Hugging Face's logo

gchhablani
/
bert-large-cased-finetuned-wnli

Text Classification
Transformers
PyTorch
TensorBoard
English
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
gchhablani commited on
Commit
7a24dfa
·
1 Parent(s): a5a7f6a

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. checkpoint-159/config.json +42 -0
  2. checkpoint-159/optimizer.pt +3 -0
  3. checkpoint-159/pytorch_model.bin +3 -0
  4. checkpoint-159/rng_state.pth +3 -0
  5. checkpoint-159/scheduler.pt +3 -0
  6. checkpoint-159/special_tokens_map.json +1 -0
  7. checkpoint-159/tokenizer.json +0 -0
  8. checkpoint-159/tokenizer_config.json +1 -0
  9. checkpoint-159/trainer_state.json +31 -0
  10. checkpoint-159/training_args.bin +3 -0
  11. checkpoint-159/vocab.txt +0 -0
  12. config.json +42 -0
  13. pytorch_model.bin +3 -0
  14. runs/Sep23_04-38-21_patrick-general-gpu/1632371921.1884568/events.out.tfevents.1632371921.patrick-general-gpu.956617.1 +3 -0
  15. runs/Sep23_04-38-21_patrick-general-gpu/events.out.tfevents.1632371921.patrick-general-gpu.956617.0 +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-159/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "wnli",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "not_entailment",
16
+ "1": "entailment"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "entailment": 1,
22
+ "not_entailment": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.11.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
checkpoint-159/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b994992f17876e6e05e3090641bd58c6276be7b03aea1b19d267b8cac71c6e
3
+ size 2668878813
checkpoint-159/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e891738eaf0284e09ea7684f96da740d147a4e6798f668e6044703a0c5ccd35
3
+ size 1334486957
checkpoint-159/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e1729a177d2e67171f3a928abb4c4f700f5e30653c91cbcd0a3d87f90da2222
3
+ size 14503
checkpoint-159/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ed00d7db04a3313edfabe288b9be415ba80399d5b699ff34f4f4dde3bc6fde
3
+ size 623
checkpoint-159/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-159/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-159/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-large-cased", "tokenizer_class": "BertTokenizer"}
checkpoint-159/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": 159,
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": 1.6000000000000003e-05,
13
+ "loss": 0.7114,
14
+ "step": 159
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5633802816901409,
19
+ "eval_loss": 0.6923297047615051,
20
+ "eval_runtime": 2.3107,
21
+ "eval_samples_per_second": 30.726,
22
+ "eval_steps_per_second": 3.895,
23
+ "step": 159
24
+ }
25
+ ],
26
+ "max_steps": 795,
27
+ "num_train_epochs": 5,
28
+ "total_flos": 591776415713280.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-159/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f437d761207ace3e79f2ae16f9d937b1288fc6469422d252660a340c9050722c
3
+ size 2799
checkpoint-159/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "wnli",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "not_entailment",
16
+ "1": "entailment"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "entailment": 1,
22
+ "not_entailment": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.11.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e891738eaf0284e09ea7684f96da740d147a4e6798f668e6044703a0c5ccd35
3
+ size 1334486957
runs/Sep23_04-38-21_patrick-general-gpu/1632371921.1884568/events.out.tfevents.1632371921.patrick-general-gpu.956617.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c3a6a8de3c2a65e1410a1002e9774f09652a4cad53517649be6c5db5122bda
3
+ size 4372
runs/Sep23_04-38-21_patrick-general-gpu/events.out.tfevents.1632371921.patrick-general-gpu.956617.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803e5ff41043973f63bfa34bd9cc6d361103f9afd4aa08a480882b868f391d24
3
+ size 3921
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-large-cased", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f437d761207ace3e79f2ae16f9d937b1288fc6469422d252660a340c9050722c
3
+ size 2799
vocab.txt ADDED
The diff for this file is too large to render. See raw diff