Harish Tayyar Madabushi commited on
Commit
9ef8561
1 Parent(s): 7521e66

added model

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.10.0.dev0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50265
29
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a184b8d1868b6dc57575cfd5f6b88b1d60c06fc8b78d38a585648f5f608a3c
3
+ size 997299320
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e051a03af0bc06776c7c3ae848ddf06519df307347e8a1e9c4643fd122b03e6
3
+ size 498677273
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5808aa7e47e521689c8577c30b9f642574ebe208389d769cc00f5a5a8ff21f4e
3
+ size 14583
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
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8006957116788321,
3
+ "best_model_checkpoint": "output-no-git/EN-OUTPUT/roberta-base/FalseTrue-0/0/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": 0.7961373329162598,
13
+ "eval_f1": 0.7856662164059511,
14
+ "eval_f1_binary": 0.8330404217926186,
15
+ "eval_f1_weighted": 0.796035677670844,
16
+ "eval_loss": 0.5423606038093567,
17
+ "eval_runtime": 1.3536,
18
+ "eval_samples_per_second": 344.258,
19
+ "eval_steps_per_second": 43.586,
20
+ "step": 104
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8068669438362122,
25
+ "eval_f1": 0.8006957116788321,
26
+ "eval_f1_binary": 0.8357664233576643,
27
+ "eval_f1_weighted": 0.8083721335484477,
28
+ "eval_loss": 1.0314300060272217,
29
+ "eval_runtime": 1.3539,
30
+ "eval_samples_per_second": 344.198,
31
+ "eval_steps_per_second": 43.579,
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:f37f483c297a8fba099623cc933f7c7411db23ee26f03bd270103913c0a2ae96
3
+ size 2735
vocab.json ADDED
The diff for this file is too large to render. See raw diff