Hugging Face's logo

gchhablani
/
bert-base-cased-finetuned-qnli

Text Classification
Transformers
PyTorch
TensorBoard
English
bert
generated_from_trainer
fnet-bert-base-comparison
Eval Results
Inference Endpoints
Model card Files Metrics Community
4
gchhablani commited on
Commit
537bb0c
•
1 Parent(s): d7d1d8a

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. checkpoint-6547/config.json +36 -0
  2. checkpoint-6547/optimizer.pt +3 -0
  3. checkpoint-6547/pytorch_model.bin +3 -0
  4. checkpoint-6547/rng_state.pth +3 -0
  5. checkpoint-6547/scheduler.pt +3 -0
  6. checkpoint-6547/special_tokens_map.json +1 -0
  7. checkpoint-6547/tokenizer.json +0 -0
  8. checkpoint-6547/tokenizer_config.json +1 -0
  9. checkpoint-6547/trainer_state.json +31 -0
  10. checkpoint-6547/training_args.bin +3 -0
  11. checkpoint-6547/vocab.txt +0 -0
  12. config.json +36 -0
  13. pytorch_model.bin +3 -0
  14. runs/Sep17_14-24-47_patrick-general-gpu/1631888732.514477/events.out.tfevents.1631888732.patrick-general-gpu.282818.1 +3 -0
  15. runs/Sep17_14-24-47_patrick-general-gpu/events.out.tfevents.1631888732.patrick-general-gpu.282818.0 +3 -0
  16. special_tokens_map.json +1 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +1 -0
  19. training_args.bin +3 -0
  20. vocab.txt +0 -0
checkpoint-6547/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "qnli",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "entailment",
15
+ "1": "not_entailment"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "entailment": 0,
21
+ "not_entailment": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.11.0.dev0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 28996
36
+ }
checkpoint-6547/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05aafe471a1dc71a34034843ea364308622abf248719bb430035489fd205d329
3
+ size 866610973
checkpoint-6547/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b152e566bf126e7ed80b2dd309ab008f6566b5b5d5a93a063c7e243144155c3
3
+ size 433331373
checkpoint-6547/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1632a7db567bcd3130effaa12edec117f6359482ca5e2ff3f30d9aad956f9b60
3
+ size 14503
checkpoint-6547/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbb18857f6def2ffcecfd194302b4498255430dfc3abbcfb66053c438b733b7
3
+ size 623
checkpoint-6547/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-6547/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-6547/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
checkpoint-6547/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 6547,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.3333333333333333e-05,
13
+ "loss": 0.337,
14
+ "step": 6547
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.9013362621270364,
19
+ "eval_loss": 0.24480287730693817,
20
+ "eval_runtime": 55.721,
21
+ "eval_samples_per_second": 98.042,
22
+ "eval_steps_per_second": 12.258,
23
+ "step": 6547
24
+ }
25
+ ],
26
+ "max_steps": 19641,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 2.755904127157248e+16,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-6547/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc54d0f744ff426ea106709cabc71730fd2811c6f430ce8415d7ad0f58f4f5a1
3
+ size 2799
checkpoint-6547/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "qnli",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "entailment",
15
+ "1": "not_entailment"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "entailment": 0,
21
+ "not_entailment": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.11.0.dev0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 28996
36
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b152e566bf126e7ed80b2dd309ab008f6566b5b5d5a93a063c7e243144155c3
3
+ size 433331373
runs/Sep17_14-24-47_patrick-general-gpu/1631888732.514477/events.out.tfevents.1631888732.patrick-general-gpu.282818.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e70458edab2271ef66f77c4fb426fd29ec0f6400b1b9a68dbff7434bfeaf78
3
+ size 4369
runs/Sep17_14-24-47_patrick-general-gpu/events.out.tfevents.1631888732.patrick-general-gpu.282818.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a40583f5db435694bfbfc2dda27b260876abefbf08223f974a7493dfb23a485
3
+ size 3726
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc54d0f744ff426ea106709cabc71730fd2811c6f430ce8415d7ad0f58f4f5a1
3
+ size 2799
vocab.txt ADDED
The diff for this file is too large to render. See raw diff