Hugging Face's logo

Tech-oriented
/
best_model_bert_uncasedbert-base-uncased-finetuned-sst2

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Tech-oriented commited on
Commit
cfaf364
•
1 Parent(s): 6917143

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. config.json +27 -0
  2. model.safetensors +3 -0
  3. run-0/checkpoint-421/config.json +27 -0
  4. run-0/checkpoint-421/model.safetensors +3 -0
  5. run-0/checkpoint-421/optimizer.pt +3 -0
  6. run-0/checkpoint-421/rng_state.pth +3 -0
  7. run-0/checkpoint-421/scheduler.pt +3 -0
  8. run-0/checkpoint-421/special_tokens_map.json +7 -0
  9. run-0/checkpoint-421/tokenizer.json +0 -0
  10. run-0/checkpoint-421/tokenizer_config.json +55 -0
  11. run-0/checkpoint-421/trainer_state.json +36 -0
  12. run-0/checkpoint-421/training_args.bin +3 -0
  13. run-0/checkpoint-421/vocab.txt +0 -0
  14. runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709651527.9d72474d753b.33271.0 +3 -0
  15. runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709651760.9d72474d753b.33271.1 +3 -0
  16. special_tokens_map.json +7 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +55 -0
  19. training_args.bin +3 -0
  20. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.3,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.3,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b428807a2e5da9ebee7ca15e468f1f1ec4ecbe9303e4fe21671433032a0ebbc5
3
+ size 437958648
run-0/checkpoint-421/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.3,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.3,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-0/checkpoint-421/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b428807a2e5da9ebee7ca15e468f1f1ec4ecbe9303e4fe21671433032a0ebbc5
3
+ size 437958648
run-0/checkpoint-421/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6058c1879b16d58d902697bda5d845900afe2d3660fe47d733bebed241943a86
3
+ size 876038394
run-0/checkpoint-421/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c97730e8ef7fe003e00ca57e2d8c1d9608f1dba9d62d7a5a9a2c290c4a7efe
3
+ size 14244
run-0/checkpoint-421/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c148e6ecf633320215ce755b18037bdd7c11c04051ed1c0c3fa6e831a6203ca3
3
+ size 1064
run-0/checkpoint-421/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-0/checkpoint-421/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-421/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": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-421/trainer_state.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5871559633027523,
3
+ "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-0/checkpoint-421",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 421,
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_accuracy": 0.5871559633027523,
14
+ "eval_loss": 0.6697461009025574,
15
+ "eval_runtime": 2.3652,
16
+ "eval_samples_per_second": 368.681,
17
+ "eval_steps_per_second": 23.254,
18
+ "step": 421
19
+ }
20
+ ],
21
+ "logging_steps": 4209,
22
+ "max_steps": 1263,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.3048303331369337e-06,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 6,
34
+ "weight_decay": 0.3377283287391723
35
+ }
36
+ }
run-0/checkpoint-421/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44dc25bba6431ca36f2d7d667943561f905d13814eb88802e61a1b3a6032a237
3
+ size 4984
run-0/checkpoint-421/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709651527.9d72474d753b.33271.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58a883e0b0a636fb333bfcab2f96c366dbfdb61961feba973574056f563af46
3
+ size 4736
runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709651760.9d72474d753b.33271.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ecded596c4f3d643c2cc5326c7c02af83d343d45d0251f9255bc817c79b89e4
3
+ size 5073
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44dc25bba6431ca36f2d7d667943561f905d13814eb88802e61a1b3a6032a237
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff