masha98 commited on
Commit
f2706f0
·
1 Parent(s): cf31107

small files added

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
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
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 514,
29
+ "model_type": "roberta",
30
+ "num_attention_heads": 16,
31
+ "num_hidden_layers": 24,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.15.0",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 50265
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e243230add1f2da6b97602a08743f53d1357ae2685ae2529ad10282d407a794e
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93588afb4e75bf2b0e7c63134eab6ce825f12bd253118f137983f063a2dfd61e
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>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.666666666666667,
5
+ "global_step": 3500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.67,
12
+ "learning_rate": 4.3333333333333334e-05,
13
+ "loss": 0.4627,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.33,
18
+ "learning_rate": 3.6666666666666666e-05,
19
+ "loss": 0.1953,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "learning_rate": 3e-05,
25
+ "loss": 0.135,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.67,
30
+ "learning_rate": 2.3333333333333336e-05,
31
+ "loss": 0.0733,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 3.33,
36
+ "learning_rate": 1.6666666666666667e-05,
37
+ "loss": 0.0452,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 4.0,
42
+ "learning_rate": 1e-05,
43
+ "loss": 0.0312,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 4.67,
48
+ "learning_rate": 3.3333333333333333e-06,
49
+ "loss": 0.0086,
50
+ "step": 3500
51
+ }
52
+ ],
53
+ "max_steps": 3750,
54
+ "num_train_epochs": 5,
55
+ "total_flos": 2.4270539872703616e+16,
56
+ "trial_name": null,
57
+ "trial_params": null
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b9ba8c536963d6413dd7420a8fda692af28877f999850a54d222ada60e759c1
3
+ size 2927
vocab.json ADDED
The diff for this file is too large to render. See raw diff