Harish Tayyar Madabushi commited on
Commit
e4d608c
1 Parent(s): 15048b5

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 sha256:0d889c05a0298edac78418204a4e0ced66e93a612dba6cd3ded187e486fd4a1d
3
+ size 866616443
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4625370000c87c264f5a8bd8da23e10be034f12ca6a49cb1186e917481c9b013
3
+ size 433334553
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c097873578041db497694ca29361a7d512128733ecc752fc2f1dca20d4a83f7
3
+ size 14647
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90aa17a68c55a5a2a5804d579de823f56b2ef158f213971b77a95930c547fdd2
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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7852336620886717,
3
+ "best_model_checkpoint": "output-no-git/EN-OUTPUT/bert-base-cased/FalseTrue-0/3/checkpoint-208",
4
+ "epoch": 2.0,
5
+ "global_step": 208,
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": 0.7768240571022034,
13
+ "eval_f1": 0.773312378386469,
14
+ "eval_f1_binary": 0.8015267175572518,
15
+ "eval_f1_weighted": 0.779488049192091,
16
+ "eval_loss": 0.594271719455719,
17
+ "eval_runtime": 1.3847,
18
+ "eval_samples_per_second": 336.535,
19
+ "eval_steps_per_second": 42.608,
20
+ "step": 104
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.7961373329162598,
25
+ "eval_f1": 0.7852336620886717,
26
+ "eval_f1_binary": 0.8336252189141856,
27
+ "eval_f1_weighted": 0.795825805428162,
28
+ "eval_loss": 0.7225714921951294,
29
+ "eval_runtime": 1.3887,
30
+ "eval_samples_per_second": 335.57,
31
+ "eval_steps_per_second": 42.486,
32
+ "step": 208
33
+ }
34
+ ],
35
+ "max_steps": 936,
36
+ "num_train_epochs": 9,
37
+ "total_flos": 437685240591360.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50121f3ca8d1e4bab406dd66cf97ff2d5315252477d4ac25f53ddb2afaa4b5e7
3
+ size 2735
vocab.txt ADDED
The diff for this file is too large to render. See raw diff