Hugging Face's logo

gchhablani
/
bert-base-cased-finetuned-qqp

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
d8699ad
•
1 Parent(s): 38d653b

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. checkpoint-22741/config.json +36 -0
  2. checkpoint-22741/optimizer.pt +3 -0
  3. checkpoint-22741/pytorch_model.bin +3 -0
  4. checkpoint-22741/rng_state.pth +3 -0
  5. checkpoint-22741/scheduler.pt +3 -0
  6. checkpoint-22741/special_tokens_map.json +1 -0
  7. checkpoint-22741/tokenizer.json +0 -0
  8. checkpoint-22741/tokenizer_config.json +1 -0
  9. checkpoint-22741/trainer_state.json +33 -0
  10. checkpoint-22741/training_args.bin +3 -0
  11. checkpoint-22741/vocab.txt +0 -0
  12. config.json +36 -0
  13. pytorch_model.bin +3 -0
  14. runs/Sep18_08-14-37_patrick-general-gpu/1631953045.8304787/events.out.tfevents.1631953045.patrick-general-gpu.335601.1 +3 -0
  15. runs/Sep18_08-14-37_patrick-general-gpu/events.out.tfevents.1631953045.patrick-general-gpu.335601.0 +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-22741/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": "qqp",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "not_duplicate",
15
+ "1": "duplicate"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "duplicate": 1,
21
+ "not_duplicate": 0
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-22741/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32599f3841fb74274a8eb71c3882b595d1e53fcb1cefba819b29fa4c474e9c9a
3
+ size 866610973
checkpoint-22741/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab45aac6f632447eaa05de28dac53fad1f9af1bd2769b318985ee9fede5575e4
3
+ size 433331373
checkpoint-22741/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38da7bad108541735082948c6bfb0c2e3d4b3032d64b9a615cdc96e592a96104
3
+ size 14503
checkpoint-22741/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96de79fb7807c1989c8172d9386bb706dac4db2f5398bd94c3b6e1949bb75f6a
3
+ size 623
checkpoint-22741/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-22741/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-22741/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-22741/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 22741,
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": 0.308,
14
+ "step": 22741
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8924560969577047,
19
+ "eval_combined_score": 0.8740405069726762,
20
+ "eval_f1": 0.8556249169876479,
21
+ "eval_loss": 0.2548316419124603,
22
+ "eval_runtime": 413.8779,
23
+ "eval_samples_per_second": 97.686,
24
+ "eval_steps_per_second": 12.211,
25
+ "step": 22741
26
+ }
27
+ ],
28
+ "max_steps": 68223,
29
+ "num_train_epochs": 3,
30
+ "total_flos": 9.573190504851456e+16,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-22741/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6215fd2fbd87e3a32e37bbf8b010344513fcafbfbf1dfe761fed7bac26bf7003
3
+ size 2799
checkpoint-22741/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": "qqp",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "not_duplicate",
15
+ "1": "duplicate"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "duplicate": 1,
21
+ "not_duplicate": 0
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:ab45aac6f632447eaa05de28dac53fad1f9af1bd2769b318985ee9fede5575e4
3
+ size 433331373
runs/Sep18_08-14-37_patrick-general-gpu/1631953045.8304787/events.out.tfevents.1631953045.patrick-general-gpu.335601.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1798a13b77a2eead58f1172ba24134b8a0b21a7774623d8edfcc7f28593b11
3
+ size 4366
runs/Sep18_08-14-37_patrick-general-gpu/events.out.tfevents.1631953045.patrick-general-gpu.335601.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa5678bebae3f1a5c6b6cc60a6a009ce15102fc16f7d4952726a22fe4be7f25
3
+ size 3833
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 sha256:6215fd2fbd87e3a32e37bbf8b010344513fcafbfbf1dfe761fed7bac26bf7003
3
+ size 2799
vocab.txt ADDED
The diff for this file is too large to render. See raw diff