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
c2ae5b2
·
verified ·
1 Parent(s): 8ff3984

Training in progress, epoch 1

Browse files
Files changed (34) hide show
  1. logs/events.out.tfevents.1709877562.6c1c016b0e3e.7263.13 +2 -2
  2. logs/events.out.tfevents.1709878119.6c1c016b0e3e.7263.14 +3 -0
  3. logs/events.out.tfevents.1709878231.6c1c016b0e3e.7263.15 +3 -0
  4. logs/events.out.tfevents.1709878343.6c1c016b0e3e.7263.16 +3 -0
  5. model.safetensors +1 -1
  6. run-13/checkpoint-144/config.json +34 -0
  7. run-13/checkpoint-144/model.safetensors +3 -0
  8. run-13/checkpoint-144/optimizer.pt +3 -0
  9. run-13/checkpoint-144/rng_state.pth +3 -0
  10. run-13/checkpoint-144/scheduler.pt +3 -0
  11. run-13/checkpoint-144/special_tokens_map.json +7 -0
  12. run-13/checkpoint-144/tokenizer.json +0 -0
  13. run-13/checkpoint-144/tokenizer_config.json +57 -0
  14. run-13/checkpoint-144/trainer_state.json +83 -0
  15. run-13/checkpoint-144/training_args.bin +3 -0
  16. run-13/checkpoint-144/vocab.txt +0 -0
  17. run-13/checkpoint-192/model.safetensors +1 -1
  18. run-13/checkpoint-192/optimizer.pt +1 -1
  19. run-13/checkpoint-192/rng_state.pth +1 -1
  20. run-13/checkpoint-192/scheduler.pt +1 -1
  21. run-13/checkpoint-192/trainer_state.json +72 -34
  22. run-13/checkpoint-192/training_args.bin +1 -1
  23. run-16/checkpoint-48/config.json +34 -0
  24. run-16/checkpoint-48/model.safetensors +3 -0
  25. run-16/checkpoint-48/optimizer.pt +3 -0
  26. run-16/checkpoint-48/rng_state.pth +3 -0
  27. run-16/checkpoint-48/scheduler.pt +3 -0
  28. run-16/checkpoint-48/special_tokens_map.json +7 -0
  29. run-16/checkpoint-48/tokenizer.json +0 -0
  30. run-16/checkpoint-48/tokenizer_config.json +57 -0
  31. run-16/checkpoint-48/trainer_state.json +45 -0
  32. run-16/checkpoint-48/training_args.bin +3 -0
  33. run-16/checkpoint-48/vocab.txt +0 -0
  34. training_args.bin +1 -1
logs/events.out.tfevents.1709877562.6c1c016b0e3e.7263.13 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91c483dc72c731ee5889006b2c0f509bfa33e8b4ab3bf1638c87259a5275cea8
3
- size 5984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:238932615ff54ac732b6f0c623a1a2678b6e3c31b8380732d3bbf4ba03c5d586
3
+ size 8033
logs/events.out.tfevents.1709878119.6c1c016b0e3e.7263.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad1704a03da4499688d1fe76ffee047829203c34b168160bac859f785d1611f
3
+ size 5314
logs/events.out.tfevents.1709878231.6c1c016b0e3e.7263.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d83f054ad12aae91567323c292bf4317c344c08740d980b24649b47de4050c
3
+ size 5314
logs/events.out.tfevents.1709878343.6c1c016b0e3e.7263.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66fbe2b30759a779431ee345986991f1ca9078664ae104ce5b1254f2249647b
3
+ size 5315
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:151aa3a5749cce0a8f07d90fcdbe0fa6d0a63b3a7060e683aa6d311b63a5a579
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6686bb2537fd44affb628e87f3476f2ed8535e617f7a8a0d48ddbc9d84f18e28
3
  size 17549312
run-13/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-13/checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499f49a8c19334c74d177a7e44d347395b423487a827dce2d7160301daeba914
3
+ size 17549312
run-13/checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78891b05fa6ab01527f52a426a44393992687eaeea95cf856f3906de0d098c10
3
+ size 35122746
run-13/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-13/checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261c86b5a17c7050a47980283063fa6b7a897b962a1d89c661607ad5cd5dbd78
3
+ size 1064
run-13/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-13/checkpoint-144/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/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-13/checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8091976516634051,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/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": 1.1932880878448486,
14
+ "learning_rate": 0.00031905315423317427,
15
+ "loss": 0.5324,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7514677103718199,
21
+ "eval_f1": 0.7897350993377483,
22
+ "eval_loss": 0.4841874837875366,
23
+ "eval_precision": 0.6843615494978479,
24
+ "eval_recall": 0.9334637964774951,
25
+ "eval_runtime": 27.3845,
26
+ "eval_samples_per_second": 37.32,
27
+ "eval_steps_per_second": 0.584,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 5.759732723236084,
33
+ "learning_rate": 0.0002552425233865394,
34
+ "loss": 0.4624,
35
+ "step": 96
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.7720156555772995,
40
+ "eval_f1": 0.762487257900102,
41
+ "eval_loss": 0.43731480836868286,
42
+ "eval_precision": 0.7957446808510639,
43
+ "eval_recall": 0.7318982387475538,
44
+ "eval_runtime": 27.3758,
45
+ "eval_samples_per_second": 37.332,
46
+ "eval_steps_per_second": 0.584,
47
+ "step": 96
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 1.5165303945541382,
52
+ "learning_rate": 0.00019143189253990455,
53
+ "loss": 0.4346,
54
+ "step": 144
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8091976516634051,
59
+ "eval_f1": 0.8133971291866028,
60
+ "eval_loss": 0.4113065004348755,
61
+ "eval_precision": 0.795880149812734,
62
+ "eval_recall": 0.8317025440313112,
63
+ "eval_runtime": 26.8327,
64
+ "eval_samples_per_second": 38.088,
65
+ "eval_steps_per_second": 0.596,
66
+ "step": 144
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 288,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 6,
73
+ "save_steps": 500,
74
+ "total_flos": 707085591840.0,
75
+ "train_batch_size": 64,
76
+ "trial_name": null,
77
+ "trial_params": {
78
+ "alpha": 0.804266474524187,
79
+ "learning_rate": 0.0003828637850798091,
80
+ "num_train_epochs": 6,
81
+ "temperature": 12
82
+ }
83
+ }
run-13/checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f002440cabbefeb4455cfed69099363d2aa36dc476d0817c5f461e40a0d9c304
3
+ size 4920
run-13/checkpoint-144/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-192/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd0d6f8e320436d079f0d7746e19263f92e5a55b0adb2f3f11c8690ae59206c2
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec936bdbd05fce36e04feb9175016a668f2656862e3ebe1e41b08d9b168c218e
3
  size 17549312
run-13/checkpoint-192/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6e74e362199a97483614fe1679a94a8a3c83db96e104ad0fab53fe4e5f2aa6e
3
  size 35122746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d7a984e692c1ceefc8287215564d0a0f0933154db48c4b07e90b01eec7f910
3
  size 35122746
run-13/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-13/checkpoint-192/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1503d94ac99f2a6df5ee52252e91b9f55b6a5a1cc941650a0e87738e07d4c396
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ebf2e2a39f7392b671af90dbfc3dcf5c6d20071895936fbcc160751e900b77
3
  size 1064
run-13/checkpoint-192/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.7954990215264188,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/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": 2.201279878616333,
14
- "learning_rate": 0.00022445268667640978,
15
- "loss": 0.5435,
16
- "step": 96
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.7700587084148728,
21
- "eval_f1": 0.7979363714531386,
22
- "eval_loss": 0.4716385006904602,
23
- "eval_precision": 0.7116564417177914,
24
- "eval_recall": 0.9080234833659491,
25
- "eval_runtime": 24.8269,
26
- "eval_samples_per_second": 41.165,
27
- "eval_steps_per_second": 1.289,
 
