Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +43 -0
- pytorch_model.bin +3 -0
- runs/May08_09-41-45_d2c5f2c950bf/1683538917.828508/events.out.tfevents.1683538917.d2c5f2c950bf.1240.1 +3 -0
- runs/May08_09-41-45_d2c5f2c950bf/events.out.tfevents.1683538917.d2c5f2c950bf.1240.0 +3 -0
- runs/May08_09-45-32_d2c5f2c950bf/1683539138.9599898/events.out.tfevents.1683539138.d2c5f2c950bf.1240.3 +3 -0
- runs/May08_09-45-32_d2c5f2c950bf/events.out.tfevents.1683539138.d2c5f2c950bf.1240.2 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +5 -0
- training_args.bin +3 -0
.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 sha256:130d92b37a25071d06af8fa5f6060d732cdde1a6ade598237c346047dd4e4151
|
3 |
+
size 455947197
|
runs/May08_09-41-45_d2c5f2c950bf/1683538917.828508/events.out.tfevents.1683538917.d2c5f2c950bf.1240.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:362981a322ad261743636a822342eb97d9c7941be9a32cb066bfac08c4659a2f
|
3 |
+
size 5870
|
runs/May08_09-41-45_d2c5f2c950bf/events.out.tfevents.1683538917.d2c5f2c950bf.1240.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:849913d02b2fff29ee65ebd9ed4029087102350c89d6dd2330540dc6c8a1d80f
|
3 |
+
size 4336
|
runs/May08_09-45-32_d2c5f2c950bf/1683539138.9599898/events.out.tfevents.1683539138.d2c5f2c950bf.1240.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:285811d01d4c69ca1c5cd68acced87ce8a638c2e8802c6fb1b797130a980e50f
|
3 |
+
size 5870
|
runs/May08_09-45-32_d2c5f2c950bf/events.out.tfevents.1683539138.d2c5f2c950bf.1240.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:422a81f4c0b332396da052bc843b1b9fed9c2012afb69679805d8c5a77114e1a
|
3 |
+
size 4653
|
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 sha256:494a1eda540c876e59ac1844ebb727dc25ef724ab8689e8e44099cbcc5c6f1be
|
3 |
+
size 3579
|