Hugging Face's logo

gchhablani
/
bert-large-cased-finetuned-mrpc

Text Classification Transformers PyTorch TensorBoard
English bert generated_from_trainer Eval Results Inference Endpoints
Model card Files Metrics Community
2
gchhablani commited on
Commit
f526315
•
1 Parent(s): 6062ec8

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. checkpoint-917/config.json +42 -0
  2. checkpoint-917/optimizer.pt +3 -0
  3. checkpoint-917/pytorch_model.bin +3 -0
  4. checkpoint-917/rng_state.pth +3 -0
  5. checkpoint-917/scheduler.pt +3 -0
  6. checkpoint-917/special_tokens_map.json +1 -0
  7. checkpoint-917/tokenizer.json +0 -0
  8. checkpoint-917/tokenizer_config.json +1 -0
  9. checkpoint-917/trainer_state.json +33 -0
  10. checkpoint-917/training_args.bin +3 -0
  11. checkpoint-917/vocab.txt +0 -0
  12. config.json +42 -0
  13. pytorch_model.bin +3 -0
  14. runs/Sep22_06-07-26_patrick-general-gpu/1632290866.8581698/events.out.tfevents.1632290866.patrick-general-gpu.751022.1 +3 -0
  15. runs/Sep22_06-07-26_patrick-general-gpu/events.out.tfevents.1632290866.patrick-general-gpu.751022.0 +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-917/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": "mrpc",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "not_equivalent",
16
+ "1": "equivalent"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "equivalent": 1,
22
+ "not_equivalent": 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-917/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ee19327a4fcb979b419e9cd860740ab8c6bf8e9ba51257c48be7ac4eea6d31
3
+ size 2668879261
checkpoint-917/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1a79f43ae599c6cc95cd4e701bacf9c24299d5aa9ef8581befb59bb1fff8b8
3
+ size 1334486957
checkpoint-917/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e957b9c2907e618100dd2aa92afe491139ed701a8e8d049acba531c44369cd
3
+ size 14503
checkpoint-917/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b28337081bc5a0824f55e95d8b6ffb6a36f2eb2bc048b6344dd5220a40ab59e
3
+ size 623
checkpoint-917/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-917/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-917/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-917/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": 917,
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": 0.6441,
14
+ "step": 917
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.6838235294117647,
19
+ "eval_combined_score": 0.7480253018237863,
20
+ "eval_f1": 0.8122270742358079,
21
+ "eval_loss": 0.6369990706443787,
22
+ "eval_runtime": 13.1449,
23
+ "eval_samples_per_second": 31.039,
24
+ "eval_steps_per_second": 3.88,
25
+ "step": 917
26
+ }
27
+ ],
28
+ "max_steps": 4585,
29
+ "num_train_epochs": 5,
30
+ "total_flos": 3418324240687104.0,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-917/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b497fdf35eb49ca9dc4a49ae7289bd94d2105c9dfbca8e37d973c3bb6758058d
3
+ size 2799
checkpoint-917/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": "mrpc",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "not_equivalent",
16
+ "1": "equivalent"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "equivalent": 1,
22
+ "not_equivalent": 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:db1a79f43ae599c6cc95cd4e701bacf9c24299d5aa9ef8581befb59bb1fff8b8
3
+ size 1334486957
runs/Sep22_06-07-26_patrick-general-gpu/1632290866.8581698/events.out.tfevents.1632290866.patrick-general-gpu.751022.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453af1ed7e6205b6e1059831a6b96f13e8457c19072e692e695fea7e4cc16e13
3
+ size 4372
runs/Sep22_06-07-26_patrick-general-gpu/events.out.tfevents.1632290866.patrick-general-gpu.751022.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e925b4be512ba274ac69fc763849950b7ec47179b615a12d51b255d7a7e27b8
3
+ size 4025
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:b497fdf35eb49ca9dc4a49ae7289bd94d2105c9dfbca8e37d973c3bb6758058d
3
+ size 2799
vocab.txt ADDED
The diff for this file is too large to render. See raw diff