 
 
 
 
 
 
28
  "step": 96
29
  },
30
  {
31
  "epoch": 2.0,
32
- "grad_norm": 3.4069817066192627,
33
- "learning_rate": 0.00018704390556367485,
34
- "loss": 0.4642,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  "step": 192
36
  },
37
  {
38
- "epoch": 2.0,
39
- "eval_accuracy": 0.7954990215264188,
40
- "eval_f1": 0.819047619047619,
41
- "eval_loss": 0.4382912516593933,
42
- "eval_precision": 0.734472049689441,
43
- "eval_recall": 0.9256360078277887,
44
- "eval_runtime": 25.9254,
45
- "eval_samples_per_second": 39.421,
46
- "eval_steps_per_second": 1.234,
47
  "step": 192
48
  }
49
  ],
50
  "logging_steps": 500,
51
- "max_steps": 672,
52
  "num_input_tokens_seen": 0,
53
- "num_train_epochs": 7,
54
  "save_steps": 500,
55
- "total_flos": 471390394560.0,
56
- "train_batch_size": 32,
57
  "trial_name": null,
58
  "trial_params": {
59
- "alpha": 0.8348768037192943,
60
- "learning_rate": 0.0002618614677891448,
61
- "num_train_epochs": 7,
62
- "temperature": 10
63
  }
64
  }
 
