Hugging Face's logo

obudzecie
/
mobilebert-uncased-finetuned-cola

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
mobilebert
Inference Endpoints
Model card Files Metrics Community
obudzecie commited on
Commit
9b04cb1
•
1 Parent(s): b76743c

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-54/config.json +34 -0
  3. run-2/checkpoint-54/model.safetensors +3 -0
  4. run-2/checkpoint-54/optimizer.pt +3 -0
  5. run-2/checkpoint-54/rng_state.pth +3 -0
  6. run-2/checkpoint-54/scheduler.pt +3 -0
  7. run-2/checkpoint-54/special_tokens_map.json +7 -0
  8. run-2/checkpoint-54/tokenizer.json +0 -0
  9. run-2/checkpoint-54/tokenizer_config.json +55 -0
  10. run-2/checkpoint-54/trainer_state.json +44 -0
  11. run-2/checkpoint-54/training_args.bin +3 -0
  12. run-2/checkpoint-54/vocab.txt +0 -0
  13. run-3/checkpoint-214/config.json +34 -0
  14. run-3/checkpoint-214/model.safetensors +3 -0
  15. run-3/checkpoint-214/optimizer.pt +3 -0
  16. run-3/checkpoint-214/rng_state.pth +3 -0
  17. run-3/checkpoint-214/scheduler.pt +3 -0
  18. run-3/checkpoint-214/special_tokens_map.json +7 -0
  19. run-3/checkpoint-214/tokenizer.json +0 -0
  20. run-3/checkpoint-214/tokenizer_config.json +55 -0
  21. run-3/checkpoint-214/trainer_state.json +35 -0
  22. run-3/checkpoint-214/training_args.bin +3 -0
  23. run-3/checkpoint-214/vocab.txt +0 -0
  24. runs/Mar06_18-31-06_d31543f127fe/events.out.tfevents.1709750602.d31543f127fe.795.4 +2 -2
  25. runs/Mar06_18-31-06_d31543f127fe/events.out.tfevents.1709750627.d31543f127fe.795.5 +3 -0
  26. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81556d50ade0f4353bf56ebb6cbb02447d41c31bdd92986ed1c9bf5e76949524
3
  size 98470112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b782aae39b7d2bb1bcdbf118a01ef1a4d3df99cf87aaf43572cfa99cad398d
3
  size 98470112
run-2/checkpoint-54/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mobilebert-uncased",
3
+ "architectures": [
4
+ "MobileBertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_activation": false,
8
+ "classifier_dropout": null,
9
+ "embedding_size": 128,
10
+ "hidden_act": "relu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 512,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 512,
15
+ "intra_bottleneck_size": 128,
16
+ "key_query_shared_bottleneck": true,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "mobilebert",
20
+ "normalization_type": "no_norm",
21
+ "num_attention_heads": 4,
22
+ "num_feedforward_networks": 4,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 0,
25
+ "problem_type": "single_label_classification",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.38.2",
28
+ "trigram_input": true,
29
+ "true_hidden_size": 128,
30
+ "type_vocab_size": 2,
31
+ "use_bottleneck": true,
32
+ "use_bottleneck_attention": false,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ce5cba71ab627aa4d3b1694264448dd6b7c33fa58fdf00e3b68101b022d151
3
+ size 98470112
run-2/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf9090313f1d1e637238680271b34cf9e7a19532a6474f42fe7432fe43e0ff6
3
+ size 197593757
run-2/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d07fb318ad742c1c4d329e1f07ad38c5c4a57d1f01ad4efb31257c2bccb417a
3
+ size 14244
run-2/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b71680a09b19af463162c25c87905ddd0917ca13d590913abe6708a7d33215
3
+ size 1064
run-2/checkpoint-54/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-2/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-54/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "MobileBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-2/checkpoint-54/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-2/checkpoint-27",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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
+ "eval_loss": 18281.876953125,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 2.4635,
16
+ "eval_samples_per_second": 423.379,
17
+ "eval_steps_per_second": 26.791,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 866.8018798828125,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 2.6773,
25
+ "eval_samples_per_second": 389.575,
26
+ "eval_steps_per_second": 24.652,
27
+ "step": 54
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 54,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 2.81582432447674e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 5
43
+ }
44
+ }
run-2/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1b81ffb403f14950689bf76af4de34d59644f8842de05b90ea8aa4ee6730d4b
3
+ size 4920
run-2/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-214/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mobilebert-uncased",
3
+ "architectures": [
4
+ "MobileBertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_activation": false,
8
+ "classifier_dropout": null,
9
+ "embedding_size": 128,
10
+ "hidden_act": "relu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 512,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 512,
15
+ "intra_bottleneck_size": 128,
16
+ "key_query_shared_bottleneck": true,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "mobilebert",
20
+ "normalization_type": "no_norm",
21
+ "num_attention_heads": 4,
22
+ "num_feedforward_networks": 4,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 0,
25
+ "problem_type": "single_label_classification",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.38.2",
28
+ "trigram_input": true,
29
+ "true_hidden_size": 128,
30
+ "type_vocab_size": 2,
31
+ "use_bottleneck": true,
32
+ "use_bottleneck_attention": false,
33
+ "vocab_size": 30522
34
+ }
run-3/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b782aae39b7d2bb1bcdbf118a01ef1a4d3df99cf87aaf43572cfa99cad398d
3
+ size 98470112
run-3/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a46a06181120d69bc2b40ce343e91b8b247662043551c6134baf8cbd5068ea6
3
+ size 197593757
run-3/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c58dcb170961efe0517136cfde6dea1f1a280a99d325b68df07810b54f3f127c
3
+ size 14244
run-3/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5853b58eceb665e25e0c5d848132e71e1d4ac5ff5c75069a2276770addaa5dd
3
+ size 1064
run-3/checkpoint-214/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-3/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-214/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "MobileBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-3/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.058904192434496606,
3
+ "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-3/checkpoint-214",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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
+ "eval_loss": 2.5210232734680176,
14
+ "eval_matthews_correlation": 0.058904192434496606,
15
+ "eval_runtime": 2.5315,
16
+ "eval_samples_per_second": 412.011,
17
+ "eval_steps_per_second": 26.072,
18
+ "step": 214
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1070,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 4,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.0779195001059162e-05,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 4,
33
+ "seed": 3
34
+ }
35
+ }
run-3/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee669fd7e4a4001e1f35cd42535ae98ba5d3ab835bda65f0948d763ff5e7e446
3
+ size 4920
run-3/checkpoint-214/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar06_18-31-06_d31543f127fe/events.out.tfevents.1709750602.d31543f127fe.795.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c25810c0251d535186c94bb87b9be9d3fec42dc3e2ca4311761fe7d53b7d13ca
3
- size 5203
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f206a098c816ec567fd5d07affda58496d683551fe6717b36d89d263061ab8
3
+ size 5880
runs/Mar06_18-31-06_d31543f127fe/events.out.tfevents.1709750627.d31543f127fe.795.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b845eaf2a106261b1f383cf6b4f202a0915007477381a9320aae430a78870a5a
3
+ size 5210
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1b81ffb403f14950689bf76af4de34d59644f8842de05b90ea8aa4ee6730d4b
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee669fd7e4a4001e1f35cd42535ae98ba5d3ab835bda65f0948d763ff5e7e446
3
  size 4920