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
f52602e
·
verified ·
1 Parent(s): 67f2124

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1709700410.a2333cf40ebd.21010.13 +2 -2
  2. logs/events.out.tfevents.1709700653.a2333cf40ebd.21010.14 +3 -0
  3. model.safetensors +1 -1
  4. run-13/checkpoint-192/config.json +34 -0
  5. run-13/checkpoint-192/model.safetensors +3 -0
  6. run-13/checkpoint-192/optimizer.pt +3 -0
  7. run-13/checkpoint-192/rng_state.pth +3 -0
  8. run-13/checkpoint-192/scheduler.pt +3 -0
  9. run-13/checkpoint-192/special_tokens_map.json +7 -0
  10. run-13/checkpoint-192/tokenizer.json +0 -0
  11. run-13/checkpoint-192/tokenizer_config.json +57 -0
  12. run-13/checkpoint-192/trainer_state.json +64 -0
  13. run-13/checkpoint-192/training_args.bin +3 -0
  14. run-13/checkpoint-192/vocab.txt +0 -0
  15. run-14/checkpoint-96/config.json +34 -0
  16. run-14/checkpoint-96/model.safetensors +3 -0
  17. run-14/checkpoint-96/optimizer.pt +3 -0
  18. run-14/checkpoint-96/rng_state.pth +3 -0
  19. run-14/checkpoint-96/scheduler.pt +3 -0
  20. run-14/checkpoint-96/special_tokens_map.json +7 -0
  21. run-14/checkpoint-96/tokenizer.json +0 -0
  22. run-14/checkpoint-96/tokenizer_config.json +57 -0
  23. run-14/checkpoint-96/trainer_state.json +45 -0
  24. run-14/checkpoint-96/training_args.bin +3 -0
  25. run-14/checkpoint-96/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1709700410.a2333cf40ebd.21010.13 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2586102e32da660f372ed36fe089f41b67836f6862a9581524e2cacf2fce8c30
3
- size 5314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371e38a639d7504a52805568f8bb36456b6ff366408af44634254b176587c50d
3
+ size 6351
logs/events.out.tfevents.1709700653.a2333cf40ebd.21010.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d06db7aa6fc83d605a325a8ad1e8348004921d69997038d05e47b64b325014f
3
+ size 5315
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:279f7a67a943e71a59d0ff47b581a76117de8af0dcda5818c19473c5e8f27989
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3225f795e3cfeb211e08af5b4dba84ef884ea7c28cda7fc06a865b45f240f9
3
  size 17549312
run-13/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-13/checkpoint-192/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f8d22e427f88a3cccb4343fe9a81e4f810cd23d2c572e330ac5c439934459da
3
+ size 17549312
run-13/checkpoint-192/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da2e88401839e9ab35f222ad1a67477afdcf4d64aedc15a9faec5b33140ad3ba
3
+ size 35122746
run-13/checkpoint-192/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
3
+ size 14054
run-13/checkpoint-192/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827aad0fd5a1155a436d484cfb1b57ea7db209266ead7a878cac15cd726f4131
3
+ size 1064
run-13/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-13/checkpoint-192/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/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-13/checkpoint-192/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8101761252446184,
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,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 3.178528308868408,
14
+ "learning_rate": 0.00013234646126788495,
15
+ "loss": 0.5867,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7818003913894325,
21
+ "eval_f1": 0.8102127659574467,
22
+ "eval_loss": 0.47177326679229736,
23
+ "eval_precision": 0.7168674698795181,
24
+ "eval_recall": 0.9315068493150684,
25
+ "eval_runtime": 29.1712,
26
+ "eval_samples_per_second": 35.035,
27
+ "eval_steps_per_second": 1.097,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 3.0951292514801025,
33
+ "learning_rate": 0.0,
34
+ "loss": 0.469,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8101761252446184,
40
+ "eval_f1": 0.830122591943958,
41
+ "eval_loss": 0.44528669118881226,
42
+ "eval_precision": 0.751188589540412,
43
+ "eval_recall": 0.9275929549902152,
44
+ "eval_runtime": 28.496,
45
+ "eval_samples_per_second": 35.865,
46
+ "eval_steps_per_second": 1.123,
47
+ "step": 192
48
+ }
49
+ ],
50
+ "logging_steps": 500,
51
+ "max_steps": 192,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 2,
54
+ "save_steps": 500,
55
+ "total_flos": 471390394560.0,
56
+ "train_batch_size": 32,
57
+ "trial_name": null,
58
+ "trial_params": {
59
+ "alpha": 0.9936603556458727,
60
+ "learning_rate": 0.0002646929225357699,
61
+ "num_train_epochs": 2,
62
+ "temperature": 26
63
+ }
64
+ }
run-13/checkpoint-192/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633c942d0b60f05ab3fa982f5bbaaa9bbdcf47198dfbdd5d1b639decdd30975e
3
+ size 4920
run-13/checkpoint-192/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-96/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-14/checkpoint-96/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3225f795e3cfeb211e08af5b4dba84ef884ea7c28cda7fc06a865b45f240f9
3
+ size 17549312
run-14/checkpoint-96/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405cc74fb32707b94293b2391bc45f2b70820f4c5c3ac5cba5ce4050a15f6e7b
3
+ size 35122746
run-14/checkpoint-96/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
3
+ size 14054
run-14/checkpoint-96/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b6c01a10e1b90e8a67febecf5111e97af6ff0452a267a16d088a9580fe6f07
3
+ size 1064
run-14/checkpoint-96/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-14/checkpoint-96/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-96/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-14/checkpoint-96/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7945205479452054,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-96",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 96,
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": 1.392162561416626,
14
+ "learning_rate": 0.00018327679510936405,
15
+ "loss": 0.506,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7945205479452054,
21
+ "eval_f1": 0.8138297872340425,
22
+ "eval_loss": 0.43322718143463135,
23
+ "eval_precision": 0.7439222042139384,
24
+ "eval_recall": 0.898238747553816,
25
+ "eval_runtime": 28.335,
26
+ "eval_samples_per_second": 36.068,
27
+ "eval_steps_per_second": 1.129,
28
+ "step": 96
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 384,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 4,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 32,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.7512024699670536,
41
+ "learning_rate": 0.00024436906014581875,
42
+ "num_train_epochs": 4,
43
+ "temperature": 25
44
+ }
45
+ }
run-14/checkpoint-96/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a362a16e304bed4ef4106f9a75a81f97a0fe20c647127af248c0389326eed5
3
+ size 4920
run-14/checkpoint-96/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:eca285e074f5751b46e77605d55ec46cae8a3b205f294ab4811aec331d54f279
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a362a16e304bed4ef4106f9a75a81f97a0fe20c647127af248c0389326eed5
3
  size 4920