Hugging Face's logo

gchhablani
/
bert-base-cased-finetuned-wnli

Text Classification
Transformers
PyTorch
TensorBoard
English
bert
Generated from Trainer
fnet-bert-base-comparison
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
gchhablani commited on
Commit
ab6d30f
•
1 Parent(s): 64170eb

Training in progress, epoch 2

Browse files
Files changed (13) hide show
  1. checkpoint-80/config.json +36 -0
  2. checkpoint-80/optimizer.pt +3 -0
  3. checkpoint-80/pytorch_model.bin +3 -0
  4. checkpoint-80/rng_state.pth +3 -0
  5. checkpoint-80/scheduler.pt +3 -0
  6. checkpoint-80/special_tokens_map.json +1 -0
  7. checkpoint-80/tokenizer.json +0 -0
  8. checkpoint-80/tokenizer_config.json +1 -0
  9. checkpoint-80/trainer_state.json +46 -0
  10. checkpoint-80/training_args.bin +3 -0
  11. checkpoint-80/vocab.txt +0 -0
  12. pytorch_model.bin +1 -1
  13. runs/Sep16_17-01-08_patrick-general-gpu/events.out.tfevents.1631811685.patrick-general-gpu.176909.0 +2 -2
checkpoint-80/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": "wnli",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "not_entailment",
15
+ "1": "entailment"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "entailment": 1,
21
+ "not_entailment": 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-80/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488e3ad9aeae3208eab5c3591c9ce805370785540d29e918cac17aefa0c6fbdd
3
+ size 866610781
checkpoint-80/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35853cad31a133c89f44f8496a454e1218d06af54e3d34c22bb52a2d6e2fc6b3
3
+ size 433331373
checkpoint-80/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf252e0043295cabd64eec4916340dd22991b5e8129cdf9519aa3b76ef20220
3
+ size 14503
checkpoint-80/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b87f8ba4c0cc97d1cb84e99916436cfd692e67e4a2573bfe57ee6abcbd84bd1
3
+ size 623
checkpoint-80/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-80/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-80/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-80/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 80,
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": 0.7299,
14
+ "step": 40
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5633802816901409,
19
+ "eval_loss": 0.6923056840896606,
20
+ "eval_runtime": 0.73,
21
+ "eval_samples_per_second": 97.265,
22
+ "eval_steps_per_second": 12.329,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 1.2e-05,
28
+ "loss": 0.6982,
29
+ "step": 80
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.38028169014084506,
34
+ "eval_loss": 0.7026631832122803,
35
+ "eval_runtime": 0.7338,
36
+ "eval_samples_per_second": 96.754,
37
+ "eval_steps_per_second": 12.265,
38
+ "step": 80
39
+ }
40
+ ],
41
+ "max_steps": 200,
42
+ "num_train_epochs": 5,
43
+ "total_flos": 334151040307200.0,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-80/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04198b57eef90f34dae9a352cd24db86f2af39af571e6944ddb87456406dcc51
3
+ size 2799
checkpoint-80/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fefeb7bef91122b78b9bc617168d526673cd93739756b10d58f10116b4e614f0
3
  size 433331373
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35853cad31a133c89f44f8496a454e1218d06af54e3d34c22bb52a2d6e2fc6b3
3
  size 433331373
runs/Sep16_17-01-08_patrick-general-gpu/events.out.tfevents.1631811685.patrick-general-gpu.176909.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4364bc06f10adc14b7c40cd7d7a721eeff0fb6ebca03e7c2679010dfc0210573
3
- size 3717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31e910c2c59036b2ac4ed92926334a4a142af18cdf662c52393665993f4f5bf0
3
+ size 4188