Hugging Face's logo

gchhablani
/
bert-base-cased-finetuned-mnli

Text Classification
Transformers
PyTorch
TensorBoard
English
bert
Generated from Trainer
fnet-bert-base-comparison
Eval Results
Inference Endpoints
Model card Files Metrics Community
3
gchhablani commited on
Commit
8f4e305
•
1 Parent(s): 492fa50

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. checkpoint-24544/config.json +38 -0
  2. checkpoint-24544/optimizer.pt +3 -0
  3. checkpoint-24544/pytorch_model.bin +3 -0
  4. checkpoint-24544/rng_state.pth +3 -0
  5. checkpoint-24544/scheduler.pt +3 -0
  6. checkpoint-24544/special_tokens_map.json +1 -0
  7. checkpoint-24544/tokenizer.json +0 -0
  8. checkpoint-24544/tokenizer_config.json +1 -0
  9. checkpoint-24544/trainer_state.json +31 -0
  10. checkpoint-24544/training_args.bin +3 -0
  11. checkpoint-24544/vocab.txt +0 -0
  12. config.json +38 -0
  13. pytorch_model.bin +3 -0
  14. runs/Sep16_20-47-31_patrick-general-gpu/1631825269.5558164/events.out.tfevents.1631825269.patrick-general-gpu.214155.1 +3 -0
  15. runs/Sep16_20-47-31_patrick-general-gpu/events.out.tfevents.1631825269.patrick-general-gpu.214155.0 +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-24544/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "mnli",
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": "neutral",
16
+ "2": "contradiction"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "contradiction": 2,
22
+ "entailment": 0,
23
+ "neutral": 1
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.11.0.dev0",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 28996
38
+ }
checkpoint-24544/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba4bb5493adf0eb26497f5908c194de7c7e0a7206632006c2d2bc5a0b8ced029
3
+ size 866617117
checkpoint-24544/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc57c5898becf90b13f5874e4a708971018d911e3a1d27b20b56f50f70610389
3
+ size 433334445
checkpoint-24544/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be762c850b0fa10dadb8260ed9aa5388bc8832587117d69124237b0e31cc1862
3
+ size 14503
checkpoint-24544/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2001c64ada8fbad63d9fef31c5b12c73ccec49a590e98a18f28b62f88e283e4
3
+ size 623
checkpoint-24544/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-24544/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-24544/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-24544/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": 24544,
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": 0.5323,
14
+ "step": 24544
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.83015792154865,
19
+ "eval_loss": 0.44308236241340637,
20
+ "eval_runtime": 99.9144,
21
+ "eval_samples_per_second": 98.234,
22
+ "eval_steps_per_second": 12.281,
23
+ "step": 24544
24
+ }
25
+ ],
26
+ "max_steps": 73632,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 1.0332516536862106e+17,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-24544/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:987dcb06464bd5cbb652af2a7c46c08796060a94cd02142160b0f18314774a7d
3
+ size 2799
checkpoint-24544/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "mnli",
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": "neutral",
16
+ "2": "contradiction"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "contradiction": 2,
22
+ "entailment": 0,
23
+ "neutral": 1
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.11.0.dev0",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 28996
38
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc57c5898becf90b13f5874e4a708971018d911e3a1d27b20b56f50f70610389
3
+ size 433334445
runs/Sep16_20-47-31_patrick-general-gpu/1631825269.5558164/events.out.tfevents.1631825269.patrick-general-gpu.214155.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bbf94315596e1185f340d5301865f81716f86a6f0de483cbafbdfbab03c692f
3
+ size 4369
runs/Sep16_20-47-31_patrick-general-gpu/events.out.tfevents.1631825269.patrick-general-gpu.214155.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67859a57353573b54310427ad8dc574f45540a293707a205d68315585f58176c
3
+ size 3771
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 sha256:987dcb06464bd5cbb652af2a7c46c08796060a94cd02142160b0f18314774a7d
3
+ size 2799
vocab.txt ADDED
The diff for this file is too large to render. See raw diff