lgw1995 commited on
Commit
696aecc
1 Parent(s): 76331cb

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "AIRI-Institute/gena-lm-bigbird-base-t2t",
3
+ "architectures": [
4
+ "BigBirdForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_type": "block_sparse",
8
+ "block_size": 64,
9
+ "bos_token_id": 1,
10
+ "classifier_dropout": null,
11
+ "eos_token_id": 2,
12
+ "gradient_checkpointing": false,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "NEGATIVE",
18
+ "1": "POSITIVE"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "NEGATIVE": 0,
24
+ "POSITIVE": 1
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 4096,
28
+ "model_type": "big_bird",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "num_random_blocks": 3,
32
+ "pad_token_id": 3,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "rescale_embeddings": false,
36
+ "sep_token_id": 66,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.28.1",
39
+ "type_vocab_size": 2,
40
+ "use_bias": true,
41
+ "use_cache": true,
42
+ "vocab_size": 32000
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221736e46fc7a85bf9cdca8993acfc0a62b9e2216097fcdad15b9a855fafc4f7
3
+ size 455950077
runs/May09_02-12-10_549f1224980c/1683598332.4039667/events.out.tfevents.1683598332.549f1224980c.6795.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29907f09ecd8d0f7af1d281ef7cf6d3608509e2e1fd8595a34cf8dd6f4a1a21d
3
+ size 5858
runs/May09_02-12-10_549f1224980c/events.out.tfevents.1683598332.549f1224980c.6795.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7ba49b89f1328d944ef79c82a68ff185c6aa8758056b7a6d8343ad6dbeb8a8
3
+ size 4478
runs/May09_02-13-28_549f1224980c/1683598411.3768811/events.out.tfevents.1683598411.549f1224980c.6795.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbfd61827edb159ff8d85be3d2e7f5deba91893eec1f3e231c375079cb530334
3
+ size 5858
runs/May09_02-13-28_549f1224980c/events.out.tfevents.1683598411.549f1224980c.6795.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01511e6906b494a38d0503405a393af13803683a1688c9ef8b3e489196dcac9
3
+ size 4795
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 1000000000000000019884624838656,
4
+ "tokenizer_class": "PreTrainedTokenizerFast"
5
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc276d8f385bc02a3cbffda0ffa3bfbe75e7ad5936c131440aba24a294bfa16
3
+ size 3579