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
80db4ec
·
verified ·
1 Parent(s): 8f0f62a

Training in progress, epoch 1

Browse files
Files changed (19) hide show
  1. logs/events.out.tfevents.1711305662.73e3a81c01ef.4225.43 +3 -0
  2. logs/events.out.tfevents.1711305945.73e3a81c01ef.4225.44 +3 -0
  3. logs/events.out.tfevents.1711306227.73e3a81c01ef.4225.45 +3 -0
  4. logs/events.out.tfevents.1711306509.73e3a81c01ef.4225.46 +3 -0
  5. logs/events.out.tfevents.1711306791.73e3a81c01ef.4225.47 +3 -0
  6. logs/events.out.tfevents.1711307073.73e3a81c01ef.4225.48 +3 -0
  7. model.safetensors +1 -1
  8. run-48/checkpoint-192/config.json +34 -0
  9. run-48/checkpoint-192/model.safetensors +3 -0
  10. run-48/checkpoint-192/optimizer.pt +3 -0
  11. run-48/checkpoint-192/rng_state.pth +3 -0
  12. run-48/checkpoint-192/scheduler.pt +3 -0
  13. run-48/checkpoint-192/special_tokens_map.json +7 -0
  14. run-48/checkpoint-192/tokenizer.json +0 -0
  15. run-48/checkpoint-192/tokenizer_config.json +57 -0
  16. run-48/checkpoint-192/trainer_state.json +47 -0
  17. run-48/checkpoint-192/training_args.bin +3 -0
  18. run-48/checkpoint-192/vocab.txt +0 -0
  19. training_args.bin +1 -1
logs/events.out.tfevents.1711305662.73e3a81c01ef.4225.43 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885d84322a638b1cde06331be433f79993ae9e283589dfb042bb7725ed825592
3
+ size 5406
logs/events.out.tfevents.1711305945.73e3a81c01ef.4225.44 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb9ee92d6b8dd1066db5927bb40a6d2cedb54dda86738cd624f1cfb733f9f89
3
+ size 5407
logs/events.out.tfevents.1711306227.73e3a81c01ef.4225.45 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3270d8d0379468761a691cbc6ce19f05a32a6c69e8bbf60b509e7b0345bdca
3
+ size 5407
logs/events.out.tfevents.1711306509.73e3a81c01ef.4225.46 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eabf6cdb27ad092a830a19a5d19f9558edd8e3f1167a02b2327c4dc490d936d6
3
+ size 5405
logs/events.out.tfevents.1711306791.73e3a81c01ef.4225.47 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c7b3a7120406dacc0b25508ebef6a7678b35806440d763b43b2b762ab5b476
3
+ size 5407
logs/events.out.tfevents.1711307073.73e3a81c01ef.4225.48 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdff036c57e9f6ce9d02f83bf240b36b627203f0a5200c6d715fcdd37315e15a
3
+ size 5407
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5d89dea0b7ac99d4a9c61e56ff105fb989a0ef5fec71ac3eeb99be7e068bbf0
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35a5546d0fc73fcc3adc887eb853063ffaeb94d98f331a01d1750a610afe8c1
3
  size 17549312
run-48/checkpoint-192/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-48/checkpoint-192/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35a5546d0fc73fcc3adc887eb853063ffaeb94d98f331a01d1750a610afe8c1
3
+ size 17549312
run-48/checkpoint-192/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f4fbcd370c419092db3371d23bb5717b76c47dda11d065740cb8f1507f750a6
3
+ size 35122746
run-48/checkpoint-192/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
3
+ size 14054
run-48/checkpoint-192/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e9ba35de518271d87d76e6e7f09bb25dc08883991e96d43ab049a811c3dc4e
3
+ size 1064
run-48/checkpoint-192/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-48/checkpoint-192/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-48/checkpoint-192/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-48/checkpoint-192/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7984344422700587,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-48/checkpoint-192",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 192,
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": 6.156297206878662,
14
+ "learning_rate": 6.847131652416489e-05,
15
+ "loss": 0.5617,
16
+ "step": 192
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7984344422700587,
21
+ "eval_f1": 0.8186619718309858,
22
+ "eval_loss": 0.4545396566390991,
23
+ "eval_mcc": 0.6123004481387646,
24
+ "eval_precision": 0.744,
25
+ "eval_recall": 0.9099804305283757,
26
+ "eval_runtime": 66.7324,
27
+ "eval_samples_per_second": 15.315,
28
+ "eval_steps_per_second": 0.48,
29
+ "step": 192
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 384,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 2,
36
+ "save_steps": 500,
37
+ "total_flos": 235695197280.0,
38
+ "train_batch_size": 16,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.8915947606865525,
42
+ "learning_rate": 0.00013694263304832977,
43
+ "num_train_epochs": 2,
44
+ "per_device_train_batch_size": 16,
45
+ "temperature": 24
46
+ }
47
+ }
run-48/checkpoint-192/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d30e5b21f83d87a77503fd594b335990baf967de194f9e146aac9cf831a4555
3
+ size 4984
run-48/checkpoint-192/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:f09f6e3007799f4d90af21ec2c7261c6a15eb8e5c390bbc135f1f4ce7735edeb
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d30e5b21f83d87a77503fd594b335990baf967de194f9e146aac9cf831a4555
3
  size 4984