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
cb9d2f6
·
verified ·
1 Parent(s): be0419f

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-8/checkpoint-56/config.json +34 -0
  3. run-8/checkpoint-56/model.safetensors +3 -0
  4. run-8/checkpoint-56/optimizer.pt +3 -0
  5. run-8/checkpoint-56/rng_state.pth +3 -0
  6. run-8/checkpoint-56/scheduler.pt +3 -0
  7. run-8/checkpoint-56/special_tokens_map.json +7 -0
  8. run-8/checkpoint-56/tokenizer.json +0 -0
  9. run-8/checkpoint-56/tokenizer_config.json +55 -0
  10. run-8/checkpoint-56/trainer_state.json +62 -0
  11. run-8/checkpoint-56/training_args.bin +3 -0
  12. run-8/checkpoint-56/vocab.txt +0 -0
  13. run-8/checkpoint-70/config.json +34 -0
  14. run-8/checkpoint-70/model.safetensors +3 -0
  15. run-8/checkpoint-70/optimizer.pt +3 -0
  16. run-8/checkpoint-70/rng_state.pth +3 -0
  17. run-8/checkpoint-70/scheduler.pt +3 -0
  18. run-8/checkpoint-70/special_tokens_map.json +7 -0
  19. run-8/checkpoint-70/tokenizer.json +0 -0
  20. run-8/checkpoint-70/tokenizer_config.json +55 -0
  21. run-8/checkpoint-70/trainer_state.json +71 -0
  22. run-8/checkpoint-70/training_args.bin +3 -0
  23. run-8/checkpoint-70/vocab.txt +0 -0
  24. run-9/checkpoint-107/config.json +34 -0
  25. run-9/checkpoint-107/model.safetensors +3 -0
  26. run-9/checkpoint-107/optimizer.pt +3 -0
  27. run-9/checkpoint-107/rng_state.pth +3 -0
  28. run-9/checkpoint-107/scheduler.pt +3 -0
  29. run-9/checkpoint-107/special_tokens_map.json +7 -0
  30. run-9/checkpoint-107/tokenizer.json +0 -0
  31. run-9/checkpoint-107/tokenizer_config.json +55 -0
  32. run-9/checkpoint-107/trainer_state.json +35 -0
  33. run-9/checkpoint-107/training_args.bin +3 -0
  34. run-9/checkpoint-107/vocab.txt +0 -0
  35. runs/Mar07_08-06-39_49d4a3166cad/events.out.tfevents.1709800438.49d4a3166cad.3288.13 +3 -0
  36. runs/Mar07_08-06-39_49d4a3166cad/events.out.tfevents.1709800486.49d4a3166cad.3288.14 +3 -0
  37. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06dafb1c5e3d70bca74a43c8e112b3b92a3b79a6de98cfef236cf37ddf4af884
3
  size 98470112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3edbbb614a592d510a068a7f5ee9efef3bf658643ad039ba040de20e691b3da5
3
  size 98470112
run-8/checkpoint-56/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-8/checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d2e67179e88233b7bdec60e9461240918f445a2b22e89c82a50748d101cd9d
3
+ size 98470112
run-8/checkpoint-56/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b592d0e16f3172535b85bc0d7b0d362ed40fcae4b18338f9ab19f76b254b3d42
3
+ size 197593757
run-8/checkpoint-56/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a58e4c8d075c7c0a341e1c69bccbaafbf74d1aae9c5ce4f206091db1dce0d472
3
+ size 14244
run-8/checkpoint-56/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a7adeedbd4f49114a787969e8f008b987b689f3cc8b8c702c0a5c0a3257c60c
3
+ size 1064
run-8/checkpoint-56/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-8/checkpoint-56/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-56/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-8/checkpoint-56/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-8/checkpoint-14",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 56,
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": 1441566.625,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 2.7596,
16
+ "eval_samples_per_second": 377.953,
17
+ "eval_steps_per_second": 23.917,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 88462.984375,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 2.7775,
25
+ "eval_samples_per_second": 375.515,
26
+ "eval_steps_per_second": 23.762,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 23446.939453125,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 2.7458,
34
+ "eval_samples_per_second": 379.85,
35
+ "eval_steps_per_second": 24.037,
36
+ "step": 42
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 10152.943359375,
41
+ "eval_matthews_correlation": -0.06375555059959441,
42
+ "eval_runtime": 2.7564,
43
+ "eval_samples_per_second": 378.398,
44
+ "eval_steps_per_second": 23.945,
45
+ "step": 56
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 70,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 64,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 1.690358131865815e-05,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 64,
60
+ "seed": 5
61
+ }
62
+ }
run-8/checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d8ce71bb58e2b1b63bdb7814d651df78a16f43893be6c36bed8d6382ade922
3
+ size 4920
run-8/checkpoint-56/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-70/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-8/checkpoint-70/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f56364e6a014665ac27d944da76eb3a305c3fe58a18378f9353d4d3cfe49d0
3
+ size 98470112
