  "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 4,
92
  "save_steps": 500,
93
+ "total_flos": 942780789120.0,
94
+ "train_batch_size": 64,
95
  "trial_name": null,
96
  "trial_params": {
97
+ "alpha": 0.9963289128276592,
98
+ "learning_rate": 0.00040285783494844405,
99
+ "num_train_epochs": 4,
100
+ "temperature": 26
101
  }
102
  }
run-32/checkpoint-192/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83d69afa7ea349d5580248b9721c10f3b2232803e6d1d873807217055f137bde
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b981331b7e11065eeb20a82cac9e704d68d3e3b85deac08ed79b4a3a2b48e41
3
  size 4920
run-33/checkpoint-48/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-33/checkpoint-48/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56218f772328f5c26a9e20dba2e720b46b270c6093f3e718bcd0a5f543007533
3
+ size 17549312
run-33/checkpoint-48/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4ff82b70ebf68b0e26bca7b1a126f143b5caf9b9a1b54d99eee7788047a099
3
+ size 35122746
run-33/checkpoint-48/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f731098665929ed6a815501631b54240caaac6508207c5c55cf0fe36ad39b17
3
+ size 14054
run-33/checkpoint-48/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c479147503b33419ed92efed8c4c6bfa5fb5978c78e04391e5a5b2ec9ff5942d
3
+ size 1064
run-33/checkpoint-48/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
+ }
run-33/checkpoint-48/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-33/checkpoint-48/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": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-33/checkpoint-48/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7573385518590998,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-33/checkpoint-48",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 48,
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
+ "grad_norm": 1.3328498601913452,
14
+ "learning_rate": 0.0002538644629516305,
15
+ "loss": 0.5508,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7573385518590998,
21
+ "eval_f1": 0.7933333333333334,
22
+ "eval_loss": 0.4848305583000183,
23
+ "eval_precision": 0.690856313497823,
24
+ "eval_recall": 0.9315068493150684,
25
+ "eval_runtime": 27.0185,
26
+ "eval_samples_per_second": 37.826,
27
+ "eval_steps_per_second": 0.592,
28
+ "step": 48
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 144,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 3,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 64,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.8587810819129409,
41
+ "learning_rate": 0.00038079669442744575,
42
+ "num_train_epochs": 3,
43
+ "temperature": 25
44
+ }
45
+ }
run-33/checkpoint-48/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fea57f032e46adee993684d2bb27d6f7241d7a66f7ca178a5e2563440a0887
3
+ size 4920
run-33/checkpoint-48/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 sha256:7b981331b7e11065eeb20a82cac9e704d68d3e3b85deac08ed79b4a3a2b48e41
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fea57f032e46adee993684d2bb27d6f7241d7a66f7ca178a5e2563440a0887
3
  size 4920