Harish Tayyar Madabushi commited on
Commit
b8c0ed9
1 Parent(s): 480c434

added model

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.10.0.dev0",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 28996
27
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3297fce24805584f29edadc38e239991e73b186594140e5bd9cd33de0b21855d
3
+ size 866616634
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b133615d72957d18c7df255bf7588c9cfabb4ca602099f6a814e263dd1c3f5
3
+ size 433334622
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c7c2862bf3707a6d3d00bb9802e4e9b1d887c9b9b34db1fa8c42198b12c72b
3
+ size 14583
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:477942c74c3089ba96f7d3d1f346e421a58618837e875bf62691456abb3463a4
3
+ size 623
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"}
trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7174127132745682,
3
+ "best_model_checkpoint": "output-no-git/EN-OUTPUT/bert-base-cased/TrueFalse-0/4/checkpoint-312",
4
+ "epoch": 3.0,
5
+ "global_step": 312,
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
+ "eval_accuracy": 0.6802574992179871,
13
+ "eval_f1": 0.6757405513447375,
14
+ "eval_f1_binary": 0.7140115163147792,
15
+ "eval_f1_weighted": 0.6841174578403261,
16
+ "eval_loss": 0.6594671010971069,
17
+ "eval_runtime": 1.3925,
18
+ "eval_samples_per_second": 334.642,
19
+ "eval_steps_per_second": 42.369,
20
+ "step": 104
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.7145922780036926,
25
+ "eval_f1": 0.6946821350279564,
26
+ "eval_f1_binary": 0.7726495726495727,
27
+ "eval_f1_weighted": 0.7117479690138037,
28
+ "eval_loss": 0.8513606786727905,
29
+ "eval_runtime": 1.3873,
30
+ "eval_samples_per_second": 335.896,
31
+ "eval_steps_per_second": 42.528,
32
+ "step": 208
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_accuracy": 0.7317596673965454,
37
+ "eval_f1": 0.7174127132745682,
38
+ "eval_f1_binary": 0.7810858143607706,
39
+ "eval_f1_weighted": 0.7313497439844237,
40
+ "eval_loss": 1.0373839139938354,
41
+ "eval_runtime": 1.3878,
42
+ "eval_samples_per_second": 335.771,
43
+ "eval_steps_per_second": 42.512,
44
+ "step": 312
45
+ }
46
+ ],
47
+ "max_steps": 936,
48
+ "num_train_epochs": 9,
49
+ "total_flos": 656527860887040.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67dbe276f211643f5c9a2bab6afb97a133c11233b64e79229c7375d5fc9113ce
3
+ size 2735
vocab.txt ADDED
The diff for this file is too large to render. See raw diff