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
f03a0a9
·
verified ·
1 Parent(s): 19cf646

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. logs/events.out.tfevents.1711299118.8cc2eef2edb7.2942.35 +2 -2
  2. logs/events.out.tfevents.1711299157.8cc2eef2edb7.2942.36 +3 -0
  3. logs/events.out.tfevents.1711299176.8cc2eef2edb7.2942.37 +3 -0
  4. logs/events.out.tfevents.1711299196.8cc2eef2edb7.2942.38 +3 -0
  5. logs/events.out.tfevents.1711299216.8cc2eef2edb7.2942.39 +3 -0
  6. logs/events.out.tfevents.1711299235.8cc2eef2edb7.2942.40 +3 -0
  7. logs/events.out.tfevents.1711299255.8cc2eef2edb7.2942.41 +3 -0
  8. model.safetensors +1 -1
  9. run-41/checkpoint-297/config.json +34 -0
  10. run-41/checkpoint-297/model.safetensors +3 -0
  11. run-41/checkpoint-297/optimizer.pt +3 -0
  12. run-41/checkpoint-297/rng_state.pth +3 -0
  13. run-41/checkpoint-297/scheduler.pt +3 -0
  14. run-41/checkpoint-297/special_tokens_map.json +7 -0
  15. run-41/checkpoint-297/tokenizer.json +0 -0
  16. run-41/checkpoint-297/tokenizer_config.json +57 -0
  17. run-41/checkpoint-297/trainer_state.json +46 -0
  18. run-41/checkpoint-297/training_args.bin +3 -0
  19. run-41/checkpoint-297/vocab.txt +0 -0
  20. training_args.bin +1 -1
logs/events.out.tfevents.1711299118.8cc2eef2edb7.2942.35 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c201d741f3f8cd0156d9449ca7d84852e4fe2837f855dc1c8bfdcfca60dc7d7
3
- size 5406
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b6f89b34da1e98e94b1c6bf53beccfe3a9a04ab0b83762579da6153dc950ab
3
+ size 6136
logs/events.out.tfevents.1711299157.8cc2eef2edb7.2942.36 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4496beb646c8c2503ae979a7ca24c4d57293e57c7549720861f002c2ca6a9c3d
3
+ size 5406
logs/events.out.tfevents.1711299176.8cc2eef2edb7.2942.37 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9337bbfc80e9171f316705f600dfe6ea2ec5c27800877a3993343f04ec5af07d
3
+ size 5406
logs/events.out.tfevents.1711299196.8cc2eef2edb7.2942.38 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44cf839bf504dc596ab898454e512d32a74668f989b6aa32b5f5d8f505b430ef
3
+ size 5406
logs/events.out.tfevents.1711299216.8cc2eef2edb7.2942.39 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9ce23667e4e0b11ba3fe8f103638e6eb3cac7ac3be24efc7d2703b38594781
3
+ size 5406
logs/events.out.tfevents.1711299235.8cc2eef2edb7.2942.40 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85099c41bce5df835954fbd157a938e3a1996b2439456ba3eb12a130f84b5518
3
+ size 5406
logs/events.out.tfevents.1711299255.8cc2eef2edb7.2942.41 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:860c8e8c7efe0919ef3c72cdf8414767898c10916f59ed270db28477b5231f64
3
+ size 5407
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adcb77a661aa58bcee1882579f4f446dcd45fd555c27a4d70afe50daafe7f770
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a404c1aa6217252d7412c9ed97914eba2888c959b6bf7243eda627015463c9
3
  size 17549312
run-41/checkpoint-297/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": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-41/checkpoint-297/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a404c1aa6217252d7412c9ed97914eba2888c959b6bf7243eda627015463c9
3
+ size 17549312
run-41/checkpoint-297/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:897108fd5120056c832db7d7a629d638fea10ad46a1c12e945c8b5d2d1cbc37f
3
+ size 35123898
run-41/checkpoint-297/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f5e396c574b9b2ecc40d3f9e87d628a8f4be69caef81905a47fcf8895067e6
3
+ size 14308
run-41/checkpoint-297/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8bca187a34ddb5757f4ed3254dc9110349c2c8399c84cd25e8f2ce9b2d4cfae
3
+ size 1064
run-41/checkpoint-297/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-41/checkpoint-297/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-41/checkpoint-297/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-41/checkpoint-297/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5366336633663367,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-41/checkpoint-297",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 297,
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": 2.0725367069244385,
14
+ "learning_rate": 0.00020209984458518428,
15
+ "loss": 0.6597,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5366336633663367,
21
+ "eval_f1": 0.31176470588235294,
22
+ "eval_loss": 0.6622546911239624,
23
+ "eval_mcc": 0.09487420793018501,
24
+ "eval_precision": 0.6022727272727273,
25
+ "eval_recall": 0.21031746031746032,
26
+ "eval_runtime": 0.9278,
27
+ "eval_samples_per_second": 544.286,
28
+ "eval_steps_per_second": 17.245,
29
+ "step": 297
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 2079,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 7,
36
+ "save_steps": 500,
37
+ "total_flos": 730701265980.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9417813739243972,
42
+ "learning_rate": 0.00023578315201604834,
43
+ "num_train_epochs": 7,
44
+ "temperature": 19
45
+ }
46
+ }
run-41/checkpoint-297/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa03e49d599722cca04bf2146c0b449c7b7a4a95dd98c7060525ec81c8b3b1c
3
+ size 4920
run-41/checkpoint-297/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 sha256:5517b196c46e47a36c72ced76e5af4b26f847ea05009b31731917e96011dcbda
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa03e49d599722cca04bf2146c0b449c7b7a4a95dd98c7060525ec81c8b3b1c
3
  size 4920