1
  {
2
+ "best_metric": 0.8160469667318982,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/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": 1.1932880878448486,
14
+ "learning_rate": 0.00031905315423317427,
15
+ "loss": 0.5324,
16
+ "step": 48
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.7514677103718199,
21
+ "eval_f1": 0.7897350993377483,
22
+ "eval_loss": 0.4841874837875366,
23
+ "eval_precision": 0.6843615494978479,
24
+ "eval_recall": 0.9334637964774951,
25
+ "eval_runtime": 27.3845,
26
+ "eval_samples_per_second": 37.32,
27
+ "eval_steps_per_second": 0.584,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 5.759732723236084,
33
+ "learning_rate": 0.0002552425233865394,
34
+ "loss": 0.4624,
35
  "step": 96
36
  },
37
  {
38
  "epoch": 2.0,
39
+ "eval_accuracy": 0.7720156555772995,
40
+ "eval_f1": 0.762487257900102,
41
+ "eval_loss": 0.43731480836868286,
42
+ "eval_precision": 0.7957446808510639,
43
+ "eval_recall": 0.7318982387475538,
44
+ "eval_runtime": 27.3758,
45
+ "eval_samples_per_second": 37.332,
46
+ "eval_steps_per_second": 0.584,
47
+ "step": 96
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 1.5165303945541382,
52
+ "learning_rate": 0.00019143189253990455,
53
+ "loss": 0.4346,
54
+ "step": 144
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8091976516634051,
59
+ "eval_f1": 0.8133971291866028,
60
+ "eval_loss": 0.4113065004348755,
61
+ "eval_precision": 0.795880149812734,
62
+ "eval_recall": 0.8317025440313112,
63
+ "eval_runtime": 26.8327,
64
+ "eval_samples_per_second": 38.088,
65
+ "eval_steps_per_second": 0.596,
66
+ "step": 144
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 2.3469491004943848,
71
+ "learning_rate": 0.0001276212616932697,
72
+ "loss": 0.4143,
73
  "step": 192
74
  },
75
  {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8160469667318982,
78
+ "eval_f1": 0.821969696969697,
79
+ "eval_loss": 0.39889204502105713,
80
+ "eval_precision": 0.7963302752293578,
81
+ "eval_recall": 0.8493150684931506,
82
+ "eval_runtime": 27.0864,
83
+ "eval_samples_per_second": 37.731,
84
+ "eval_steps_per_second": 0.591,
85
  "step": 192
86
  }
87
  ],
88
  "logging_steps": 500,
89
+ "max_steps": 288,
90
  "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 6,
92
  "save_steps": 500,
93
+ "total_flos": 942780789120.0,
94
+ "train_batch_size": 64,
95
  "trial_name": null,
96
  "trial_params": {
97
+ "alpha": 0.804266474524187,
98
+ "learning_rate": 0.0003828637850798091,
99
+ "num_train_epochs": 6,
100
+ "temperature": 12
101
  }
102
  }
run-13/checkpoint-192/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c39a4a57a6152c8ee182f392094f81926b25a2790f096406761336357b2e5950
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f002440cabbefeb4455cfed69099363d2aa36dc476d0817c5f461e40a0d9c304
3
  size 4920
run-16/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-16/checkpoint-48/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6686bb2537fd44affb628e87f3476f2ed8535e617f7a8a0d48ddbc9d84f18e28
3
+ size 17549312
run-16/checkpoint-48/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15221e2a6612c9e696caa8a60fe4986e460fa3b75e6ae0b44a8d9efd4869598
3
+ size 35122746
run-16/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-16/checkpoint-48/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119f265e7238eae1cff9a34e945a918882ac8a8097616f0e190f6b07bf0ecbe6
3
+ size 1064
run-16/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-16/checkpoint-48/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/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-16/checkpoint-48/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.700587084148728,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/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": 1.2878928184509277,
14
+ "learning_rate": 0.00013115653902338105,
15
+ "loss": 0.4962,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.700587084148728,
21
+ "eval_f1": 0.662251655629139,
22
+ "eval_loss": 0.4426267147064209,
23
+ "eval_precision": 0.759493670886076,
24
+ "eval_recall": 0.5870841487279843,
25
+ "eval_runtime": 27.3,
26
+ "eval_samples_per_second": 37.436,
27
+ "eval_steps_per_second": 0.586,
28
+ "step": 48
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 384,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 8,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 64,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.6758158495370239,
41
+ "learning_rate": 0.00014989318745529262,
42
+ "num_train_epochs": 8,
43
+ "temperature": 20
44
+ }
45
+ }
run-16/checkpoint-48/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63572106dff22a09912a371bd397d01ccf0c92ef49dec03568516e174c66f6b6
3
+ size 4920
run-16/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:f002440cabbefeb4455cfed69099363d2aa36dc476d0817c5f461e40a0d9c304
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63572106dff22a09912a371bd397d01ccf0c92ef49dec03568516e174c66f6b6
3
  size 4920