Hugging Face's logo

samil24
/
bert-base-uncased-finetuned-rte-run_3

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
samil24 commited on
Commit
15b5694
·
verified ·
1 Parent(s): 601858a

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-33/checkpoint-156/config.json +26 -0
  3. run-33/checkpoint-156/model.safetensors +3 -0
  4. run-33/checkpoint-156/optimizer.pt +3 -0
  5. run-33/checkpoint-156/rng_state.pth +3 -0
  6. run-33/checkpoint-156/scheduler.pt +3 -0
  7. run-33/checkpoint-156/special_tokens_map.json +7 -0
  8. run-33/checkpoint-156/tokenizer.json +0 -0
  9. run-33/checkpoint-156/tokenizer_config.json +56 -0
  10. run-33/checkpoint-156/trainer_state.json +56 -0
  11. run-33/checkpoint-156/training_args.bin +3 -0
  12. run-33/checkpoint-156/vocab.txt +0 -0
  13. run-35/checkpoint-78/config.json +26 -0
  14. run-35/checkpoint-78/model.safetensors +3 -0
  15. run-35/checkpoint-78/optimizer.pt +3 -0
  16. run-35/checkpoint-78/rng_state.pth +3 -0
  17. run-35/checkpoint-78/scheduler.pt +3 -0
  18. run-35/checkpoint-78/special_tokens_map.json +7 -0
  19. run-35/checkpoint-78/tokenizer.json +0 -0
  20. run-35/checkpoint-78/tokenizer_config.json +56 -0
  21. run-35/checkpoint-78/trainer_state.json +47 -0
  22. run-35/checkpoint-78/training_args.bin +3 -0
  23. run-35/checkpoint-78/vocab.txt +0 -0
  24. runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743537967.1357c7d90830.592.52 +3 -0
  25. runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743537991.1357c7d90830.592.53 +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 sha256:5a277f6a12a1409fe0f4a7b40db1096c337cfa9bec3ec504facc99b24ff1f661
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7c55cddcb22efba1156da69cf662755b1e15870712b560d6fad70e41d6b858
3
  size 437958648
run-33/checkpoint-156/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-33/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0864cd67dc356eb980c7ae4c44bb9e77795fe96896c3089a09fe9f280fba672
3
+ size 437958648
run-33/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82af4bcba43f5fb84a97072eecb99c9b3838c67c14378cfbbb1311628cf7a50d
3
+ size 876038394
run-33/checkpoint-156/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a64755083f7633da1abd1de577e641d7084f1c57535fb19884090b3171beb5
3
+ size 14244
run-33/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ff19055c3e14fecc48f16e5e4f4f0d5490c6d973f854ce1af9de2b719cc489
3
+ size 1064
run-33/checkpoint-156/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-33/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-33/checkpoint-156/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-33/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 156,
3
+ "best_metric": 0.6534296028880866,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-33/checkpoint-156",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 156,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.6498194945848376,
15
+ "eval_loss": 0.6419539451599121,
16
+ "eval_runtime": 0.6591,
17
+ "eval_samples_per_second": 420.293,
18
+ "eval_steps_per_second": 7.587,
19
+ "step": 78
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.6534296028880866,
24
+ "eval_loss": 0.634818434715271,
25
+ "eval_runtime": 0.6639,
26
+ "eval_samples_per_second": 417.224,
27
+ "eval_steps_per_second": 7.531,
28
+ "step": 156
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 156,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 2,
35
+ "save_steps": 500,
36
+ "stateful_callbacks": {
37
+ "TrainerControl": {
38
+ "args": {
39
+ "should_epoch_stop": false,
40
+ "should_evaluate": false,
41
+ "should_log": false,
42
+ "should_save": true,
43
+ "should_training_stop": true
44
+ },
45
+ "attributes": {}
46
+ }
47
+ },
48
+ "total_flos": 0,
49
+ "train_batch_size": 32,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "learning_rate": 5.59313791861194e-05,
53
+ "num_train_epochs": 2,
54
+ "per_device_train_batch_size": 32
55
+ }
56
+ }
run-33/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe9873c26a745d93c4e7225004d447f3546bea07903f60d63754c1b8158128d
3
+ size 5432
run-33/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-35/checkpoint-78/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-35/checkpoint-78/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7c55cddcb22efba1156da69cf662755b1e15870712b560d6fad70e41d6b858
3
+ size 437958648
run-35/checkpoint-78/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4882ba5fa44fca1c6195f4207d5b13f3a987822f6151ff197aad86711e4730e0
3
+ size 876038394
run-35/checkpoint-78/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ab796df965c74c106f46f16854d55804fecfe14c1d69ae73ebe7269fc9ed28
3
+ size 14244
run-35/checkpoint-78/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0a5ca042cf0af0e003d667a8333bb8afb4e09dd9bfca63025459b72a195e5b6
3
+ size 1064
run-35/checkpoint-78/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-35/checkpoint-78/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-35/checkpoint-78/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-35/checkpoint-78/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 78,
3
+ "best_metric": 0.6534296028880866,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-35/checkpoint-78",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 78,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.6534296028880866,
15
+ "eval_loss": 0.6615884304046631,
16
+ "eval_runtime": 0.6594,
17
+ "eval_samples_per_second": 420.098,
18
+ "eval_steps_per_second": 7.583,
19
+ "step": 78
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 156,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 2,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 0,
40
+ "train_batch_size": 32,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "learning_rate": 6.164930711166937e-05,
44
+ "num_train_epochs": 2,
45
+ "per_device_train_batch_size": 32
46
+ }
47
+ }
run-35/checkpoint-78/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64eef85f415610621a3109a46c6844ce1af66848605c9506a49eb78d3c842df5
3
+ size 5432
run-35/checkpoint-78/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743537967.1357c7d90830.592.52 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7055a472d397e4788599a71d09d8346a620972f14ca553a93c10473b6040342e
3
+ size 5418
runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743537991.1357c7d90830.592.53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed517b803db6d0666983bae3ade36dffa44f04c1f23134f942d281fcf28d9692
3
+ size 6095
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbe9873c26a745d93c4e7225004d447f3546bea07903f60d63754c1b8158128d
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64eef85f415610621a3109a46c6844ce1af66848605c9506a49eb78d3c842df5
3
  size 5432