run-8/checkpoint-70/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97bec574ece0bebe41f716c7f829c1e6647678a001caf8762a11b6530cf3044f
3
+ size 197593757
run-8/checkpoint-70/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9061fe81d99081359587658cc56c5839d546dd8ad7ca357bc62edba44a483824
3
+ size 14244
run-8/checkpoint-70/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e7972d8f16d40e2b404ef4716a1a2b04295543aa7d7ee7a40b0532939aee8e
3
+ size 1064
run-8/checkpoint-70/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-8/checkpoint-70/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-70/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-8/checkpoint-70/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-8/checkpoint-14",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 70,
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": 1441566.625,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 2.7596,
16
+ "eval_samples_per_second": 377.953,
17
+ "eval_steps_per_second": 23.917,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 88462.984375,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 2.7775,
25
+ "eval_samples_per_second": 375.515,
26
+ "eval_steps_per_second": 23.762,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 23446.939453125,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 2.7458,
34
+ "eval_samples_per_second": 379.85,
35
+ "eval_steps_per_second": 24.037,
36
+ "step": 42
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 10152.943359375,
41
+ "eval_matthews_correlation": -0.06375555059959441,
42
+ "eval_runtime": 2.7564,
43
+ "eval_samples_per_second": 378.398,
44
+ "eval_steps_per_second": 23.945,
45
+ "step": 56
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_loss": 8982.5546875,
50
+ "eval_matthews_correlation": -0.0018582137243486861,
51
+ "eval_runtime": 2.7362,
52
+ "eval_samples_per_second": 381.181,
53
+ "eval_steps_per_second": 24.121,
54
+ "step": 70
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 70,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "total_flos": 0,
63
+ "train_batch_size": 64,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 1.690358131865815e-05,
67
+ "num_train_epochs": 5,
68
+ "per_device_train_batch_size": 64,
69
+ "seed": 5
70
+ }
71
+ }
run-8/checkpoint-70/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d8ce71bb58e2b1b63bdb7814d651df78a16f43893be6c36bed8d6382ade922
3
+ size 4920
run-8/checkpoint-70/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-107/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-9/checkpoint-107/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564f2457fd92892bdbd665eab7fbfb8adbd0063235d28c39a55389676da45baa
3
+ size 98470112
run-9/checkpoint-107/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd75310c0a5b6bd39645df3ae29cc16f5e21d7676024b150c5530e589d3d1c6
3
+ size 197593757
run-9/checkpoint-107/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de06f41e723769ef3d342e670def24740df18da41904f6ba9f656f9dbf8a7071
3
+ size 14308
run-9/checkpoint-107/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97dc7ae12a95cf72f03c6c6d529bef5b734039954552cfe91229afd23c319e41
3
+ size 1064
run-9/checkpoint-107/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-9/checkpoint-107/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-107/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-9/checkpoint-107/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-9/checkpoint-107",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 107,
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": 2351.89892578125,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 2.6877,
16
+ "eval_samples_per_second": 388.069,
17
+ "eval_steps_per_second": 24.557,
18
+ "step": 107
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 214,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 8,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.1140944916532557e-05,
31
+ "num_train_epochs": 2,
32
+ "per_device_train_batch_size": 8,
33
+ "seed": 31
34
+ }
35
+ }
run-9/checkpoint-107/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44f8c3d5bd96a720b0d19fce182c3ad9128127ea92f5e82d7e16110ec312daee
3
+ size 4920
run-9/checkpoint-107/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar07_08-06-39_49d4a3166cad/events.out.tfevents.1709800438.49d4a3166cad.3288.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf7ded14b6a3d91d1159a709638e97fdb19cefe0ed235f390258b4bf5b48beb
3
+ size 5540
runs/Mar07_08-06-39_49d4a3166cad/events.out.tfevents.1709800486.49d4a3166cad.3288.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48445ae5ee33054ca1608151ae6f1819c9fc3133649c4ddc920f7b61f3fafe25
3
+ size 5203
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9d8ce71bb58e2b1b63bdb7814d651df78a16f43893be6c36bed8d6382ade922
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0926346707a8d66976e74089ae692911018b9e10991497cdb1023e38ec538cc
3
  size 4920